{"id":110695,"date":"2026-09-29T08:56:58","date_gmt":"2026-09-29T00:56:58","guid":{"rendered":"https:\/\/www.wsisp.com\/helps\/110695.html"},"modified":"2026-09-29T08:56:58","modified_gmt":"2026-09-29T00:56:58","slug":"%e6%8a%a5%e5%88%8a%e5%8e%86%e5%8f%b2%e6%9c%9f%e5%8f%b7%e7%b4%a2%e5%bc%95%e5%b9%b3%e5%8f%b0%e7%88%ac%e8%99%ab%e5%ae%9e%e6%88%98%ef%bc%9a%e5%b9%b4%e6%9c%88%e6%9c%9f%e5%8f%b7%e7%ba%a7%e8%81%94%e3%80%81","status":"publish","type":"post","link":"https:\/\/www.wsisp.com\/helps\/110695.html","title":{"rendered":"\u62a5\u520a\u5386\u53f2\u671f\u53f7\u7d22\u5f15\u5e73\u53f0\u722c\u866b\u5b9e\u6218\uff1a\u5e74\u6708\u671f\u53f7\u7ea7\u8054\u3001\u52a8\u6001\u65e5\u5386\u4e0e\u5386\u53f2\u5206\u9875\u89e3\u6790"},"content":{"rendered":"<p> <img decoding=\"async\" width=\"1000\" src=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/09\/20260929005652-6abb0cd402c34.png\" \/> <\/p>\n<p>\u3297\ufe0f\u672c\u671f\u5185\u5bb9\u5df2\u6536\u5f55\u81f3\u4e13\u680f\u300aPython\u722c\u866b\u5b9e\u6218\u300b&#xff0c;\u6301\u7eed\u5b8c\u5584\u77e5\u8bc6\u4f53\u7cfb\u4e0e\u9879\u76ee\u5b9e\u6218&#xff0c;\u5efa\u8bae\u5148\u8ba2\u9605\u6536\u85cf&#xff0c;\u540e\u7eed\u67e5\u9605\u66f4\u65b9\u4fbf&#xff5e; \u3299\ufe0f\u672c\u671f\u722c\u866b\u96be\u5ea6\u6307\u6570&#xff1a;\u2b50\u2b50\u2b50\u2b50\u2606&#xff08;\u9ad8\u7ea7&#xff09; &#x1f250;\u798f\u5229&#xff1a; <font color=\"red\">\u4e00\u6b21\u8ba2\u9605\u540e&#xff0c;\u4e13\u680f\u5185\u7684\u6240\u6709\u6587\u7ae0\u53ef\u6c38\u4e45\u514d\u8d39\u770b&#xff0c;\u6301\u7eed\u66f4\u65b0\u4e2d&#xff0c;\u4fdd\u5e951000&#043;(\u7bc7)\u786c\u6838\u5b9e\u6218\u5185\u5bb9\u3002<\/font><\/p>\n<\/p>\n<h4>\u5168\u6587\u76ee\u5f55&#xff1a;<\/h4>\n<ul>\n<li>\n<ul>\n<li>&#x1f31f; \u5f00\u7bc7\u8bed<\/li>\n<li>0\ufe0f\u20e3 \u524d\u8a00&#xff08;Preface&#xff09;<\/li>\n<li>1\ufe0f\u20e3 \u6458\u8981&#xff08;Abstract&#xff09;<\/li>\n<li>2\ufe0f\u20e3 \u80cc\u666f\u4e0e\u9700\u6c42&#xff08;Why&#xff09;<\/li>\n<li>\n<ul>\n<li>2.1 \u4e3a\u4ec0\u4e48\u8981\u722c\u62a5\u520a\u5386\u53f2\u671f\u53f7\u7d22\u5f15<\/li>\n<li>2.2 \u76ee\u6807\u7ad9\u70b9\u7684\u5178\u578b\u7ed3\u6784<\/li>\n<li>2.3 \u76ee\u6807\u5b57\u6bb5\u6e05\u5355<\/li>\n<\/ul>\n<\/li>\n<li>3\ufe0f\u20e3 \u5408\u89c4\u4e0e\u6ce8\u610f\u4e8b\u9879<\/li>\n<li>\n<ul>\n<li>3.1 robots.txt \u57fa\u672c\u8bf4\u660e<\/li>\n<li>3.2 \u9891\u7387\u63a7\u5236<\/li>\n<li>3.3 \u4e0d\u91c7\u96c6\u654f\u611f\u4fe1\u606f<\/li>\n<li>3.4 \u4e0d\u7ed5\u8fc7\u4ed8\u8d39\u6216\u767b\u5f55\u9650\u5236<\/li>\n<\/ul>\n<\/li>\n<li>4\ufe0f\u20e3 \u6280\u672f\u9009\u578b\u4e0e\u6574\u4f53\u6d41\u7a0b&#xff08;What\/How&#xff09;<\/li>\n<li>\n<ul>\n<li>4.1 \u9759\u6001\u3001\u52a8\u6001\u548c API \u7684\u5224\u65ad<\/li>\n<li>4.2 \u4e3a\u4ec0\u4e48\u4e0d\u4e00\u5f00\u59cb\u5c31\u7528 Scrapy<\/li>\n<li>4.3 \u6574\u4f53\u6d41\u7a0b<\/li>\n<\/ul>\n<\/li>\n<li>5\ufe0f\u20e3 \u73af\u5883\u51c6\u5907\u4e0e\u4f9d\u8d56\u5b89\u88c5<\/li>\n<li>\n<ul>\n<li>5.1 Python \u7248\u672c<\/li>\n<li>5.2 \u521b\u5efa\u865a\u62df\u73af\u5883<\/li>\n<li>5.3 \u5b89\u88c5\u4f9d\u8d56<\/li>\n<li>5.4 \u63a8\u8350\u9879\u76ee\u7ed3\u6784<\/li>\n<li>5.5 requirements.txt<\/li>\n<\/ul>\n<\/li>\n<li>6\ufe0f\u20e3 \u6838\u5fc3\u5b9e\u73b0&#xff1a;\u8bf7\u6c42\u5c42&#xff08;Fetcher&#xff09;<\/li>\n<li>\n<ul>\n<li>6.1 headers \u8bbe\u7f6e<\/li>\n<li>6.2 timeout<\/li>\n<li>6.3 session\/cookie<\/li>\n<li>6.4 \u5931\u8d25\u5904\u7406&#xff1a;\u91cd\u8bd5\u4e0e\u9000\u907f<\/li>\n<\/ul>\n<\/li>\n<li>7\ufe0f\u20e3 \u6838\u5fc3\u5b9e\u73b0&#xff1a;\u89e3\u6790\u5c42&#xff08;Parser&#xff09;<\/li>\n<li>\n<ul>\n<li>7.1 \u89e3\u6790\u65b9\u5f0f\u9009\u62e9<\/li>\n<li>7.2 \u5217\u8868\u9875\u5982\u4f55\u62ff\u8be6\u60c5\u94fe\u63a5<\/li>\n<li>7.3 \u8be6\u60c5\u9875\u5982\u4f55\u62bd\u5b57\u6bb5<\/li>\n<li>7.4 \u7f3a\u5931\u5b57\u6bb5\u600e\u4e48\u529e<\/li>\n<\/ul>\n<\/li>\n<li>8\ufe0f\u20e3 \u6570\u636e\u5b58\u50a8\u4e0e\u5bfc\u51fa&#xff08;Storage&#xff09;<\/li>\n<li>\n<ul>\n<li>8.1 \u4e3a\u4ec0\u4e48\u9009\u62e9 SQLite \u8d77\u6b65<\/li>\n<li>8.2 \u5b57\u6bb5\u6620\u5c04\u8868<\/li>\n<li>8.3 \u53bb\u91cd\u7b56\u7565<\/li>\n<\/ul>\n<\/li>\n<li>9\ufe0f\u20e3 \u5b8c\u6574\u53ef\u8fd0\u884c\u4ee3\u7801<\/li>\n<li>\n<ul>\n<li>9.1 \u8fd0\u884c\u7ed3\u679c<\/li>\n<\/ul>\n<\/li>\n<li>10. \u771f\u5b9e\u7ad9\u70b9\u6539\u9020\u65b9\u6cd5<\/li>\n<li>\n<ul>\n<li>10.1 \u5173\u95ed\u6837\u4f8b\u6a21\u5f0f<\/li>\n<li>10.2 \u4fee\u6539\u65e5\u5386 URL \u89c4\u5219<\/li>\n<li>10.3 \u4fee\u6539 CSS \u9009\u62e9\u5668<\/li>\n<\/ul>\n<\/li>\n<li>11. \u5e74\u6708\u671f\u53f7\u7ea7\u8054\u89e3\u6790<\/li>\n<li>\n<ul>\n<li>11.1 \u5e74\u4efd\u5c42<\/li>\n<li>11.2 \u6708\u4efd\u5c42<\/li>\n<li>11.3 \u65e5\u671f\u5c42<\/li>\n<li>11.4 \u671f\u53f7\u5c42<\/li>\n<li>11.5 \u5206\u9875\u5c42<\/li>\n<\/ul>\n<\/li>\n<li>12. \u52a8\u6001\u65e5\u5386\u89e3\u6790<\/li>\n<li>\n<ul>\n<li>12.1 \u4ec0\u4e48\u662f\u52a8\u6001\u65e5\u5386<\/li>\n<li>12.2 JSON \u65e5\u5386\u89e3\u6790\u793a\u4f8b<\/li>\n<li>12.3 \u53ea\u6709\u6e32\u67d3\u7ed3\u679c&#xff0c;\u6ca1\u6709\u63a5\u53e3\u600e\u4e48\u529e<\/li>\n<\/ul>\n<\/li>\n<li>13. \u5386\u53f2\u5206\u9875\u89e3\u6790\u7ec6\u8282<\/li>\n<li>\n<ul>\n<li>13.1 \u4ece\u7b2c\u4e00\u9875\u987a\u7740\u4e0b\u4e00\u9875\u8d70<\/li>\n<li>13.2 \u6839\u636e\u603b\u9875\u6570\u6784\u9020 URL<\/li>\n<li>13.3 \u7a7a\u9875\u5904\u7406<\/li>\n<\/ul>\n<\/li>\n<li>14. \u6570\u636e\u6e05\u6d17\u7b56\u7565<\/li>\n<li>\n<ul>\n<li>14.1 \u65e5\u671f\u6e05\u6d17<\/li>\n<li>14.2 \u6570\u5b57\u5316\u72b6\u6001\u6e05\u6d17<\/li>\n<li>14.3 URL \u8865\u5168<\/li>\n<\/ul>\n<\/li>\n<li>15. \u8fd0\u884c\u65b9\u5f0f\u4e0e\u7ed3\u679c\u5c55\u793a<\/li>\n<li>\n<ul>\n<li>15.1 \u542f\u52a8\u547d\u4ee4<\/li>\n<li>15.2 \u8f93\u51fa\u4f4d\u7f6e<\/li>\n<li>15.3 \u67e5\u770b SQLite \u6570\u636e<\/li>\n<li>15.4 \u793a\u4f8b\u7ed3\u679c<\/li>\n<\/ul>\n<\/li>\n<li>16. \u5e38\u89c1\u95ee\u9898\u4e0e\u6392\u9519<\/li>\n<li>\n<ul>\n<li>16.1 403 \u600e\u4e48\u529e<\/li>\n<li>16.2 429 \u600e\u4e48\u529e<\/li>\n<li>16.3 HTML \u6293\u5230\u7a7a\u58f3\u600e\u4e48\u529e<\/li>\n<li>16.4 \u89e3\u6790\u62a5\u9519\u600e\u4e48\u529e<\/li>\n<li>16.5 \u7f16\u7801\u4e71\u7801\u600e\u4e48\u529e<\/li>\n<li>16.6 \u65e5\u671f\u89e3\u6790\u5931\u8d25\u600e\u4e48\u529e<\/li>\n<li>16.7 \u91cd\u590d\u6570\u636e\u592a\u591a\u600e\u4e48\u529e<\/li>\n<li>16.8 \u4e0b\u4e00\u9875\u6b7b\u5faa\u73af\u600e\u4e48\u529e<\/li>\n<\/ul>\n<\/li>\n<li>17. \u8fdb\u9636\u4f18\u5316<\/li>\n<li>\n<ul>\n<li>17.1 \u5e76\u53d1\u91c7\u96c6<\/li>\n<li>17.2 asyncio<\/li>\n<li>17.3 Scrapy \u6539\u9020\u65b9\u5411<\/li>\n<li>17.4 \u65ad\u70b9\u7eed\u8dd1<\/li>\n<li>17.5 \u6e38\u6807\u8bb0\u5f55<\/li>\n<li>17.6 \u65e5\u5fd7\u4e0e\u76d1\u63a7<\/li>\n<li>17.7 \u5b9a\u65f6\u4efb\u52a1<\/li>\n<li>17.8 \u589e\u91cf\u91c7\u96c6<\/li>\n<\/ul>\n<\/li>\n<li>18. \u5de5\u7a0b\u5316\u62c6\u5206\u5efa\u8bae<\/li>\n<li>\n<ul>\n<li>18.1 config.py<\/li>\n<li>18.2 crawler\/fetcher.py<\/li>\n<li>18.3 crawler\/parser.py<\/li>\n<li>18.4 crawler\/storage.py<\/li>\n<\/ul>\n<\/li>\n<li>19. \u5b57\u6bb5\u8d28\u91cf\u68c0\u67e5<\/li>\n<li>\n<ul>\n<li>19.1 \u68c0\u67e5\u7a7a\u5b57\u6bb5<\/li>\n<li>19.2 \u68c0\u67e5\u65e5\u671f\u8303\u56f4<\/li>\n<li>19.3 \u68c0\u67e5\u91cd\u590d\u4e3b\u9898<\/li>\n<li>19.4 \u68c0\u67e5\u72b6\u6001\u5206\u5e03<\/li>\n<\/ul>\n<\/li>\n<li>20. MySQL \u5b58\u50a8\u6269\u5c55\u793a\u4f8b<\/li>\n<li>21. \u9009\u62e9\u5668\u7a33\u5b9a\u6027\u5efa\u8bae<\/li>\n<li>\n<ul>\n<li>21.1 \u4e0d\u5efa\u8bae\u7684\u5199\u6cd5<\/li>\n<li>21.2 \u63a8\u8350\u5199\u6cd5<\/li>\n<li>21.3 \u591a\u9009\u62e9\u5668\u515c\u5e95<\/li>\n<\/ul>\n<\/li>\n<li>22. \u8bf7\u6c42\u5931\u8d25 URL \u7684\u8865\u6293<\/li>\n<li>23. \u9762\u5411\u771f\u5b9e\u4e1a\u52a1\u7684\u91c7\u96c6\u8fb9\u754c<\/li>\n<li>24. \u603b\u7ed3\u4e0e\u5ef6\u4f38\u9605\u8bfb<\/li>\n<li>&#x1f31f; \u6587\u672b<\/li>\n<li>\n<ul>\n<li>\u2705 \u4e13\u680f\u6301\u7eed\u66f4\u65b0\u4e2d&#xff5c;\u5efa\u8bae\u6536\u85cf &#043; \u8ba2\u9605<\/li>\n<li>\u2705 \u4e92\u52a8\u5f81\u96c6<\/li>\n<li>\u2705 \u514d\u8d23\u58f0\u660e<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<h3>&#x1f31f; \u5f00\u7bc7\u8bed<\/h3>\n<p>\u54c8\u55bd&#xff0c;\u5404\u4f4d\u5c0f\u4f19\u4f34\u4eec\u4f60\u4eec\u597d\u5440&#xff5e;\u6211\u662f\u3010\u55b5\u624b\u3011\u3002 \u8fd0\u8425\u793e\u533a&#xff1a; C\u7ad9 \/ \u6398\u91d1 \/ \u817e\u8baf\u4e91 \/ \u963f\u91cc\u4e91 \/ \u534e\u4e3a\u4e91 \/ 51CTO \u6b22\u8fce\u5927\u5bb6\u5e38\u6765\u901b\u901b&#xff0c;\u4e00\u8d77\u5b66\u4e60&#xff0c;\u4e00\u8d77\u8fdb\u6b65&#xff5e;&#x1f31f;<\/p>\n<p>\u2003\u2003\u6211\u957f\u671f\u4e13\u6ce8 Python \u722c\u866b\u5de5\u7a0b\u5316\u5b9e\u6218&#xff0c;\u4e3b\u7406\u4e13\u680f&#x1f449; \u300aPython\u722c\u866b\u5b9e\u6218\u300b&#xff1a;\u4ece\u91c7\u96c6\u7b56\u7565\u5230\u53cd\u722c\u5bf9\u6297&#xff0c;\u4ece\u6570\u636e\u6e05\u6d17\u5230\u5206\u5e03\u5f0f\u8c03\u5ea6&#xff0c;\u6301\u7eed\u8f93\u51fa\u53ef\u590d\u7528\u7684\u65b9\u6cd5\u8bba\u4e0e\u53ef\u843d\u5730\u6848\u4f8b\u3002\u5185\u5bb9\u4e3b\u6253\u4e00\u4e2a\u201c\u80fd\u8dd1\u3001\u80fd\u7528\u3001\u80fd\u6269\u5c55\u201d&#xff0c;\u8ba9\u6570\u636e\u4ef7\u503c\u771f\u6b63\u505a\u5230\u2014\u2014\u6293\u5f97\u5230\u3001\u6d17\u5f97\u51c0\u3001\u7528\u5f97\u4e0a\u3002<\/p>\n<p>\u2003\u2003&#x1f4cc; \u4e13\u680f\u98df\u7528\u6307\u5357&#xff08;\u5efa\u8bae\u6536\u85cf&#xff09;<\/p>\n<ul>\n<li>\u2705 \u5165\u95e8\u57fa\u7840&#xff1a;\u73af\u5883\u642d\u5efa \/ \u8bf7\u6c42\u4e0e\u89e3\u6790 \/ \u6570\u636e\u843d\u5e93<\/li>\n<li>\u2705 \u8fdb\u9636\u63d0\u5347&#xff1a;\u767b\u5f55\u9274\u6743 \/ \u52a8\u6001\u6e32\u67d3 \/ \u53cd\u722c\u5bf9\u6297<\/li>\n<li>\u2705 \u5de5\u7a0b\u5b9e\u6218&#xff1a;\u5f02\u6b65\u5e76\u53d1 \/ \u5206\u5e03\u5f0f\u8c03\u5ea6 \/ \u76d1\u63a7\u4e0e\u5bb9\u9519<\/li>\n<li>\u2705 \u9879\u76ee\u843d\u5730&#xff1a;\u6570\u636e\u6cbb\u7406 \/ \u53ef\u89c6\u5316\u5206\u6790 \/ \u573a\u666f\u5316\u5e94\u7528<\/li>\n<\/ul>\n<p>&#x1f4e3; \u4e13\u680f\u63a8\u5e7f\u65f6\u95f4&#xff1a;\u5982\u679c\u4f60\u60f3\u7cfb\u7edf\u5b66\u722c\u866b&#xff0c;\u800c\u4e0d\u662f\u788e\u7247\u5316\u4e1c\u62fc\u897f\u51d1&#xff0c;\u6b22\u8fce\u8ba2\u9605\u4e13\u680f&#x1f449;\u300aPython\u722c\u866b\u5b9e\u6218\u300b&#x1f448;&#xff0c;<font color=\"red\">\u4e00\u6b21\u8ba2\u9605\u540e&#xff0c;\u4e13\u680f\u5185\u7684\u6240\u6709\u6587\u7ae0\u53ef\u6c38\u4e45\u514d\u8d39\u9605\u8bfb&#xff0c;\u6301\u7eed\u66f4\u65b0\u4e2d\u3002<\/font> \u2003\u2003 &#x1f495;\u8ba2\u9605\u540e\u66f4\u65b0\u4f1a\u4f18\u5148\u63a8\u9001&#xff0c;\u6309\u76ee\u5f55\u5b66\u4e60\u66f4\u9ad8\u6548&#x1f4af;&#xff5e;<\/p>\n<h3>0\ufe0f\u20e3 \u524d\u8a00&#xff08;Preface&#xff09;<\/h3>\n<p>\u8fd9\u7bc7\u6587\u7ae0\u8981\u505a\u7684\u4e8b\u60c5\u5f88\u660e\u786e&#xff1a;\u7528 Python \u6293\u53d6\u4e00\u4e2a\u201c\u62a5\u520a\u5386\u53f2\u671f\u53f7\u7d22\u5f15\u5e73\u53f0\u201d\u7684\u516c\u5f00\u7d22\u5f15\u6570\u636e&#xff0c;\u5b57\u6bb5\u5305\u62ec\u62a5\u520a\u540d\u3001\u671f\u53f7\u3001\u51fa\u7248\u65e5\u671f\u3001\u680f\u76ee\u3001\u4e3b\u9898\u3001\u6570\u5b57\u5316\u72b6\u6001\u548c\u8be6\u60c5\u94fe\u63a5&#xff0c;\u6700\u540e\u628a\u7ed3\u679c\u4fdd\u5b58\u5230 SQLite \u4e0e CSV \u6587\u4ef6\u4e2d&#xff0c;\u65b9\u4fbf\u540e\u7eed\u68c0\u7d22\u3001\u5206\u6790\u548c\u5f52\u6863\u3002<\/p>\n<p>\u8bfb\u5b8c\u8fd9\u7bc7\u6587\u7ae0&#xff0c;\u4f60\u53ef\u4ee5\u83b7\u5f97&#xff1a;<\/p>\n<li>\u4e00\u5957\u9002\u5408\u62a5\u520a\u3001\u671f\u520a\u3001\u516c\u544a\u3001\u6863\u6848\u7c7b\u7f51\u7ad9\u7684\u901a\u7528\u722c\u866b\u8bbe\u8ba1\u601d\u8def\u3002<\/li>\n<li>\u4e00\u4e2a\u80fd\u591f\u5904\u7406\u201c\u5e74\u4efd \u2192 \u6708\u4efd \u2192 \u671f\u53f7 \u2192 \u8be6\u60c5\u9875\u201d\u7684\u7ea7\u8054\u91c7\u96c6\u8303\u5f0f\u3002<\/li>\n<li>\u4e00\u4efd\u53ef\u672c\u5730\u8fd0\u884c\u3001\u53ef\u6539\u9020\u6210\u771f\u5b9e\u7ad9\u70b9\u722c\u866b\u7684\u5b8c\u6574 Python \u793a\u4f8b\u4ee3\u7801\u3002<\/li>\n<p>\u8fd9\u4e0d\u662f\u4e00\u7bc7\u4e3a\u4e86\u70ab\u6280\u800c\u5199\u7684\u6587\u7ae0\u3002\u62a5\u520a\u5386\u53f2\u6570\u636e\u7684\u722c\u53d6\u5e76\u4e0d\u4e00\u5b9a\u96be\u5728\u8bf7\u6c42\u672c\u8eab&#xff0c;\u771f\u6b63\u9ebb\u70e6\u7684\u662f\u7ed3\u6784&#xff1a;\u6709\u4e9b\u7ad9\u70b9\u6309\u5e74\u4efd\u5f52\u6863&#xff0c;\u6709\u4e9b\u7ad9\u70b9\u6309\u6708\u4efd\u63d0\u4f9b\u65e5\u5386&#xff0c;\u6709\u4e9b\u7ad9\u70b9\u7684\u5386\u53f2\u5206\u9875\u89c4\u5219\u8fd8\u5e26\u7740\u8001\u7cfb\u7edf\u7684\u75d5\u8ff9\u3002\u6211\u7684\u7ecf\u9a8c\u662f&#xff0c;\u5199\u8fd9\u79cd\u722c\u866b\u4e0d\u80fd\u4e00\u4e0a\u6765\u5c31\u731b\u5806\u5e76\u53d1&#xff0c;\u5148\u628a\u201c\u8def\u5f84\u201d\u548c\u201c\u6570\u636e\u6a21\u578b\u201d\u60f3\u6e05\u695a&#xff0c;\u540e\u9762\u53cd\u800c\u4f1a\u7a33\u5f88\u591a\u3002<\/p>\n<hr \/>\n<h3>1\ufe0f\u20e3 \u6458\u8981&#xff08;Abstract&#xff09;<\/h3>\n<p>\u672c\u6587\u56f4\u7ed5\u201c\u62a5\u520a\u5386\u53f2\u671f\u53f7\u7d22\u5f15\u5e73\u53f0\u201d\u8bbe\u8ba1\u5e76\u5b9e\u73b0\u4e00\u4e2a Python \u722c\u866b&#xff0c;\u4f7f\u7528 requests\u3001BeautifulSoup\u3001lxml\u3001SQLite \u548c pandas \u5b8c\u6210\u516c\u5f00\u7d22\u5f15\u9875\u91c7\u96c6\u3001\u8be6\u60c5\u9875\u89e3\u6790\u3001\u5b57\u6bb5\u6e05\u6d17\u3001\u53bb\u91cd\u5b58\u50a8\u4e0e CSV \u5bfc\u51fa\u3002<\/p>\n<p>\u4f60\u5c06\u5b66\u5230&#xff1a;<\/p>\n<li>\u5982\u4f55\u5904\u7406\u5e74\u6708\u671f\u53f7\u7ea7\u8054\u7ed3\u6784&#xff0c;\u6bd4\u5982\u5148\u6293\u5e74\u4efd&#xff0c;\u518d\u6293\u6708\u4efd&#xff0c;\u518d\u8fdb\u5165\u5bf9\u5e94\u671f\u53f7\u5217\u8868\u3002<\/li>\n<li>\u5982\u4f55\u89e3\u6790\u52a8\u6001\u65e5\u5386\u548c\u5386\u53f2\u5206\u9875&#xff0c;\u5c24\u5176\u662f\u201c\u67d0\u6708\u6709\u591a\u5c11\u671f\u3001\u6bcf\u9875\u6709\u54ea\u4e9b\u680f\u76ee\u6587\u7ae0\u201d\u7684\u7ed3\u6784\u3002<\/li>\n<li>\u5982\u4f55\u8bbe\u8ba1\u4e00\u4e2a\u7a33\u5b9a\u3001\u53ef\u7ef4\u62a4\u3001\u53ef\u6269\u5c55\u7684\u722c\u866b\u5de5\u7a0b&#xff0c;\u800c\u4e0d\u662f\u5199\u4e00\u4e2a\u53ea\u80fd\u8dd1\u4e00\u6b21\u7684\u4e34\u65f6\u4ee3\u7801\u3002<\/li>\n<p>\u6700\u7ec8\u4ea7\u51fa\u662f\u4e00\u5f20\u7ed3\u6784\u5316\u6570\u636e\u8868&#xff0c;\u6838\u5fc3\u5b57\u6bb5\u5982\u4e0b&#xff1a;<\/p>\n<table>\n<tr>\u5b57\u6bb5\u8bf4\u660e<\/tr>\n<tbody>\n<tr>\n<td>\u62a5\u520a\u540d<\/td>\n<td>\u62a5\u7eb8\u6216\u671f\u520a\u540d\u79f0<\/td>\n<\/tr>\n<tr>\n<td>\u671f\u53f7<\/td>\n<td>\u7b2c\u51e0\u671f\u3001\u603b\u7b2c\u51e0\u671f\u6216\u9875\u9762\u663e\u793a\u7684\u671f\u53f7<\/td>\n<\/tr>\n<tr>\n<td>\u51fa\u7248\u65e5\u671f<\/td>\n<td>\u8be5\u671f\u51fa\u7248\u65e5\u671f<\/td>\n<\/tr>\n<tr>\n<td>\u680f\u76ee<\/td>\n<td>\u6587\u7ae0\u6216\u7d22\u5f15\u6240\u5c5e\u680f\u76ee<\/td>\n<\/tr>\n<tr>\n<td>\u4e3b\u9898<\/td>\n<td>\u6587\u7ae0\u6807\u9898\u3001\u4e3b\u9898\u8bcd\u6216\u7d22\u5f15\u4e3b\u9898<\/td>\n<\/tr>\n<tr>\n<td>\u6570\u5b57\u5316\u72b6\u6001<\/td>\n<td>\u5df2\u6570\u5b57\u5316\u3001\u5f85\u6570\u5b57\u5316\u3001\u4ec5\u76ee\u5f55\u3001\u7f3a\u9875\u7b49<\/td>\n<\/tr>\n<tr>\n<td>\u94fe\u63a5<\/td>\n<td>\u8be6\u60c5\u9875 URL<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<hr \/>\n<h3>2\ufe0f\u20e3 \u80cc\u666f\u4e0e\u9700\u6c42&#xff08;Why&#xff09;<\/h3>\n<h4>2.1 \u4e3a\u4ec0\u4e48\u8981\u722c\u62a5\u520a\u5386\u53f2\u671f\u53f7\u7d22\u5f15<\/h4>\n<p>\u62a5\u520a\u5386\u53f2\u7d22\u5f15\u6709\u5f88\u9ad8\u7684\u4fe1\u606f\u4ef7\u503c\u3002\u5f88\u591a\u65f6\u5019&#xff0c;\u6211\u4eec\u5e76\u4e0d\u662f\u4e3a\u4e86\u6293\u53d6\u6b63\u6587\u5185\u5bb9&#xff0c;\u800c\u662f\u4e3a\u4e86\u5efa\u7acb\u4e00\u4e2a\u201c\u53ef\u641c\u7d22\u7684\u76ee\u5f55\u201d\u3002\u6bd4\u5982&#xff1a;<\/p>\n<li>\u505a\u8d44\u6599\u68c0\u7d22&#xff1a;\u6309\u65f6\u95f4\u3001\u680f\u76ee\u3001\u4e3b\u9898\u5feb\u901f\u5b9a\u4f4d\u67d0\u4e00\u671f\u5185\u5bb9\u3002<\/li>\n<li>\u505a\u6570\u636e\u5206\u6790&#xff1a;\u7edf\u8ba1\u67d0\u4e2a\u4e3b\u9898\u5728\u4e0d\u540c\u5e74\u4efd\u3001\u6708\u4efd\u51fa\u73b0\u7684\u9891\u7387\u3002<\/li>\n<li>\u505a\u4fe1\u606f\u805a\u5408&#xff1a;\u628a\u5206\u6563\u5728\u7f51\u7ad9\u5386\u53f2\u9875\u91cc\u7684\u671f\u53f7\u7edf\u4e00\u6574\u7406\u6210\u7ed3\u6784\u5316\u6570\u636e\u3002<\/li>\n<li>\u505a\u81ea\u52a8\u5316\u5f52\u6863&#xff1a;\u5b9a\u671f\u6293\u53d6\u65b0\u589e\u671f\u53f7&#xff0c;\u51cf\u5c11\u624b\u5de5\u7ef4\u62a4\u8868\u683c\u7684\u5de5\u4f5c\u91cf\u3002<\/li>\n<p>\u6211\u4e2a\u4eba\u6bd4\u8f83\u559c\u6b22\u628a\u8fd9\u7c7b\u722c\u866b\u79f0\u4e3a\u201c\u7d22\u5f15\u578b\u722c\u866b\u201d\u3002\u5b83\u548c\u6293\u7535\u5546\u5546\u54c1\u3001\u65b0\u95fb\u5217\u8868\u4e0d\u592a\u4e00\u6837\u3002\u7d22\u5f15\u578b\u722c\u866b\u7684\u91cd\u70b9\u901a\u5e38\u4e0d\u662f\u201c\u6293\u5f97\u8d8a\u591a\u8d8a\u597d\u201d&#xff0c;\u800c\u662f\u201c\u5b57\u6bb5\u8981\u51c6\u3001\u5c42\u7ea7\u8981\u6e05\u695a\u3001\u53ef\u4ee5\u590d\u67e5\u6765\u6e90\u201d\u3002<\/p>\n<h4>2.2 \u76ee\u6807\u7ad9\u70b9\u7684\u5178\u578b\u7ed3\u6784<\/h4>\n<p>\u672c\u6587\u5047\u8bbe\u76ee\u6807\u7ad9\u70b9\u662f\u4e00\u4e2a\u516c\u5f00\u7684\u62a5\u520a\u5386\u53f2\u671f\u53f7\u7d22\u5f15\u5e73\u53f0&#xff0c;\u9875\u9762\u7ed3\u6784\u5927\u81f4\u5982\u4e0b&#xff1a;<\/p>\n<p>\u9996\u9875<br \/>\n \u251c\u2500\u2500 \u5e74\u4efd\u5f52\u6863<br \/>\n \u2502    \u251c\u2500\u2500 2021<br \/>\n \u2502    \u251c\u2500\u2500 2022<br \/>\n \u2502    \u251c\u2500\u2500 2023<br \/>\n \u2502    \u2514\u2500\u2500 2024<br \/>\n \u2502<br \/>\n \u251c\u2500\u2500 \u6708\u4efd\u65e5\u5386<br \/>\n \u2502    \u251c\u2500\u2500 2024-01<br \/>\n \u2502    \u251c\u2500\u2500 2024-02<br \/>\n \u2502    \u251c\u2500\u2500 2024-03<br \/>\n \u2502    \u2514\u2500\u2500 &#8230;<br \/>\n \u2502<br \/>\n \u251c\u2500\u2500 \u671f\u53f7\u5217\u8868\u9875<br \/>\n \u2502    \u251c\u2500\u2500 \u7b2c 1 \u9875<br \/>\n \u2502    \u251c\u2500\u2500 \u7b2c 2 \u9875<br \/>\n \u2502    \u2514\u2500\u2500 \u7b2c N \u9875<br \/>\n \u2502<br \/>\n \u2514\u2500\u2500 \u8be6\u60c5\u9875<br \/>\n      \u251c\u2500\u2500 \u62a5\u520a\u540d<br \/>\n      \u251c\u2500\u2500 \u671f\u53f7<br \/>\n      \u251c\u2500\u2500 \u51fa\u7248\u65e5\u671f<br \/>\n      \u251c\u2500\u2500 \u680f\u76ee<br \/>\n      \u251c\u2500\u2500 \u4e3b\u9898<br \/>\n      \u251c\u2500\u2500 \u6570\u5b57\u5316\u72b6\u6001<br \/>\n      \u2514\u2500\u2500 \u94fe\u63a5<\/p>\n<p>\u5f88\u591a\u5386\u53f2\u62a5\u520a\u7ad9\u70b9\u5e76\u4e0d\u662f\u73b0\u4ee3\u5316\u7684\u524d\u540e\u7aef\u5206\u79bb\u67b6\u6784\u3002\u6709\u7684\u9875\u9762\u662f\u7eaf HTML&#xff0c;\u6709\u7684\u9875\u9762\u7528 JavaScript \u751f\u6210\u65e5\u5386&#xff0c;\u6709\u7684\u5219\u9690\u85cf\u4e86\u4e00\u4e2a\u63a5\u53e3\u3002\u771f\u5b9e\u5de5\u4f5c\u4e2d&#xff0c;\u6211\u4e00\u822c\u4f1a\u5148\u7528\u6d4f\u89c8\u5668\u5f00\u53d1\u8005\u5de5\u5177\u89c2\u5bdf\u4e09\u4ef6\u4e8b&#xff1a;<\/p>\n<li>\u5207\u6362\u5e74\u4efd\u548c\u6708\u4efd\u65f6&#xff0c;\u9875\u9762\u662f\u5426\u771f\u7684\u5237\u65b0\u3002<\/li>\n<li>\u70b9\u51fb\u65e5\u5386\u65e5\u671f\u65f6&#xff0c;\u6d4f\u89c8\u5668\u662f\u5426\u8bf7\u6c42\u4e86\u63a5\u53e3\u3002<\/li>\n<li>\u7ffb\u9875\u65f6 URL \u662f\u5426\u6709\u660e\u786e\u53c2\u6570&#xff0c;\u6bd4\u5982 page&#061;2\u3001year&#061;2024\u3001month&#061;05\u3002<\/li>\n<h4>2.3 \u76ee\u6807\u5b57\u6bb5\u6e05\u5355<\/h4>\n<p>\u672c\u9879\u76ee\u91c7\u96c6\u5b57\u6bb5\u5982\u4e0b&#xff1a;<\/p>\n<table>\n<tr>\u5b57\u6bb5\u540d\u82f1\u6587\u5b57\u6bb5\u8bf4\u660e<\/tr>\n<tbody>\n<tr>\n<td>\u62a5\u520a\u540d<\/td>\n<td>newspaper_name<\/td>\n<td>\u62a5\u520a\u3001\u671f\u520a\u6216\u5e73\u53f0\u5c55\u793a\u540d\u79f0<\/td>\n<\/tr>\n<tr>\n<td>\u671f\u53f7<\/td>\n<td>issue_no<\/td>\n<td>\u5982\u201c2024\u5e74\u7b2c05\u671f\u201d\u201c\u603b\u7b2c238\u671f\u201d<\/td>\n<\/tr>\n<tr>\n<td>\u51fa\u7248\u65e5\u671f<\/td>\n<td>publish_date<\/td>\n<td>\u6807\u51c6\u5316\u4e3a YYYY-MM-DD<\/td>\n<\/tr>\n<tr>\n<td>\u680f\u76ee<\/td>\n<td>column_name<\/td>\n<td>\u6587\u7ae0\u6216\u7d22\u5f15\u6240\u5c5e\u680f\u76ee<\/td>\n<\/tr>\n<tr>\n<td>\u4e3b\u9898<\/td>\n<td>topic<\/td>\n<td>\u6807\u9898\u3001\u4e3b\u9898\u6216\u7d22\u5f15\u540d\u79f0<\/td>\n<\/tr>\n<tr>\n<td>\u6570\u5b57\u5316\u72b6\u6001<\/td>\n<td>digitization_status<\/td>\n<td>\u5df2\u6570\u5b57\u5316\u3001\u672a\u6570\u5b57\u5316\u3001\u4ec5\u76ee\u5f55\u7b49<\/td>\n<\/tr>\n<tr>\n<td>\u94fe\u63a5<\/td>\n<td>url<\/td>\n<td>\u8be6\u60c5\u9875\u5b8c\u6574\u94fe\u63a5<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<hr \/>\n<h3>3\ufe0f\u20e3 \u5408\u89c4\u4e0e\u6ce8\u610f\u4e8b\u9879<\/h3>\n<p>\u722c\u866b\u4e0d\u662f\u201c\u770b\u5230\u9875\u9762\u5c31\u968f\u4fbf\u6293\u201d\u3002\u6280\u672f\u4e0a\u80fd\u505a\u5230&#xff0c;\u4e0d\u4ee3\u8868\u573a\u666f\u4e0a\u5c31\u4e00\u5b9a\u5408\u9002\u3002\u5c24\u5176\u662f\u62a5\u520a\u3001\u6863\u6848\u3001\u5386\u53f2\u6587\u732e\u7c7b\u7ad9\u70b9&#xff0c;\u5f88\u591a\u5c5e\u4e8e\u516c\u5171\u670d\u52a1\u3001\u5b66\u672f\u673a\u6784\u6216\u8d44\u6599\u9986\u7cfb\u7edf&#xff0c;\u66f4\u5e94\u8be5\u63a7\u5236\u8bf7\u6c42\u9891\u7387&#xff0c;\u5c0a\u91cd\u7ad9\u70b9\u89c4\u5219\u3002<\/p>\n<h4>3.1 robots.txt \u57fa\u672c\u8bf4\u660e<\/h4>\n<p>\u6b63\u5f0f\u91c7\u96c6\u524d\u5efa\u8bae\u67e5\u770b\u76ee\u6807\u7ad9\u70b9\u6839\u76ee\u5f55\u4e0b\u7684 robots.txt \u6587\u4ef6&#xff0c;\u4f8b\u5982&#xff1a;<\/p>\n<p>https:\/\/example.com\/robots.txt<\/p>\n<p>robots.txt \u901a\u5e38\u4f1a\u58f0\u660e\u54ea\u4e9b\u8def\u5f84\u5141\u8bb8\u6293\u53d6&#xff0c;\u54ea\u4e9b\u8def\u5f84\u4e0d\u5efa\u8bae\u6293\u53d6\u3002\u4f8b\u5982&#xff1a;<\/p>\n<p>User-agent: *<br \/>\nDisallow: \/admin\/<br \/>\nDisallow: \/login\/<br \/>\nAllow: \/archive\/<\/p>\n<p>\u5b83\u4e0d\u662f\u8bbf\u95ee\u63a7\u5236\u7cfb\u7edf&#xff0c;\u4f46\u5b83\u4f53\u73b0\u4e86\u7ad9\u70b9\u5bf9\u722c\u866b\u8bbf\u95ee\u7684\u57fa\u672c\u6001\u5ea6\u3002\u5bf9\u4e8e\u6280\u672f\u5206\u4eab\u548c\u4e2a\u4eba\u5b66\u4e60\u6765\u8bf4&#xff0c;\u5e94\u8be5\u5c3d\u91cf\u9075\u5b88\u8fd9\u4e9b\u58f0\u660e\u3002<\/p>\n<p>\u5728\u672c\u6587\u793a\u4f8b\u4ee3\u7801\u4e2d&#xff0c;\u6211\u4eec\u4e0d\u4f1a\u7ed5\u8fc7\u767b\u5f55&#xff0c;\u4e0d\u4f1a\u91c7\u96c6\u4e2a\u4eba\u654f\u611f\u4fe1\u606f&#xff0c;\u4e5f\u4e0d\u4f1a\u8bbf\u95ee\u540e\u53f0\u8def\u5f84\u3002\u793a\u4f8b\u53ea\u9762\u5411\u516c\u5f00\u7d22\u5f15\u9875\u3002<\/p>\n<h4>3.2 \u9891\u7387\u63a7\u5236<\/h4>\n<p>\u4e0d\u8981\u4f7f\u7528\u653b\u51fb\u5f0f\u5e76\u53d1\u3002\u5bf9\u4e8e\u7d22\u5f15\u578b\u7ad9\u70b9\u6765\u8bf4&#xff0c;\u8bf7\u6c42\u91cf\u5f80\u5f80\u4e0d\u9700\u8981\u5f88\u5927\u3002\u66f4\u7a33\u59a5\u7684\u65b9\u5f0f\u662f&#xff1a;<\/p>\n<li>\u6bcf\u6b21\u8bf7\u6c42\u4e4b\u95f4\u589e\u52a0\u968f\u673a\u7b49\u5f85\u3002<\/li>\n<li>\u5931\u8d25\u540e\u8fdb\u884c\u6307\u6570\u9000\u907f\u3002<\/li>\n<li>\u9650\u5236\u6700\u5927\u91cd\u8bd5\u6b21\u6570\u3002<\/li>\n<li>\u65e5\u5fd7\u8bb0\u5f55\u5931\u8d25 URL&#xff0c;\u540e\u7eed\u5355\u72ec\u8865\u6293\u3002<\/li>\n<p>\u793a\u4f8b\u7b56\u7565&#xff1a;<\/p>\n<p>\u6b63\u5e38\u8bf7\u6c42\u95f4\u9694&#xff1a;1.0 ~ 2.5 \u79d2<br \/>\n\u5931\u8d25\u540e\u7b49\u5f85&#xff1a;2 \u79d2\u30014 \u79d2\u30018 \u79d2<br \/>\n\u6700\u5927\u91cd\u8bd5&#xff1a;3 \u6b21<br \/>\n\u5355\u673a\u5e76\u53d1&#xff1a;\u521d\u59cb\u5efa\u8bae 1&#xff0c;\u4e0d\u5efa\u8bae\u4e00\u5f00\u59cb\u5c31\u5f00\u51e0\u5341\u4e2a\u7ebf\u7a0b<\/p>\n<h4>3.3 \u4e0d\u91c7\u96c6\u654f\u611f\u4fe1\u606f<\/h4>\n<p>\u672c\u6587\u53ea\u5904\u7406\u516c\u5f00\u9875\u9762\u4e2d\u7684\u62a5\u520a\u7d22\u5f15\u4fe1\u606f&#xff0c;\u4e0d\u91c7\u96c6\u624b\u673a\u53f7\u3001\u8eab\u4efd\u8bc1\u3001\u79c1\u4eba\u90ae\u7bb1\u3001\u8d26\u6237\u4fe1\u606f\u7b49\u654f\u611f\u6570\u636e\u3002\u5982\u679c\u7ad9\u70b9\u9700\u8981\u767b\u5f55\u6216\u4ed8\u8d39\u9605\u8bfb&#xff0c;\u5e94\u4f7f\u7528\u5e73\u53f0\u63d0\u4f9b\u7684\u6b63\u89c4\u8bbf\u95ee\u65b9\u5f0f&#xff0c;\u4e0d\u5efa\u8bae\u901a\u8fc7\u6280\u672f\u624b\u6bb5\u7ed5\u8fc7\u9650\u5236\u3002<\/p>\n<h4>3.4 \u4e0d\u7ed5\u8fc7\u4ed8\u8d39\u6216\u767b\u5f55\u9650\u5236<\/h4>\n<p>\u6709\u4e9b\u62a5\u520a\u7ad9\u70b9\u4f1a\u516c\u5f00\u76ee\u5f55&#xff0c;\u4f46\u6b63\u6587\u9700\u8981\u6388\u6743\u3002\u8fd9\u79cd\u60c5\u51b5\u4e0b&#xff0c;\u722c\u866b\u53ef\u4ee5\u53ea\u4fdd\u5b58\u76ee\u5f55\u7d22\u5f15\u548c\u516c\u5f00\u94fe\u63a5&#xff0c;\u4e0d\u5e94\u8be5\u5c1d\u8bd5\u7ed5\u8fc7\u6743\u9650\u3002\u6bd4\u8f83\u4e2d\u6027\u7684\u505a\u6cd5\u662f&#xff1a;<\/p>\n<p>\u76ee\u5f55\u53ef\u516c\u5f00\u8bbf\u95ee&#xff1a;\u91c7\u96c6\u76ee\u5f55\u5b57\u6bb5<br \/>\n\u6b63\u6587\u9700\u8981\u767b\u5f55&#xff1a;\u4e0d\u6293\u6b63\u6587&#xff0c;\u53ea\u4fdd\u7559\u8be6\u60c5\u9875\u94fe\u63a5<br \/>\n\u6b63\u6587\u9700\u8981\u4ed8\u8d39&#xff1a;\u4e0d\u6293\u6b63\u6587&#xff0c;\u53ea\u8bb0\u5f55\u6570\u5b57\u5316\u72b6\u6001\u6216\u8bbf\u95ee\u8bf4\u660e<\/p>\n<p>\u8fd9\u6837\u65e2\u80fd\u5b8c\u6210\u7d22\u5f15\u6574\u7406&#xff0c;\u4e5f\u80fd\u907f\u514d\u8d8a\u754c\u3002<\/p>\n<hr \/>\n<h3>4\ufe0f\u20e3 \u6280\u672f\u9009\u578b\u4e0e\u6574\u4f53\u6d41\u7a0b&#xff08;What\/How&#xff09;<\/h3>\n<h4>4.1 \u9759\u6001\u3001\u52a8\u6001\u548c API \u7684\u5224\u65ad<\/h4>\n<p>\u62a5\u520a\u5386\u53f2\u671f\u53f7\u5e73\u53f0\u5e38\u89c1\u4e09\u79cd\u5f62\u6001\u3002<\/p>\n<p>\u7b2c\u4e00\u79cd\u662f\u9759\u6001 HTML\u3002\u5e74\u4efd\u3001\u6708\u4efd\u3001\u5206\u9875\u3001\u8be6\u60c5\u90fd\u76f4\u63a5\u5199\u5728 HTML \u4e2d\u3002\u8fd9\u79cd\u6700\u9002\u5408\u4f7f\u7528 requests &#043; BeautifulSoup\/lxml\u3002<\/p>\n<p>\u7b2c\u4e8c\u79cd\u662f\u52a8\u6001\u6e32\u67d3\u3002\u9875\u9762\u521d\u59cb HTML \u53ea\u6709\u4e00\u4e2a\u7a7a\u58f3&#xff0c;\u771f\u6b63\u7684\u6570\u636e\u7531 JavaScript \u8bf7\u6c42\u540e\u518d\u6e32\u67d3\u5230\u9875\u9762\u3002\u8fd9\u65f6\u53ef\u4ee5\u5148\u627e\u63a5\u53e3&#xff0c;\u5982\u679c\u63a5\u53e3\u6e05\u6670&#xff0c;\u4ecd\u7136\u7528 requests&#xff1b;\u5982\u679c\u63a5\u53e3\u590d\u6742\u6216\u7b7e\u540d\u96be\u4ee5\u7ef4\u62a4&#xff0c;\u518d\u8003\u8651 Playwright\u3002<\/p>\n<p>\u7b2c\u4e09\u79cd\u662f\u534a\u52a8\u6001\u9875\u9762\u3002\u5e74\u6708\u65e5\u5386\u662f\u63a5\u53e3\u8fd4\u56de&#xff0c;\u8be6\u60c5\u9875\u662f\u9759\u6001 HTML\u3002\u8fd9\u7c7b\u7ad9\u70b9\u5f88\u5e38\u89c1&#xff0c;\u4e5f\u662f\u672c\u6587\u91cd\u70b9\u5904\u7406\u7684\u7c7b\u578b\u3002\u6211\u4eec\u4f1a\u628a\u8bf7\u6c42\u5c42\u3001\u89e3\u6790\u5c42\u548c\u5b58\u50a8\u5c42\u5206\u5f00&#xff0c;\u65b9\u4fbf\u4ee5\u540e\u66ff\u6362\u3002<\/p>\n<p>\u672c\u6587\u91c7\u7528\u7684\u4e3b\u65b9\u6848&#xff1a;<\/p>\n<p>requests &#043; BeautifulSoup &#043; lxml &#043; SQLite &#043; pandas<\/p>\n<p>\u53ef\u9009\u589e\u5f3a&#xff1a;<\/p>\n<p>Playwright&#xff1a;\u7528\u4e8e\u5904\u7406\u7eaf\u524d\u7aef\u6e32\u67d3\u9875\u9762<br \/>\nScrapy&#xff1a;\u7528\u4e8e\u5927\u89c4\u6a21\u961f\u5217\u3001\u53bb\u91cd\u3001\u8c03\u5ea6\u548c\u4e2d\u95f4\u4ef6\u7ba1\u7406<\/p>\n<h4>4.2 \u4e3a\u4ec0\u4e48\u4e0d\u4e00\u5f00\u59cb\u5c31\u7528 Scrapy<\/h4>\n<p>Scrapy \u5f88\u5f3a&#xff0c;\u4f46\u4e0d\u662f\u6240\u6709\u9879\u76ee\u90fd\u9700\u8981\u4e00\u4e0a\u6765\u5c31\u7528 Scrapy\u3002\u5bf9\u4e8e\u4e00\u4e2a\u5b57\u6bb5\u660e\u786e\u3001\u5c42\u7ea7\u6e05\u6670\u3001\u8bf7\u6c42\u91cf\u53ef\u63a7\u7684\u62a5\u520a\u7d22\u5f15\u91c7\u96c6\u4efb\u52a1&#xff0c;\u5148\u7528\u8f7b\u91cf\u5de5\u7a0b\u5199\u6e05\u695a\u6d41\u7a0b&#xff0c;\u5f80\u5f80\u66f4\u5bb9\u6613\u8c03\u8bd5\u3002<\/p>\n<p>\u6211\u7684\u5efa\u8bae\u662f&#xff1a;<\/p>\n<p>\u5c0f\u89c4\u6a21\u9a8c\u8bc1&#xff1a;requests &#043; bs4<br \/>\n\u957f\u671f\u91c7\u96c6&#xff1a;requests \u5de5\u7a0b\u5316 &#043; SQLite<br \/>\n\u591a\u7ad9\u70b9\u91c7\u96c6&#xff1a;Scrapy<br \/>\n\u5f3a\u52a8\u6001\u9875\u9762&#xff1a;Playwright<br \/>\n\u5927\u89c4\u6a21\u751f\u4ea7&#xff1a;Scrapy &#043; Redis &#043; \u5b9a\u65f6\u4efb\u52a1 &#043; \u76d1\u63a7<\/p>\n<h4>4.3 \u6574\u4f53\u6d41\u7a0b<\/h4>\n<p>\u672c\u9879\u76ee\u91c7\u7528\u56db\u6bb5\u5f0f\u6d41\u7a0b&#xff1a;<\/p>\n<p>\u91c7\u96c6 \u2192 \u89e3\u6790 \u2192 \u6e05\u6d17 \u2192 \u5b58\u50a8<\/p>\n<p>\u66f4\u5177\u4f53\u4e00\u70b9&#xff1a;<\/p>\n<p>1. \u83b7\u53d6\u5e74\u4efd\u5165\u53e3<br \/>\n2. \u83b7\u53d6\u67d0\u5e74\u53ef\u7528\u6708\u4efd<br \/>\n3. \u8fdb\u5165\u67d0\u6708\u5386\u53f2\u65e5\u5386<br \/>\n4. \u89e3\u6790\u8be5\u6708\u6240\u6709\u671f\u53f7\u5165\u53e3<br \/>\n5. \u904d\u5386\u671f\u53f7\u5206\u9875<br \/>\n6. \u63d0\u53d6\u5217\u8868\u9875\u8be6\u60c5\u94fe\u63a5<br \/>\n7. \u8bf7\u6c42\u8be6\u60c5\u9875<br \/>\n8. \u62bd\u53d6\u5b57\u6bb5<br \/>\n9. \u6e05\u6d17\u65e5\u671f\u3001\u72b6\u6001\u3001URL<br \/>\n10. \u5199\u5165 SQLite<br \/>\n11. \u5bfc\u51fa CSV<\/p>\n<p>\u7528\u6587\u5b57\u753b\u6210\u6d41\u7a0b\u56fe&#xff1a;<\/p>\n<p>[Start]<br \/>\n   |<br \/>\n   v<br \/>\n[Load Config]<br \/>\n   |<br \/>\n   v<br \/>\n[Fetch Year Archive]<br \/>\n   |<br \/>\n   v<br \/>\n[Parse Year List]<br \/>\n   |<br \/>\n   v<br \/>\n[Fetch Month Calendar]<br \/>\n   |<br \/>\n   v<br \/>\n[Parse Issue Dates]<br \/>\n   |<br \/>\n   v<br \/>\n[Fetch Issue List Page]<br \/>\n   |<br \/>\n   v<br \/>\n[Parse Detail Links]<br \/>\n   |<br \/>\n   v<br \/>\n[Fetch Detail Page]<br \/>\n   |<br \/>\n   v<br \/>\n[Parse Fields]<br \/>\n   |<br \/>\n   v<br \/>\n[Clean &#043; Validate]<br \/>\n   |<br \/>\n   v<br \/>\n[Save SQLite]<br \/>\n   |<br \/>\n   v<br \/>\n[Export CSV]<br \/>\n   |<br \/>\n   v<br \/>\n[End]<\/p>\n<hr \/>\n<h3>5\ufe0f\u20e3 \u73af\u5883\u51c6\u5907\u4e0e\u4f9d\u8d56\u5b89\u88c5<\/h3>\n<h4>5.1 Python \u7248\u672c<\/h4>\n<p>\u5efa\u8bae\u4f7f\u7528&#xff1a;<\/p>\n<p>Python 3.10&#043;<\/p>\n<p>\u6211\u5e73\u65f6\u5199\u722c\u866b\u4f1a\u5c3d\u91cf\u907f\u514d\u4f9d\u8d56\u592a\u65b0\u7684\u8bed\u6cd5&#xff0c;\u4e3b\u8981\u662f\u8003\u8651\u90e8\u7f72\u73af\u5883\u3002Python 3.10 \u6216 3.11 \u90fd\u6bd4\u8f83\u7a33\u3002<\/p>\n<p>\u67e5\u770b\u7248\u672c&#xff1a;<\/p>\n<p>python <span class=\"token parameter variable\">&#8211;version<\/span><\/p>\n<h4>5.2 \u521b\u5efa\u865a\u62df\u73af\u5883<\/h4>\n<p><span class=\"token function\">mkdir<\/span> newspaper_index_crawler<br \/>\n<span class=\"token builtin class-name\">cd<\/span> newspaper_index_crawler<\/p>\n<p>python <span class=\"token parameter variable\">-m<\/span> venv .venv<\/p>\n<p><span class=\"token comment\"># Windows<\/span><br \/>\n.venv<span class=\"token punctuation\">\\\\<\/span>Scripts<span class=\"token punctuation\">\\\\<\/span>activate<\/p>\n<p><span class=\"token comment\"># macOS \/ Linux<\/span><br \/>\n<span class=\"token builtin class-name\">source<\/span> .venv\/bin\/activate<\/p>\n<h4>5.3 \u5b89\u88c5\u4f9d\u8d56<\/h4>\n<p>pip <span class=\"token function\">install<\/span> requests beautifulsoup4 lxml pandas python-dateutil<\/p>\n<p>\u53ef\u9009\u5b89\u88c5 Playwright&#xff1a;<\/p>\n<p>pip <span class=\"token function\">install<\/span> playwright<br \/>\nplaywright <span class=\"token function\">install<\/span><\/p>\n<p>\u672c\u6587\u4e3b\u4ee3\u7801\u4e0d\u5f3a\u5236\u4f9d\u8d56 Playwright&#xff0c;\u53ea\u6709\u9047\u5230\u7eaf\u52a8\u6001\u7ad9\u70b9\u65f6\u624d\u9700\u8981\u3002<\/p>\n<h4>5.4 \u63a8\u8350\u9879\u76ee\u7ed3\u6784<\/h4>\n<p>newspaper_index_crawler\/<br \/>\n\u251c\u2500\u2500 main.py<br \/>\n\u251c\u2500\u2500 config.py<br \/>\n\u251c\u2500\u2500 requirements.txt<br \/>\n\u251c\u2500\u2500 data\/<br \/>\n\u2502   \u251c\u2500\u2500 newspaper_issues.db<br \/>\n\u2502   \u2514\u2500\u2500 newspaper_issues.csv<br \/>\n\u251c\u2500\u2500 fixtures\/<br \/>\n\u2502   \u251c\u2500\u2500 calendar_2024_05.html<br \/>\n\u2502   \u251c\u2500\u2500 issue_2024_05_01_page_1.html<br \/>\n\u2502   \u251c\u2500\u2500 issue_2024_05_01_page_2.html<br \/>\n\u2502   \u251c\u2500\u2500 detail_001.html<br \/>\n\u2502   \u251c\u2500\u2500 detail_002.html<br \/>\n\u2502   \u2514\u2500\u2500 detail_003.html<br \/>\n\u2514\u2500\u2500 crawler\/<br \/>\n    \u251c\u2500\u2500 __init__.py<br \/>\n    \u251c\u2500\u2500 fetcher.py<br \/>\n    \u251c\u2500\u2500 parser.py<br \/>\n    \u251c\u2500\u2500 storage.py<br \/>\n    \u2514\u2500\u2500 cleaner.py<\/p>\n<p>\u4e3a\u4e86\u8ba9\u6587\u7ae0\u91cc\u7684\u4ee3\u7801\u66f4\u5bb9\u6613\u590d\u5236\u8fd0\u884c&#xff0c;\u540e\u6587\u4f1a\u7ed9\u51fa\u4e00\u4e2a\u201c\u5355\u6587\u4ef6\u53ef\u8fd0\u884c\u7248\u201d\u3002\u771f\u5b9e\u9879\u76ee\u4e2d\u518d\u62c6\u6210\u4e0a\u9762\u7684\u7ed3\u6784\u5373\u53ef\u3002<\/p>\n<h4>5.5 requirements.txt<\/h4>\n<p>requests&#061;&#061;2.32.3<br \/>\nbeautifulsoup4&#061;&#061;4.12.3<br \/>\nlxml&#061;&#061;5.2.2<br \/>\npandas&#061;&#061;2.2.2<br \/>\npython-dateutil&#061;&#061;2.9.0.post0<\/p>\n<p>\u7248\u672c\u4e0d\u4e00\u5b9a\u975e\u5f97\u5b8c\u5168\u4e00\u81f4&#xff0c;\u4f46\u9501\u5b9a\u7248\u672c\u6709\u4e00\u4e2a\u597d\u5904&#xff1a;\u522b\u4eba\u590d\u73b0\u5b9e\u9a8c\u65f6\u4e0d\u4f1a\u56e0\u4e3a\u4f9d\u8d56\u5347\u7ea7\u5bfc\u81f4\u884c\u4e3a\u53d8\u5316\u3002<\/p>\n<hr \/>\n<h3>6\ufe0f\u20e3 \u6838\u5fc3\u5b9e\u73b0&#xff1a;\u8bf7\u6c42\u5c42&#xff08;Fetcher&#xff09;<\/h3>\n<p>\u8bf7\u6c42\u5c42\u8d1f\u8d23\u548c\u76ee\u6807\u7ad9\u70b9\u6253\u4ea4\u9053\u3002\u5b83\u7684\u804c\u8d23\u4e0d\u662f\u89e3\u6790\u9875\u9762&#xff0c;\u4e5f\u4e0d\u662f\u5b58\u50a8\u6570\u636e&#xff0c;\u800c\u662f\u7a33\u5b9a\u5730\u62ff\u5230 HTML \u6216 JSON\u3002<\/p>\n<h4>6.1 headers \u8bbe\u7f6e<\/h4>\n<p>\u5e38\u89c1 headers&#xff1a;<\/p>\n<p>headers <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n    <span class=\"token string\">&#034;User-Agent&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;Mozilla\/5.0 &#8230;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;Referer&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;https:\/\/example.com\/archive&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;Accept-Language&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;zh-CN,zh;q&#061;0.9,en;q&#061;0.8&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n<span class=\"token punctuation\">}<\/span><\/p>\n<p>User-Agent \u4e0d\u5e94\u8be5\u4f2a\u88c5\u5f97\u8fc7\u5ea6\u5938\u5f20&#xff0c;\u4fdd\u6301\u5e38\u89c4\u6d4f\u89c8\u5668\u8bbf\u95ee\u5373\u53ef\u3002Referer \u6709\u65f6\u662f\u5fc5\u8981\u7684&#xff0c;\u56e0\u4e3a\u90e8\u5206\u7ad9\u70b9\u4f1a\u68c0\u67e5\u6765\u6e90\u9875\u9762\u3002<\/p>\n<h4>6.2 timeout<\/h4>\n<p>\u4e0d\u8981\u5199\u6ca1\u6709 timeout \u7684\u8bf7\u6c42\u3002<\/p>\n<p>\u9519\u8bef\u5199\u6cd5&#xff1a;<\/p>\n<p>requests<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">)<\/span><\/p>\n<p>\u63a8\u8350\u5199\u6cd5&#xff1a;<\/p>\n<p>requests<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">,<\/span> timeout<span class=\"token operator\">&#061;<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">5<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">20<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u5176\u4e2d (5, 20) \u7684\u542b\u4e49\u662f&#xff1a;<\/p>\n<p>\u8fde\u63a5\u8d85\u65f6&#xff1a;5 \u79d2<br \/>\n\u8bfb\u53d6\u8d85\u65f6&#xff1a;20 \u79d2<\/p>\n<p>\u8fd9\u6837\u53ef\u4ee5\u907f\u514d\u67d0\u4e2a\u8bf7\u6c42\u4e00\u76f4\u5361\u4f4f\u3002<\/p>\n<h4>6.3 session\/cookie<\/h4>\n<p>\u5982\u679c\u76ee\u6807\u7ad9\u70b9\u53ea\u662f\u516c\u5f00\u7d22\u5f15\u9875&#xff0c;\u901a\u5e38\u4e0d\u9700\u8981\u767b\u5f55 cookie\u3002\u4f46\u4f7f\u7528 requests.Session() \u4ecd\u7136\u6709\u597d\u5904&#xff1a;<\/p>\n<li>\u81ea\u52a8\u590d\u7528 TCP \u8fde\u63a5\u3002<\/li>\n<li>\u4fdd\u6301\u90e8\u5206\u7ad9\u70b9\u4e0b\u53d1\u7684\u666e\u901a cookie\u3002<\/li>\n<li>\u4fbf\u4e8e\u7edf\u4e00\u8bbe\u7f6e headers\u3002<\/li>\n<p>\u793a\u4f8b&#xff1a;<\/p>\n<p>session <span class=\"token operator\">&#061;<\/span> requests<span class=\"token punctuation\">.<\/span>Session<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\nsession<span class=\"token punctuation\">.<\/span>headers<span class=\"token punctuation\">.<\/span>update<span class=\"token punctuation\">(<\/span>headers<span class=\"token punctuation\">)<\/span><\/p>\n<h4>6.4 \u5931\u8d25\u5904\u7406&#xff1a;\u91cd\u8bd5\u4e0e\u9000\u907f<\/h4>\n<p>\u5e38\u89c1\u9519\u8bef&#xff1a;<\/p>\n<p>403&#xff1a;\u8bbf\u95ee\u88ab\u62d2\u7edd<br \/>\n404&#xff1a;\u9875\u9762\u4e0d\u5b58\u5728<br \/>\n429&#xff1a;\u8bf7\u6c42\u8fc7\u591a<br \/>\n500\/502\/503&#xff1a;\u670d\u52a1\u7aef\u5f02\u5e38<br \/>\ntimeout&#xff1a;\u7f51\u7edc\u8d85\u65f6<\/p>\n<p>\u6bd4\u8f83\u7a33\u7684\u7b56\u7565\u662f&#xff1a;<\/p>\n<p>403&#xff1a;\u964d\u4f4e\u9891\u7387&#xff0c;\u68c0\u67e5 headers \u548c robots&#xff0c;\u4e0d\u5efa\u8bae\u786c\u51b2<br \/>\n404&#xff1a;\u8bb0\u5f55\u5e76\u8df3\u8fc7<br \/>\n429&#xff1a;\u660e\u663e\u89e6\u53d1\u9891\u63a7&#xff0c;\u5ef6\u957f\u7b49\u5f85<br \/>\n5xx&#xff1a;\u91cd\u8bd5\u51e0\u6b21&#xff0c;\u4e0d\u8981\u65e0\u9650\u91cd\u8bd5<br \/>\ntimeout&#xff1a;\u91cd\u8bd5&#xff0c;\u4ecd\u5931\u8d25\u5219\u8bb0\u5f55<\/p>\n<p>\u9000\u907f\u7b56\u7565\u793a\u4f8b&#xff1a;<\/p>\n<p>\u7b2c 1 \u6b21\u5931\u8d25&#xff1a;\u7b49\u5f85 2 \u79d2<br \/>\n\u7b2c 2 \u6b21\u5931\u8d25&#xff1a;\u7b49\u5f85 4 \u79d2<br \/>\n\u7b2c 3 \u6b21\u5931\u8d25&#xff1a;\u7b49\u5f85 8 \u79d2<\/p>\n<p>\u6211\u4e0d\u5efa\u8bae\u5728\u8fd9\u7c7b\u6587\u7ae0\u91cc\u628a\u4ee3\u7406\u4f5c\u4e3a\u9ed8\u8ba4\u65b9\u6848\u3002\u4ee3\u7406\u4e0d\u662f\u4e07\u80fd\u836f&#xff0c;\u4e5f\u5bb9\u6613\u628a\u7b80\u5355\u95ee\u9898\u590d\u6742\u5316\u3002\u591a\u6570\u7d22\u5f15\u91c7\u96c6\u4efb\u52a1\u5148\u505a\u597d\u9891\u63a7\u548c\u91cd\u8bd5\u5c31\u591f\u4e86\u3002<\/p>\n<hr \/>\n<h3>7\ufe0f\u20e3 \u6838\u5fc3\u5b9e\u73b0&#xff1a;\u89e3\u6790\u5c42&#xff08;Parser&#xff09;<\/h3>\n<p>\u89e3\u6790\u5c42\u8d1f\u8d23\u4ece HTML \u4e2d\u62bd\u53d6\u7ed3\u6784\u5316\u5b57\u6bb5\u3002\u8fd9\u91cc\u6709\u4e00\u4e2a\u539f\u5219&#xff1a;\u4e0d\u8981\u8ba9\u89e3\u6790\u903b\u8f91\u6563\u843d\u5728\u8bf7\u6c42\u5faa\u73af\u91cc\u3002\u8bf7\u6c42\u662f\u8bf7\u6c42&#xff0c;\u89e3\u6790\u662f\u89e3\u6790&#xff0c;\u4e24\u8005\u5206\u5f00\u540e&#xff0c;\u8c03\u8bd5\u4f1a\u8212\u670d\u5f88\u591a\u3002<\/p>\n<h4>7.1 \u89e3\u6790\u65b9\u5f0f\u9009\u62e9<\/h4>\n<p>\u672c\u6587\u4f7f\u7528&#xff1a;<\/p>\n<p>BeautifulSoup &#043; CSS Selector<\/p>\n<p>\u539f\u56e0\u662f&#xff1a;<\/p>\n<li>\u5165\u95e8\u6210\u672c\u4f4e\u3002<\/li>\n<li>\u5bf9\u4e0d\u89c4\u8303 HTML \u5bb9\u5fcd\u5ea6\u8f83\u597d\u3002<\/li>\n<li>CSS \u9009\u62e9\u5668\u5199\u8d77\u6765\u6bd4\u8f83\u76f4\u89c2\u3002<\/li>\n<p>\u5982\u679c\u9875\u9762\u7ed3\u6784\u975e\u5e38\u7a33\u5b9a&#xff0c;\u4e5f\u53ef\u4ee5\u4f7f\u7528 XPath&#xff1a;<\/p>\n<p><span class=\"token keyword\">from<\/span> lxml <span class=\"token keyword\">import<\/span> etree<br \/>\ntree <span class=\"token operator\">&#061;<\/span> etree<span class=\"token punctuation\">.<\/span>HTML<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">)<\/span><br \/>\nlinks <span class=\"token operator\">&#061;<\/span> tree<span class=\"token punctuation\">.<\/span>xpath<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;\/\/a[contains(&#064;class, &#034;detail-link&#034;)]\/&#064;href&#039;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<h4>7.2 \u5217\u8868\u9875\u5982\u4f55\u62ff\u8be6\u60c5\u94fe\u63a5<\/h4>\n<p>\u671f\u53f7\u5217\u8868\u9875\u901a\u5e38\u957f\u8fd9\u6837&#xff1a;<\/p>\n<p><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>div<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>issue-list<span class=\"token punctuation\">&#034;<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span><br \/>\n  <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>div<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>issue-item<span class=\"token punctuation\">&#034;<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span><br \/>\n    <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>a<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>detail-link<span class=\"token punctuation\">&#034;<\/span><\/span> <span class=\"token attr-name\">href<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>\/detail\/001.html<span class=\"token punctuation\">&#034;<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u57ce\u5e02\u5efa\u8bbe\u4e13\u9898<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>a<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><br \/>\n    <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>span<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>column<span class=\"token punctuation\">&#034;<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u7efc\u5408\u65b0\u95fb<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>span<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><br \/>\n    <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>span<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>status<span class=\"token punctuation\">&#034;<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u5df2\u6570\u5b57\u5316<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>span<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><br \/>\n  <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>div<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><br \/>\n<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>div<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><\/p>\n<p>\u89e3\u6790\u601d\u8def&#xff1a;<\/p>\n<p>1. \u627e\u5230\u6240\u6709 issue-item<br \/>\n2. \u63d0\u53d6 detail-link \u7684 href<br \/>\n3. \u8865\u5168\u6210\u7edd\u5bf9 URL<br \/>\n4. \u987a\u5e26\u63d0\u53d6\u5217\u8868\u9875\u5df2\u6709\u5b57\u6bb5<\/p>\n<p>\u6709\u4e9b\u5b57\u6bb5\u5217\u8868\u9875\u5c31\u6709&#xff0c;\u6709\u4e9b\u5b57\u6bb5\u8be6\u60c5\u9875\u624d\u6709\u3002\u6211\u7684\u505a\u6cd5\u662f&#xff1a;\u5217\u8868\u9875\u5148\u4fdd\u5b58\u4e00\u4efd\u201c\u6d45\u5b57\u6bb5\u201d&#xff0c;\u8be6\u60c5\u9875\u518d\u7528\u201c\u6df1\u5b57\u6bb5\u201d\u8986\u76d6\u6216\u8865\u9f50\u3002<\/p>\n<h4>7.3 \u8be6\u60c5\u9875\u5982\u4f55\u62bd\u5b57\u6bb5<\/h4>\n<p>\u8be6\u60c5\u9875\u53ef\u80fd\u957f\u8fd9\u6837&#xff1a;<\/p>\n<p><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>h1<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>topic<span class=\"token punctuation\">&#034;<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u57ce\u5e02\u5efa\u8bbe\u4e13\u9898<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>h1<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><br \/>\n<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>ul<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>meta<span class=\"token punctuation\">&#034;<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span><br \/>\n  <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>li<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>span<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u62a5\u520a\u540d&#xff1a;<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>span<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>b<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u793a\u4f8b\u65e5\u62a5<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>b<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>li<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><br \/>\n  <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>li<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>span<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u671f\u53f7&#xff1a;<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>span<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>b<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>2024\u5e74\u7b2c05\u671f<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>b<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>li<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><br \/>\n  <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>li<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>span<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u51fa\u7248\u65e5\u671f&#xff1a;<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>span<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>b<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>2024-05-01<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>b<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>li<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><br \/>\n  <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>li<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>span<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u680f\u76ee&#xff1a;<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>span<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>b<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u7efc\u5408\u65b0\u95fb<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>b<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>li<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><br \/>\n  <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>li<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>span<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u6570\u5b57\u5316\u72b6\u6001&#xff1a;<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>span<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>b<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u5df2\u6570\u5b57\u5316<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>b<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>li<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><br \/>\n<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>ul<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><\/p>\n<p>\u89e3\u6790\u65f6\u4e0d\u8981\u53ea\u4f9d\u8d56\u4f4d\u7f6e&#xff0c;\u4f8b\u5982\u7b2c\u4e00\u4e2a li \u662f\u62a5\u520a\u540d\u3001\u7b2c\u4e8c\u4e2a\u662f\u671f\u53f7\u3002\u66f4\u7a33\u7684\u65b9\u5f0f\u662f\u6309\u7167\u6807\u7b7e\u6587\u5b57\u6620\u5c04&#xff1a;<\/p>\n<p>\u770b\u5230\u201c\u62a5\u520a\u540d\u201d \u2192 newspaper_name<br \/>\n\u770b\u5230\u201c\u671f\u53f7\u201d \u2192 issue_no<br \/>\n\u770b\u5230\u201c\u51fa\u7248\u65e5\u671f\u201d \u2192 publish_date<\/p>\n<p>\u8fd9\u6837\u5373\u4f7f\u9875\u9762\u591a\u4e86\u4e00\u4e2a\u201c\u8d23\u4efb\u7f16\u8f91\u201d\u5b57\u6bb5&#xff0c;\u4e5f\u4e0d\u4f1a\u5f71\u54cd\u6838\u5fc3\u5b57\u6bb5\u3002<\/p>\n<h4>7.4 \u7f3a\u5931\u5b57\u6bb5\u600e\u4e48\u529e<\/h4>\n<p>\u771f\u5b9e\u9875\u9762\u4e00\u5b9a\u4f1a\u7f3a\u5b57\u6bb5\u3002\u4e0d\u8981\u56e0\u4e3a\u4e00\u4e2a\u5b57\u6bb5\u4e3a\u7a7a\u5c31\u8ba9\u6574\u4e2a\u7a0b\u5e8f\u5d29\u6389\u3002<\/p>\n<p>\u5efa\u8bae\u7b56\u7565&#xff1a;<\/p>\n<p>\u62a5\u520a\u540d\u7f3a\u5931&#xff1a;\u4f7f\u7528\u914d\u7f6e\u4e2d\u7684\u9ed8\u8ba4\u62a5\u520a\u540d<br \/>\n\u671f\u53f7\u7f3a\u5931&#xff1a;\u5c1d\u8bd5\u4ece URL \u6216\u5217\u8868\u9875\u7ee7\u627f<br \/>\n\u51fa\u7248\u65e5\u671f\u7f3a\u5931&#xff1a;\u5c1d\u8bd5\u4ece\u65e5\u5386\u65e5\u671f\u7ee7\u627f<br \/>\n\u680f\u76ee\u7f3a\u5931&#xff1a;\u586b\u7a7a\u5b57\u7b26\u4e32<br \/>\n\u4e3b\u9898\u7f3a\u5931&#xff1a;\u4f7f\u7528\u5217\u8868\u9875\u6807\u9898<br \/>\n\u6570\u5b57\u5316\u72b6\u6001\u7f3a\u5931&#xff1a;\u586b\u201c\u672a\u77e5\u201d<br \/>\n\u94fe\u63a5\u7f3a\u5931&#xff1a;\u4e22\u5f03\u8be5\u6761<\/p>\n<p>\u5b57\u6bb5\u7f3a\u5931\u65f6\u5e94\u8be5\u8bb0\u5f55\u65e5\u5fd7&#xff0c;\u800c\u4e0d\u662f\u5047\u88c5\u4e00\u5207\u6b63\u5e38\u3002<\/p>\n<hr \/>\n<h3>8\ufe0f\u20e3 \u6570\u636e\u5b58\u50a8\u4e0e\u5bfc\u51fa&#xff08;Storage&#xff09;<\/h3>\n<h4>8.1 \u4e3a\u4ec0\u4e48\u9009\u62e9 SQLite \u8d77\u6b65<\/h4>\n<p>\u672c\u6587\u4f7f\u7528 SQLite\u3002\u539f\u56e0\u5f88\u7b80\u5355&#xff1a;<\/p>\n<li>\u4e0d\u9700\u8981\u5355\u72ec\u5b89\u88c5\u6570\u636e\u5e93\u670d\u52a1\u3002<\/li>\n<li>\u5355\u6587\u4ef6\u5b58\u50a8&#xff0c;\u4fbf\u4e8e\u5907\u4efd\u548c\u79fb\u52a8\u3002<\/li>\n<li>\u652f\u6301\u552f\u4e00\u7ea6\u675f&#xff0c;\u65b9\u4fbf\u53bb\u91cd\u3002<\/li>\n<li>\u540e\u7eed\u53ef\u4ee5\u5f88\u5bb9\u6613\u8fc1\u79fb\u5230 MySQL \u6216 PostgreSQL\u3002<\/li>\n<p>\u5bf9\u4e8e\u4e2a\u4eba\u5b66\u4e60\u3001\u8d44\u6599\u5f52\u6863\u3001\u5c0f\u89c4\u6a21\u7d22\u5f15\u91c7\u96c6&#xff0c;SQLite \u662f\u975e\u5e38\u5408\u9002\u7684\u3002<\/p>\n<h4>8.2 \u5b57\u6bb5\u6620\u5c04\u8868<\/h4>\n<table>\n<tr>\u4e2d\u6587\u5b57\u6bb5\u6570\u636e\u5e93\u5b57\u6bb5\u7c7b\u578b\u793a\u4f8b\u503c<\/tr>\n<tbody>\n<tr>\n<td>\u62a5\u520a\u540d<\/td>\n<td>newspaper_name<\/td>\n<td>TEXT<\/td>\n<td>\u793a\u4f8b\u65e5\u62a5<\/td>\n<\/tr>\n<tr>\n<td>\u671f\u53f7<\/td>\n<td>issue_no<\/td>\n<td>TEXT<\/td>\n<td>2024\u5e74\u7b2c05\u671f<\/td>\n<\/tr>\n<tr>\n<td>\u51fa\u7248\u65e5\u671f<\/td>\n<td>publish_date<\/td>\n<td>TEXT<\/td>\n<td>2024-05-01<\/td>\n<\/tr>\n<tr>\n<td>\u680f\u76ee<\/td>\n<td>column_name<\/td>\n<td>TEXT<\/td>\n<td>\u7efc\u5408\u65b0\u95fb<\/td>\n<\/tr>\n<tr>\n<td>\u4e3b\u9898<\/td>\n<td>topic<\/td>\n<td>TEXT<\/td>\n<td>\u57ce\u5e02\u5efa\u8bbe\u4e13\u9898<\/td>\n<\/tr>\n<tr>\n<td>\u6570\u5b57\u5316\u72b6\u6001<\/td>\n<td>digitization_status<\/td>\n<td>TEXT<\/td>\n<td>\u5df2\u6570\u5b57\u5316<\/td>\n<\/tr>\n<tr>\n<td>\u94fe\u63a5<\/td>\n<td>url<\/td>\n<td>TEXT UNIQUE<\/td>\n<td>https:\/\/example.com\/detail\/001.html<\/td>\n<\/tr>\n<tr>\n<td>\u5185\u5bb9 hash<\/td>\n<td>content_hash<\/td>\n<td>TEXT<\/td>\n<td>md5 \u6458\u8981<\/td>\n<\/tr>\n<tr>\n<td>\u521b\u5efa\u65f6\u95f4<\/td>\n<td>created_at<\/td>\n<td>TEXT<\/td>\n<td>2024-05-20 12:30:00<\/td>\n<\/tr>\n<tr>\n<td>\u66f4\u65b0\u65f6\u95f4<\/td>\n<td>updated_at<\/td>\n<td>TEXT<\/td>\n<td>2024-05-20 12:30:00<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h4>8.3 \u53bb\u91cd\u7b56\u7565<\/h4>\n<p>\u53bb\u91cd\u53ef\u4ee5\u5206\u4e24\u5c42&#xff1a;<\/p>\n<p>\u7b2c\u4e00\u5c42&#xff1a;URL \u552f\u4e00\u3002<\/p>\n<p>url <span class=\"token keyword\">TEXT<\/span> <span class=\"token keyword\">UNIQUE<\/span><\/p>\n<p>\u7b2c\u4e8c\u5c42&#xff1a;\u5185\u5bb9 hash\u3002<\/p>\n<p>content_hash <span class=\"token operator\">&#061;<\/span> md5<span class=\"token punctuation\">(<\/span><br \/>\n    newspaper_name <span class=\"token operator\">&#043;<\/span> issue_no <span class=\"token operator\">&#043;<\/span> publish_date <span class=\"token operator\">&#043;<\/span> column_name <span class=\"token operator\">&#043;<\/span> topic <span class=\"token operator\">&#043;<\/span> digitization_status<br \/>\n<span class=\"token punctuation\">)<\/span><\/p>\n<p>\u4e00\u822c\u6765\u8bf4&#xff0c;\u8be6\u60c5\u9875 URL \u8db3\u591f\u4f5c\u4e3a\u552f\u4e00\u952e\u3002\u5982\u679c\u7ad9\u70b9 URL \u4e0d\u7a33\u5b9a&#xff0c;\u6bd4\u5982\u540c\u4e00\u7bc7\u5185\u5bb9\u4f1a\u6709\u591a\u4e2a\u955c\u50cf\u94fe\u63a5&#xff0c;\u5c31\u53ef\u4ee5\u518d\u52a0\u5185\u5bb9 hash\u3002<\/p>\n<hr \/>\n<h3>9\ufe0f\u20e3 \u5b8c\u6574\u53ef\u8fd0\u884c\u4ee3\u7801<\/h3>\n<p>\u4e0b\u9762\u7ed9\u51fa\u4e00\u4e2a\u5355\u6587\u4ef6\u7248\u672c\u3002\u5b83\u4f1a\u81ea\u52a8\u751f\u6210\u672c\u5730 HTML \u6837\u4f8b&#xff0c;\u7136\u540e\u6a21\u62df\u201c\u65e5\u5386\u9875 \u2192 \u5386\u53f2\u5206\u9875 \u2192 \u8be6\u60c5\u9875\u201d\u7684\u91c7\u96c6\u6d41\u7a0b\u3002\u4f60\u590d\u5236\u540e\u53ef\u4ee5\u76f4\u63a5\u8fd0\u884c\u3002<\/p>\n<p>\u4fdd\u5b58\u4e3a&#xff1a;<\/p>\n<p>main.py<\/p>\n<p>\u8fd0\u884c&#xff1a;<\/p>\n<p>python main.py<\/p>\n<p>\u4ee3\u7801\u5982\u4e0b&#xff1a;<\/p>\n<p><span class=\"token keyword\">import<\/span> csv<br \/>\n<span class=\"token keyword\">import<\/span> hashlib<br \/>\n<span class=\"token keyword\">import<\/span> logging<br \/>\n<span class=\"token keyword\">import<\/span> random<br \/>\n<span class=\"token keyword\">import<\/span> re<br \/>\n<span class=\"token keyword\">import<\/span> sqlite3<br \/>\n<span class=\"token keyword\">import<\/span> time<br \/>\n<span class=\"token keyword\">from<\/span> dataclasses <span class=\"token keyword\">import<\/span> dataclass<span class=\"token punctuation\">,<\/span> asdict<br \/>\n<span class=\"token keyword\">from<\/span> datetime <span class=\"token keyword\">import<\/span> datetime<br \/>\n<span class=\"token keyword\">from<\/span> pathlib <span class=\"token keyword\">import<\/span> Path<br \/>\n<span class=\"token keyword\">from<\/span> typing <span class=\"token keyword\">import<\/span> Dict<span class=\"token punctuation\">,<\/span> Iterable<span class=\"token punctuation\">,<\/span> List<span class=\"token punctuation\">,<\/span> Optional<br \/>\n<span class=\"token keyword\">from<\/span> urllib<span class=\"token punctuation\">.<\/span>parse <span class=\"token keyword\">import<\/span> urljoin<\/p>\n<p><span class=\"token keyword\">import<\/span> pandas <span class=\"token keyword\">as<\/span> pd<br \/>\n<span class=\"token keyword\">import<\/span> requests<br \/>\n<span class=\"token keyword\">from<\/span> bs4 <span class=\"token keyword\">import<\/span> BeautifulSoup<br \/>\n<span class=\"token keyword\">from<\/span> dateutil <span class=\"token keyword\">import<\/span> parser <span class=\"token keyword\">as<\/span> date_parser<\/p>\n<p>BASE_DIR <span class=\"token operator\">&#061;<\/span> Path<span class=\"token punctuation\">(<\/span>__file__<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>resolve<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>parent<br \/>\nDATA_DIR <span class=\"token operator\">&#061;<\/span> BASE_DIR <span class=\"token operator\">\/<\/span> <span class=\"token string\">&#034;data&#034;<\/span><br \/>\nFIXTURE_DIR <span class=\"token operator\">&#061;<\/span> BASE_DIR <span class=\"token operator\">\/<\/span> <span class=\"token string\">&#034;fixtures&#034;<\/span><\/p>\n<p>DB_PATH <span class=\"token operator\">&#061;<\/span> DATA_DIR <span class=\"token operator\">\/<\/span> <span class=\"token string\">&#034;newspaper_issues.db&#034;<\/span><br \/>\nCSV_PATH <span class=\"token operator\">&#061;<\/span> DATA_DIR <span class=\"token operator\">\/<\/span> <span class=\"token string\">&#034;newspaper_issues.csv&#034;<\/span><\/p>\n<p>BASE_URL <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;https:\/\/example.com&#034;<\/span><br \/>\nDEFAULT_NEWSPAPER_NAME <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;\u793a\u4f8b\u65e5\u62a5&#034;<\/span><\/p>\n<p>USE_FIXTURE <span class=\"token operator\">&#061;<\/span> <span class=\"token boolean\">True<\/span><\/p>\n<p>REQUEST_TIMEOUT <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">(<\/span><span class=\"token number\">5<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">20<\/span><span class=\"token punctuation\">)<\/span><br \/>\nMIN_DELAY <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">0.8<\/span><br \/>\nMAX_DELAY <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">1.6<\/span><br \/>\nMAX_RETRIES <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">3<\/span><\/p>\n<p>logging<span class=\"token punctuation\">.<\/span>basicConfig<span class=\"token punctuation\">(<\/span><br \/>\n    level<span class=\"token operator\">&#061;<\/span>logging<span class=\"token punctuation\">.<\/span>INFO<span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token builtin\">format<\/span><span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;%(asctime)s | %(levelname)s | %(message)s&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token decorator annotation punctuation\">&#064;dataclass<\/span><br \/>\n<span class=\"token keyword\">class<\/span> <span class=\"token class-name\">IssueRecord<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    newspaper_name<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><br \/>\n    issue_no<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><br \/>\n    publish_date<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><br \/>\n    column_name<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><br \/>\n    topic<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><br \/>\n    digitization_status<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><br \/>\n    url<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><br \/>\n    content_hash<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;&#034;<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">fill_hash<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        raw <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;|&#034;<\/span><span class=\"token punctuation\">.<\/span>join<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><br \/>\n            self<span class=\"token punctuation\">.<\/span>newspaper_name <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            self<span class=\"token punctuation\">.<\/span>issue_no <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            self<span class=\"token punctuation\">.<\/span>publish_date <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            self<span class=\"token punctuation\">.<\/span>column_name <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            self<span class=\"token punctuation\">.<\/span>topic <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            self<span class=\"token punctuation\">.<\/span>digitization_status <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            self<span class=\"token punctuation\">.<\/span>url <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>content_hash <span class=\"token operator\">&#061;<\/span> hashlib<span class=\"token punctuation\">.<\/span>md5<span class=\"token punctuation\">(<\/span>raw<span class=\"token punctuation\">.<\/span>encode<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;utf-8&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>hexdigest<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">ensure_dirs<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    DATA_DIR<span class=\"token punctuation\">.<\/span>mkdir<span class=\"token punctuation\">(<\/span>exist_ok<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    FIXTURE_DIR<span class=\"token punctuation\">.<\/span>mkdir<span class=\"token punctuation\">(<\/span>exist_ok<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">write_fixture_files<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n    \u751f\u6210\u672c\u5730\u6837\u4f8b\u9875\u9762\u3002<\/p>\n<p>    \u771f\u5b9e\u9879\u76ee\u4e2d&#xff0c;\u8fd9\u90e8\u5206\u4e0d\u9700\u8981\u3002<br \/>\n    \u8fd9\u91cc\u53ea\u662f\u4e3a\u4e86\u8ba9\u793a\u4f8b\u4ee3\u7801\u4e0d\u4f9d\u8d56\u4efb\u4f55\u5916\u90e8\u7f51\u7ad9&#xff0c;\u4e5f\u80fd\u5b8c\u6574\u8dd1\u901a&#xff1a;<br \/>\n    1. \u65e5\u5386\u9875<br \/>\n    2. \u671f\u53f7\u5206\u9875\u7b2c 1 \u9875<br \/>\n    3. \u671f\u53f7\u5206\u9875\u7b2c 2 \u9875<br \/>\n    4. \u4e09\u4e2a\u8be6\u60c5\u9875<br \/>\n    &#034;&#034;&#034;<\/span><br \/>\n    calendar_html <span class=\"token operator\">&#061;<\/span> <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n    &lt;!doctype html&gt;<br \/>\n    &lt;html&gt;<br \/>\n    &lt;head&gt;&lt;meta charset&#061;&#034;utf-8&#034;&gt;&lt;title&gt;2024\u5e7405\u6708\u5386\u53f2\u65e5\u5386&lt;\/title&gt;&lt;\/head&gt;<br \/>\n    &lt;body&gt;<br \/>\n      &lt;div id&#061;&#034;calendar&#034; data-year&#061;&#034;2024&#034; data-month&#061;&#034;05&#034;&gt;<br \/>\n        &lt;a class&#061;&#034;issue-day&#034; data-date&#061;&#034;2024-05-01&#034; href&#061;&#034;\/archive\/2024\/05\/01\/page\/1.html&#034;&gt;2024-05-01&lt;\/a&gt;<br \/>\n        &lt;a class&#061;&#034;issue-day&#034; data-date&#061;&#034;2024-05-08&#034; href&#061;&#034;\/archive\/2024\/05\/08\/page\/1.html&#034;&gt;2024-05-08&lt;\/a&gt;<br \/>\n      &lt;\/div&gt;<br \/>\n    &lt;\/body&gt;<br \/>\n    &lt;\/html&gt;<br \/>\n    &#034;&#034;&#034;<\/span><\/p>\n<p>    issue_page_1 <span class=\"token operator\">&#061;<\/span> <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n    &lt;!doctype html&gt;<br \/>\n    &lt;html&gt;<br \/>\n    &lt;head&gt;&lt;meta charset&#061;&#034;utf-8&#034;&gt;&lt;title&gt;2024-05-01 \u7b2c1\u9875&lt;\/title&gt;&lt;\/head&gt;<br \/>\n    &lt;body&gt;<br \/>\n      &lt;div class&#061;&#034;issue-head&#034;&gt;<br \/>\n        &lt;span class&#061;&#034;newspaper&#034;&gt;\u793a\u4f8b\u65e5\u62a5&lt;\/span&gt;<br \/>\n        &lt;span class&#061;&#034;issue-no&#034;&gt;2024\u5e74\u7b2c05\u671f&lt;\/span&gt;<br \/>\n        &lt;span class&#061;&#034;publish-date&#034;&gt;2024-05-01&lt;\/span&gt;<br \/>\n      &lt;\/div&gt;<\/p>\n<p>      &lt;div class&#061;&#034;issue-list&#034;&gt;<br \/>\n        &lt;div class&#061;&#034;issue-item&#034;&gt;<br \/>\n          &lt;a class&#061;&#034;detail-link&#034; href&#061;&#034;\/detail\/001.html&#034;&gt;\u57ce\u5e02\u5efa\u8bbe\u4e13\u9898&lt;\/a&gt;<br \/>\n          &lt;span class&#061;&#034;column&#034;&gt;\u7efc\u5408\u65b0\u95fb&lt;\/span&gt;<br \/>\n          &lt;span class&#061;&#034;status&#034;&gt;\u5df2\u6570\u5b57\u5316&lt;\/span&gt;<br \/>\n        &lt;\/div&gt;<\/p>\n<p>        &lt;div class&#061;&#034;issue-item&#034;&gt;<br \/>\n          &lt;a class&#061;&#034;detail-link&#034; href&#061;&#034;\/detail\/002.html&#034;&gt;\u8001\u7167\u7247\u91cc\u7684\u8857\u533a\u8bb0\u5fc6&lt;\/a&gt;<br \/>\n          &lt;span class&#061;&#034;column&#034;&gt;\u6587\u5316\u526f\u520a&lt;\/span&gt;<br \/>\n          &lt;span class&#061;&#034;status&#034;&gt;\u4ec5\u76ee\u5f55&lt;\/span&gt;<br \/>\n        &lt;\/div&gt;<br \/>\n      &lt;\/div&gt;<\/p>\n<p>      &lt;div class&#061;&#034;pagination&#034;&gt;<br \/>\n        &lt;a class&#061;&#034;next&#034; href&#061;&#034;\/archive\/2024\/05\/01\/page\/2.html&#034;&gt;\u4e0b\u4e00\u9875&lt;\/a&gt;<br \/>\n      &lt;\/div&gt;<br \/>\n    &lt;\/body&gt;<br \/>\n    &lt;\/html&gt;<br \/>\n    &#034;&#034;&#034;<\/span><\/p>\n<p>    issue_page_2 <span class=\"token operator\">&#061;<\/span> <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n    &lt;!doctype html&gt;<br \/>\n    &lt;html&gt;<br \/>\n    &lt;head&gt;&lt;meta charset&#061;&#034;utf-8&#034;&gt;&lt;title&gt;2024-05-01 \u7b2c2\u9875&lt;\/title&gt;&lt;\/head&gt;<br \/>\n    &lt;body&gt;<br \/>\n      &lt;div class&#061;&#034;issue-head&#034;&gt;<br \/>\n        &lt;span class&#061;&#034;newspaper&#034;&gt;\u793a\u4f8b\u65e5\u62a5&lt;\/span&gt;<br \/>\n        &lt;span class&#061;&#034;issue-no&#034;&gt;2024\u5e74\u7b2c05\u671f&lt;\/span&gt;<br \/>\n        &lt;span class&#061;&#034;publish-date&#034;&gt;2024-05-01&lt;\/span&gt;<br \/>\n      &lt;\/div&gt;<\/p>\n<p>      &lt;div class&#061;&#034;issue-list&#034;&gt;<br \/>\n        &lt;div class&#061;&#034;issue-item&#034;&gt;<br \/>\n          &lt;a class&#061;&#034;detail-link&#034; href&#061;&#034;\/detail\/003.html&#034;&gt;\u5386\u53f2\u7248\u9762\u6570\u5b57\u5316\u8bf4\u660e&lt;\/a&gt;<br \/>\n          &lt;span class&#061;&#034;column&#034;&gt;\u8d44\u6599\u7d22\u5f15&lt;\/span&gt;<br \/>\n          &lt;span class&#061;&#034;status&#034;&gt;\u5f85\u6570\u5b57\u5316&lt;\/span&gt;<br \/>\n        &lt;\/div&gt;<br \/>\n      &lt;\/div&gt;<\/p>\n<p>      &lt;div class&#061;&#034;pagination&#034;&gt;&lt;\/div&gt;<br \/>\n    &lt;\/body&gt;<br \/>\n    &lt;\/html&gt;<br \/>\n    &#034;&#034;&#034;<\/span><\/p>\n<p>    detail_001 <span class=\"token operator\">&#061;<\/span> <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n    &lt;!doctype html&gt;<br \/>\n    &lt;html&gt;<br \/>\n    &lt;head&gt;&lt;meta charset&#061;&#034;utf-8&#034;&gt;&lt;title&gt;\u57ce\u5e02\u5efa\u8bbe\u4e13\u9898&lt;\/title&gt;&lt;\/head&gt;<br \/>\n    &lt;body&gt;<br \/>\n      &lt;h1 class&#061;&#034;topic&#034;&gt;\u57ce\u5e02\u5efa\u8bbe\u4e13\u9898&lt;\/h1&gt;<br \/>\n      &lt;ul class&#061;&#034;meta&#034;&gt;<br \/>\n        &lt;li&gt;&lt;span&gt;\u62a5\u520a\u540d&#xff1a;&lt;\/span&gt;&lt;b&gt;\u793a\u4f8b\u65e5\u62a5&lt;\/b&gt;&lt;\/li&gt;<br \/>\n        &lt;li&gt;&lt;span&gt;\u671f\u53f7&#xff1a;&lt;\/span&gt;&lt;b&gt;2024\u5e74\u7b2c05\u671f&lt;\/b&gt;&lt;\/li&gt;<br \/>\n        &lt;li&gt;&lt;span&gt;\u51fa\u7248\u65e5\u671f&#xff1a;&lt;\/span&gt;&lt;b&gt;2024-05-01&lt;\/b&gt;&lt;\/li&gt;<br \/>\n        &lt;li&gt;&lt;span&gt;\u680f\u76ee&#xff1a;&lt;\/span&gt;&lt;b&gt;\u7efc\u5408\u65b0\u95fb&lt;\/b&gt;&lt;\/li&gt;<br \/>\n        &lt;li&gt;&lt;span&gt;\u6570\u5b57\u5316\u72b6\u6001&#xff1a;&lt;\/span&gt;&lt;b&gt;\u5df2\u6570\u5b57\u5316&lt;\/b&gt;&lt;\/li&gt;<br \/>\n      &lt;\/ul&gt;<br \/>\n    &lt;\/body&gt;<br \/>\n    &lt;\/html&gt;<br \/>\n    &#034;&#034;&#034;<\/span><\/p>\n<p>    detail_002 <span class=\"token operator\">&#061;<\/span> <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n    &lt;!doctype html&gt;<br \/>\n    &lt;html&gt;<br \/>\n    &lt;head&gt;&lt;meta charset&#061;&#034;utf-8&#034;&gt;&lt;title&gt;\u8001\u7167\u7247\u91cc\u7684\u8857\u533a\u8bb0\u5fc6&lt;\/title&gt;&lt;\/head&gt;<br \/>\n    &lt;body&gt;<br \/>\n      &lt;h1 class&#061;&#034;topic&#034;&gt;\u8001\u7167\u7247\u91cc\u7684\u8857\u533a\u8bb0\u5fc6&lt;\/h1&gt;<br \/>\n      &lt;ul class&#061;&#034;meta&#034;&gt;<br \/>\n        &lt;li&gt;&lt;span&gt;\u62a5\u520a\u540d&#xff1a;&lt;\/span&gt;&lt;b&gt;\u793a\u4f8b\u65e5\u62a5&lt;\/b&gt;&lt;\/li&gt;<br \/>\n        &lt;li&gt;&lt;span&gt;\u671f\u53f7&#xff1a;&lt;\/span&gt;&lt;b&gt;2024\u5e74\u7b2c05\u671f&lt;\/b&gt;&lt;\/li&gt;<br \/>\n        &lt;li&gt;&lt;span&gt;\u51fa\u7248\u65e5\u671f&#xff1a;&lt;\/span&gt;&lt;b&gt;2024\u5e745\u67081\u65e5&lt;\/b&gt;&lt;\/li&gt;<br \/>\n        &lt;li&gt;&lt;span&gt;\u680f\u76ee&#xff1a;&lt;\/span&gt;&lt;b&gt;\u6587\u5316\u526f\u520a&lt;\/b&gt;&lt;\/li&gt;<br \/>\n        &lt;li&gt;&lt;span&gt;\u6570\u5b57\u5316\u72b6\u6001&#xff1a;&lt;\/span&gt;&lt;b&gt;\u4ec5\u76ee\u5f55&lt;\/b&gt;&lt;\/li&gt;<br \/>\n      &lt;\/ul&gt;<br \/>\n    &lt;\/body&gt;<br \/>\n    &lt;\/html&gt;<br \/>\n    &#034;&#034;&#034;<\/span><\/p>\n<p>    detail_003 <span class=\"token operator\">&#061;<\/span> <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n    &lt;!doctype html&gt;<br \/>\n    &lt;html&gt;<br \/>\n    &lt;head&gt;&lt;meta charset&#061;&#034;utf-8&#034;&gt;&lt;title&gt;\u5386\u53f2\u7248\u9762\u6570\u5b57\u5316\u8bf4\u660e&lt;\/title&gt;&lt;\/head&gt;<br \/>\n    &lt;body&gt;<br \/>\n      &lt;h1 class&#061;&#034;topic&#034;&gt;\u5386\u53f2\u7248\u9762\u6570\u5b57\u5316\u8bf4\u660e&lt;\/h1&gt;<br \/>\n      &lt;ul class&#061;&#034;meta&#034;&gt;<br \/>\n        &lt;li&gt;&lt;span&gt;\u62a5\u520a\u540d&#xff1a;&lt;\/span&gt;&lt;b&gt;\u793a\u4f8b\u65e5\u62a5&lt;\/b&gt;&lt;\/li&gt;<br \/>\n        &lt;li&gt;&lt;span&gt;\u671f\u53f7&#xff1a;&lt;\/span&gt;&lt;b&gt;2024\u5e74\u7b2c05\u671f&lt;\/b&gt;&lt;\/li&gt;<br \/>\n        &lt;li&gt;&lt;span&gt;\u51fa\u7248\u65e5\u671f&#xff1a;&lt;\/span&gt;&lt;b&gt;2024-05-01&lt;\/b&gt;&lt;\/li&gt;<br \/>\n        &lt;li&gt;&lt;span&gt;\u680f\u76ee&#xff1a;&lt;\/span&gt;&lt;b&gt;\u8d44\u6599\u7d22\u5f15&lt;\/b&gt;&lt;\/li&gt;<br \/>\n        &lt;li&gt;&lt;span&gt;\u6570\u5b57\u5316\u72b6\u6001&#xff1a;&lt;\/span&gt;&lt;b&gt;\u5f85\u6570\u5b57\u5316&lt;\/b&gt;&lt;\/li&gt;<br \/>\n      &lt;\/ul&gt;<br \/>\n    &lt;\/body&gt;<br \/>\n    &lt;\/html&gt;<br \/>\n    &#034;&#034;&#034;<\/span><\/p>\n<p>    files <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n        <span class=\"token string\">&#034;calendar_2024_05.html&#034;<\/span><span class=\"token punctuation\">:<\/span> calendar_html<span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string\">&#034;issue_2024_05_01_page_1.html&#034;<\/span><span class=\"token punctuation\">:<\/span> issue_page_1<span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string\">&#034;issue_2024_05_01_page_2.html&#034;<\/span><span class=\"token punctuation\">:<\/span> issue_page_2<span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string\">&#034;detail_001.html&#034;<\/span><span class=\"token punctuation\">:<\/span> detail_001<span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string\">&#034;detail_002.html&#034;<\/span><span class=\"token punctuation\">:<\/span> detail_002<span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string\">&#034;detail_003.html&#034;<\/span><span class=\"token punctuation\">:<\/span> detail_003<span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><\/p>\n<p>    <span class=\"token keyword\">for<\/span> filename<span class=\"token punctuation\">,<\/span> html <span class=\"token keyword\">in<\/span> files<span class=\"token punctuation\">.<\/span>items<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        path <span class=\"token operator\">&#061;<\/span> FIXTURE_DIR <span class=\"token operator\">\/<\/span> filename<br \/>\n        path<span class=\"token punctuation\">.<\/span>write_text<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span> encoding<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;utf-8&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">Fetcher<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n    \u8bf7\u6c42\u5c42\u3002<\/p>\n<p>    USE_FIXTURE&#061;True \u65f6&#xff0c;\u4ece\u672c\u5730 fixtures \u76ee\u5f55\u8bfb\u53d6 HTML\u3002<br \/>\n    USE_FIXTURE&#061;False \u65f6&#xff0c;\u4f7f\u7528 requests \u8bf7\u6c42\u771f\u5b9e\u7ad9\u70b9\u3002<\/p>\n<p>    \u8fd9\u6837\u8bbe\u8ba1\u7684\u597d\u5904&#xff1a;<br \/>\n    1. \u672c\u5730\u53ef\u4ee5\u7a33\u5b9a\u590d\u73b0\u5b9e\u9a8c\u3002<br \/>\n    2. \u6539\u771f\u5b9e\u7ad9\u70b9\u65f6&#xff0c;\u53ea\u9700\u8981\u66ff\u6362 URL \u6620\u5c04\u548c\u9009\u62e9\u5668\u3002<br \/>\n    &#034;&#034;&#034;<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">__init__<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>session <span class=\"token operator\">&#061;<\/span> requests<span class=\"token punctuation\">.<\/span>Session<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>session<span class=\"token punctuation\">.<\/span>headers<span class=\"token punctuation\">.<\/span>update<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">{<\/span><br \/>\n            <span class=\"token string\">&#034;User-Agent&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token punctuation\">(<\/span><br \/>\n                <span class=\"token string\">&#034;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) &#034;<\/span><br \/>\n                <span class=\"token string\">&#034;AppleWebKit\/537.36 (KHTML, like Gecko) &#034;<\/span><br \/>\n                <span class=\"token string\">&#034;Chrome\/124.0 Safari\/537.36&#034;<\/span><br \/>\n            <span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;Accept&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;text\/html,application\/xhtml&#043;xml,application\/xml;q&#061;0.9,*\/*;q&#061;0.8&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;Accept-Language&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;zh-CN,zh;q&#061;0.9,en;q&#061;0.8&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;Connection&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;keep-alive&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">fetch<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> referer<span class=\"token punctuation\">:<\/span> Optional<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> USE_FIXTURE<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> self<span class=\"token punctuation\">.<\/span>fetch_fixture<span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">)<\/span><\/p>\n<p>        headers <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><span class=\"token punctuation\">}<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> referer<span class=\"token punctuation\">:<\/span><br \/>\n            headers<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;Referer&#034;<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> referer<\/p>\n<p>        last_error <span class=\"token operator\">&#061;<\/span> <span class=\"token boolean\">None<\/span><\/p>\n<p>        <span class=\"token keyword\">for<\/span> attempt <span class=\"token keyword\">in<\/span> <span class=\"token builtin\">range<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span> MAX_RETRIES <span class=\"token operator\">&#043;<\/span> <span class=\"token number\">1<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                self<span class=\"token punctuation\">.<\/span>polite_sleep<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n                response <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>session<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><br \/>\n                    url<span class=\"token punctuation\">,<\/span><br \/>\n                    headers<span class=\"token operator\">&#061;<\/span>headers<span class=\"token punctuation\">,<\/span><br \/>\n                    timeout<span class=\"token operator\">&#061;<\/span>REQUEST_TIMEOUT<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token punctuation\">)<\/span><\/p>\n<p>                <span class=\"token keyword\">if<\/span> response<span class=\"token punctuation\">.<\/span>status_code <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token number\">404<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                    logging<span class=\"token punctuation\">.<\/span>warning<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;404 not found: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">)<\/span><br \/>\n                    <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;&#034;<\/span><\/p>\n<p>                <span class=\"token keyword\">if<\/span> response<span class=\"token punctuation\">.<\/span>status_code <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token number\">429<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                    wait_seconds <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">2<\/span> <span class=\"token operator\">**<\/span> attempt <span class=\"token operator\">*<\/span> <span class=\"token number\">3<\/span><br \/>\n                    logging<span class=\"token punctuation\">.<\/span>warning<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;429 too many requests, sleep %s seconds: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> wait_seconds<span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">)<\/span><br \/>\n                    time<span class=\"token punctuation\">.<\/span>sleep<span class=\"token punctuation\">(<\/span>wait_seconds<span class=\"token punctuation\">)<\/span><br \/>\n                    <span class=\"token keyword\">continue<\/span><\/p>\n<p>                <span class=\"token keyword\">if<\/span> response<span class=\"token punctuation\">.<\/span>status_code <span class=\"token keyword\">in<\/span> <span class=\"token punctuation\">(<\/span><span class=\"token number\">500<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">502<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">503<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">504<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                    wait_seconds <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">2<\/span> <span class=\"token operator\">**<\/span> attempt<br \/>\n                    logging<span class=\"token punctuation\">.<\/span>warning<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;server error %s, retry after %s seconds: %s&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                                    response<span class=\"token punctuation\">.<\/span>status_code<span class=\"token punctuation\">,<\/span> wait_seconds<span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">)<\/span><br \/>\n                    time<span class=\"token punctuation\">.<\/span>sleep<span class=\"token punctuation\">(<\/span>wait_seconds<span class=\"token punctuation\">)<\/span><br \/>\n                    <span class=\"token keyword\">continue<\/span><\/p>\n<p>                response<span class=\"token punctuation\">.<\/span>raise_for_status<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>                <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> response<span class=\"token punctuation\">.<\/span>encoding <span class=\"token keyword\">or<\/span> response<span class=\"token punctuation\">.<\/span>encoding<span class=\"token punctuation\">.<\/span>lower<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token string\">&#034;iso-8859-1&#034;<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                    response<span class=\"token punctuation\">.<\/span>encoding <span class=\"token operator\">&#061;<\/span> response<span class=\"token punctuation\">.<\/span>apparent_encoding<\/p>\n<p>                <span class=\"token keyword\">return<\/span> response<span class=\"token punctuation\">.<\/span>text<\/p>\n<p>            <span class=\"token keyword\">except<\/span> requests<span class=\"token punctuation\">.<\/span>RequestException <span class=\"token keyword\">as<\/span> exc<span class=\"token punctuation\">:<\/span><br \/>\n                last_error <span class=\"token operator\">&#061;<\/span> exc<br \/>\n                wait_seconds <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">2<\/span> <span class=\"token operator\">**<\/span> attempt<br \/>\n                logging<span class=\"token punctuation\">.<\/span>warning<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;request failed attempt&#061;%s url&#061;%s error&#061;%s&#034;<\/span><span class=\"token punctuation\">,<\/span> attempt<span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">,<\/span> exc<span class=\"token punctuation\">)<\/span><br \/>\n                time<span class=\"token punctuation\">.<\/span>sleep<span class=\"token punctuation\">(<\/span>wait_seconds<span class=\"token punctuation\">)<\/span><\/p>\n<p>        logging<span class=\"token punctuation\">.<\/span>error<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;request finally failed url&#061;%s error&#061;%s&#034;<\/span><span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">,<\/span> last_error<span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;&#034;<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">fetch_fixture<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n        \u5c06\u793a\u4f8b URL \u6620\u5c04\u5230\u672c\u5730 HTML \u6587\u4ef6\u3002<\/p>\n<p>        \u793a\u4f8b&#xff1a;<br \/>\n        https:\/\/example.com\/archive\/2024\/05\/calendar.html<br \/>\n        -&gt; fixtures\/calendar_2024_05.html<br \/>\n        &#034;&#034;&#034;<\/span><br \/>\n        mapping <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n            <span class=\"token string\">&#034;\/archive\/2024\/05\/calendar.html&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;calendar_2024_05.html&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;\/archive\/2024\/05\/01\/page\/1.html&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;issue_2024_05_01_page_1.html&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;\/archive\/2024\/05\/01\/page\/2.html&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;issue_2024_05_01_page_2.html&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;\/detail\/001.html&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;detail_001.html&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;\/detail\/002.html&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;detail_002.html&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;\/detail\/003.html&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;detail_003.html&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">}<\/span><\/p>\n<p>        path_part <span class=\"token operator\">&#061;<\/span> url<span class=\"token punctuation\">.<\/span>replace<span class=\"token punctuation\">(<\/span>BASE_URL<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        filename <span class=\"token operator\">&#061;<\/span> mapping<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span>path_part<span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> filename<span class=\"token punctuation\">:<\/span><br \/>\n            logging<span class=\"token punctuation\">.<\/span>warning<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;fixture mapping not found: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;&#034;<\/span><\/p>\n<p>        path <span class=\"token operator\">&#061;<\/span> FIXTURE_DIR <span class=\"token operator\">\/<\/span> filename<br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> path<span class=\"token punctuation\">.<\/span>exists<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            logging<span class=\"token punctuation\">.<\/span>warning<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;fixture file not found: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> path<span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;&#034;<\/span><\/p>\n<p>        self<span class=\"token punctuation\">.<\/span>polite_sleep<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> path<span class=\"token punctuation\">.<\/span>read_text<span class=\"token punctuation\">(<\/span>encoding<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;utf-8&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token decorator annotation punctuation\">&#064;staticmethod<\/span><br \/>\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">polite_sleep<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        time<span class=\"token punctuation\">.<\/span>sleep<span class=\"token punctuation\">(<\/span>random<span class=\"token punctuation\">.<\/span>uniform<span class=\"token punctuation\">(<\/span>MIN_DELAY<span class=\"token punctuation\">,<\/span> MAX_DELAY<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">Parser<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n    \u89e3\u6790\u5c42\u3002<\/p>\n<p>    \u8fd9\u91cc\u7684\u9009\u62e9\u5668\u662f\u9488\u5bf9\u793a\u4f8b HTML \u5199\u7684\u3002<br \/>\n    \u771f\u5b9e\u9879\u76ee\u4e2d&#xff0c;\u4f60\u9700\u8981\u6839\u636e\u76ee\u6807\u7ad9\u70b9\u9875\u9762\u7ed3\u6784\u4fee\u6539\u9009\u62e9\u5668\u3002<br \/>\n    &#034;&#034;&#034;<\/span><\/p>\n<p>    <span class=\"token decorator annotation punctuation\">&#064;staticmethod<\/span><br \/>\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">soup<\/span><span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> BeautifulSoup<span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> BeautifulSoup<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;lxml&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">parse_calendar<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> html<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> List<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n        \u89e3\u6790\u67d0\u5e74\u67d0\u6708\u65e5\u5386\u9875\u9762&#xff0c;\u8fd4\u56de\u8be5\u6708\u6240\u6709\u671f\u53f7\u5165\u53e3 URL\u3002<br \/>\n        &#034;&#034;&#034;<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> html<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><\/p>\n<p>        soup <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>soup<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">)<\/span><br \/>\n        urls <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><\/p>\n<p>        <span class=\"token keyword\">for<\/span> a <span class=\"token keyword\">in<\/span> soup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;a.issue-day&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            href <span class=\"token operator\">&#061;<\/span> a<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;href&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> href<span class=\"token punctuation\">:<\/span><br \/>\n                <span class=\"token keyword\">continue<\/span><br \/>\n            urls<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span>urljoin<span class=\"token punctuation\">(<\/span>BASE_URL<span class=\"token punctuation\">,<\/span> href<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">return<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">(<\/span><span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">.<\/span>fromkeys<span class=\"token punctuation\">(<\/span>urls<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">parse_issue_list<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> html<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> page_url<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> Dict<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">object<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n        \u89e3\u6790\u67d0\u4e00\u671f\u7684\u5217\u8868\u9875\u3002<\/p>\n<p>        \u8fd4\u56de&#xff1a;<br \/>\n        {<br \/>\n            &#034;page_context&#034;: {&#8230;},<br \/>\n            &#034;items&#034;: [&#8230;],<br \/>\n            &#034;next_url&#034;: &#034;&#8230;&#034;<br \/>\n        }<br \/>\n        &#034;&#034;&#034;<\/span><br \/>\n        result <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n            <span class=\"token string\">&#034;page_context&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token punctuation\">{<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;items&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;next_url&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">}<\/span><\/p>\n<p>        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> html<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> result<\/p>\n<p>        soup <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>soup<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">)<\/span><\/p>\n<p>        page_context <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n            <span class=\"token string\">&#034;newspaper_name&#034;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>text_or_empty<span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.issue-head .newspaper&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;issue_no&#034;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>text_or_empty<span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.issue-head .issue-no&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;publish_date&#034;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>text_or_empty<span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.issue-head .publish-date&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">}<\/span><br \/>\n        result<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;page_context&#034;<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> page_context<\/p>\n<p>        items <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n        <span class=\"token keyword\">for<\/span> node <span class=\"token keyword\">in<\/span> soup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.issue-list .issue-item&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            link_node <span class=\"token operator\">&#061;<\/span> node<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;a.detail-link&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> link_node<span class=\"token punctuation\">:<\/span><br \/>\n                <span class=\"token keyword\">continue<\/span><\/p>\n<p>            href <span class=\"token operator\">&#061;<\/span> link_node<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;href&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> href<span class=\"token punctuation\">:<\/span><br \/>\n                <span class=\"token keyword\">continue<\/span><\/p>\n<p>            item <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n                <span class=\"token string\">&#034;topic&#034;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>text_or_empty<span class=\"token punctuation\">(<\/span>link_node<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;url&#034;<\/span><span class=\"token punctuation\">:<\/span> urljoin<span class=\"token punctuation\">(<\/span>BASE_URL<span class=\"token punctuation\">,<\/span> href<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;column_name&#034;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>text_or_empty<span class=\"token punctuation\">(<\/span>node<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.column&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;digitization_status&#034;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>text_or_empty<span class=\"token punctuation\">(<\/span>node<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.status&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token punctuation\">}<\/span><br \/>\n            items<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span>item<span class=\"token punctuation\">)<\/span><\/p>\n<p>        result<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;items&#034;<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> items<\/p>\n<p>        next_node <span class=\"token operator\">&#061;<\/span> soup<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.pagination a.next&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> next_node <span class=\"token keyword\">and<\/span> next_node<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;href&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            result<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;next_url&#034;<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> urljoin<span class=\"token punctuation\">(<\/span>BASE_URL<span class=\"token punctuation\">,<\/span> next_node<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;href&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">return<\/span> result<\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">parse_detail<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> html<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> detail_url<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> Dict<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n        \u89e3\u6790\u8be6\u60c5\u9875\u5b57\u6bb5\u3002<br \/>\n        &#034;&#034;&#034;<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> html<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> <span class=\"token punctuation\">{<\/span><span class=\"token punctuation\">}<\/span><\/p>\n<p>        soup <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>soup<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">)<\/span><\/p>\n<p>        data <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n            <span class=\"token string\">&#034;newspaper_name&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;issue_no&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;publish_date&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;column_name&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;topic&#034;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>text_or_empty<span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;h1.topic&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;digitization_status&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;url&#034;<\/span><span class=\"token punctuation\">:<\/span> detail_url<span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">}<\/span><\/p>\n<p>        label_mapping <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n            <span class=\"token string\">&#034;\u62a5\u520a\u540d&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;newspaper_name&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;\u671f\u53f7&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;issue_no&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;\u51fa\u7248\u65e5\u671f&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;publish_date&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;\u680f\u76ee&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;column_name&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;\u6570\u5b57\u5316\u72b6\u6001&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;digitization_status&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">}<\/span><\/p>\n<p>        <span class=\"token keyword\">for<\/span> li <span class=\"token keyword\">in<\/span> soup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;ul.meta li&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            full_text <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>normalize_space<span class=\"token punctuation\">(<\/span>li<span class=\"token punctuation\">.<\/span>get_text<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034; &#034;<\/span><span class=\"token punctuation\">,<\/span> strip<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> full_text<span class=\"token punctuation\">:<\/span><br \/>\n                <span class=\"token keyword\">continue<\/span><\/p>\n<p>            key_text <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;&#034;<\/span><br \/>\n            value_text <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;&#034;<\/span><\/p>\n<p>            span <span class=\"token operator\">&#061;<\/span> li<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;span&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            b <span class=\"token operator\">&#061;<\/span> li<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;b&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>            <span class=\"token keyword\">if<\/span> span<span class=\"token punctuation\">:<\/span><br \/>\n                key_text <span class=\"token operator\">&#061;<\/span> span<span class=\"token punctuation\">.<\/span>get_text<span class=\"token punctuation\">(<\/span>strip<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>replace<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;&#xff1a;&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>replace<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;:&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>            <span class=\"token keyword\">if<\/span> b<span class=\"token punctuation\">:<\/span><br \/>\n                value_text <span class=\"token operator\">&#061;<\/span> b<span class=\"token punctuation\">.<\/span>get_text<span class=\"token punctuation\">(<\/span>strip<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">else<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                value_text <span class=\"token operator\">&#061;<\/span> re<span class=\"token punctuation\">.<\/span>sub<span class=\"token punctuation\">(<\/span><span class=\"token string\">r&#034;^[^:&#xff1a;]&#043;[:&#xff1a;]\\\\s*&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span> full_text<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>            field <span class=\"token operator\">&#061;<\/span> label_mapping<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span>key_text<span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> field<span class=\"token punctuation\">:<\/span><br \/>\n                data<span class=\"token punctuation\">[<\/span>field<span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> value_text<\/p>\n<p>        <span class=\"token keyword\">return<\/span> data<\/p>\n<p>    <span class=\"token decorator annotation punctuation\">&#064;staticmethod<\/span><br \/>\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">text_or_empty<\/span><span class=\"token punctuation\">(<\/span>node<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> node<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;&#034;<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> Parser<span class=\"token punctuation\">.<\/span>normalize_space<span class=\"token punctuation\">(<\/span>node<span class=\"token punctuation\">.<\/span>get_text<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034; &#034;<\/span><span class=\"token punctuation\">,<\/span> strip<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token decorator annotation punctuation\">&#064;staticmethod<\/span><br \/>\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">normalize_space<\/span><span class=\"token punctuation\">(<\/span>text<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> re<span class=\"token punctuation\">.<\/span>sub<span class=\"token punctuation\">(<\/span><span class=\"token string\">r&#034;\\\\s&#043;&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034; &#034;<\/span><span class=\"token punctuation\">,<\/span> text <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">Cleaner<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n    \u6e05\u6d17\u5c42\u3002<br \/>\n    &#034;&#034;&#034;<\/span><\/p>\n<p>    <span class=\"token decorator annotation punctuation\">&#064;staticmethod<\/span><br \/>\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">clean_record<\/span><span class=\"token punctuation\">(<\/span>raw<span class=\"token punctuation\">:<\/span> Dict<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> fallback<span class=\"token punctuation\">:<\/span> Dict<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> Optional<span class=\"token punctuation\">[<\/span>IssueRecord<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        url <span class=\"token operator\">&#061;<\/span> raw<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;url&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> fallback<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;url&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#034;&#034;<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> url<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> <span class=\"token boolean\">None<\/span><\/p>\n<p>        newspaper_name <span class=\"token operator\">&#061;<\/span> raw<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;newspaper_name&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> fallback<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;newspaper_name&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> DEFAULT_NEWSPAPER_NAME<br \/>\n        issue_no <span class=\"token operator\">&#061;<\/span> raw<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;issue_no&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> fallback<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;issue_no&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#034;&#034;<\/span><br \/>\n        publish_date <span class=\"token operator\">&#061;<\/span> raw<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;publish_date&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> fallback<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;publish_date&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#034;&#034;<\/span><br \/>\n        column_name <span class=\"token operator\">&#061;<\/span> raw<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;column_name&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> fallback<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;column_name&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#034;&#034;<\/span><br \/>\n        topic <span class=\"token operator\">&#061;<\/span> raw<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;topic&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> fallback<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;topic&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#034;&#034;<\/span><br \/>\n        digitization_status <span class=\"token operator\">&#061;<\/span> raw<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;digitization_status&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> fallback<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;digitization_status&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#034;\u672a\u77e5&#034;<\/span><\/p>\n<p>        publish_date <span class=\"token operator\">&#061;<\/span> Cleaner<span class=\"token punctuation\">.<\/span>normalize_date<span class=\"token punctuation\">(<\/span>publish_date<span class=\"token punctuation\">)<\/span><br \/>\n        digitization_status <span class=\"token operator\">&#061;<\/span> Cleaner<span class=\"token punctuation\">.<\/span>normalize_status<span class=\"token punctuation\">(<\/span>digitization_status<span class=\"token punctuation\">)<\/span><\/p>\n<p>        record <span class=\"token operator\">&#061;<\/span> IssueRecord<span class=\"token punctuation\">(<\/span><br \/>\n            newspaper_name<span class=\"token operator\">&#061;<\/span>newspaper_name<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            issue_no<span class=\"token operator\">&#061;<\/span>issue_no<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            publish_date<span class=\"token operator\">&#061;<\/span>publish_date<span class=\"token punctuation\">,<\/span><br \/>\n            column_name<span class=\"token operator\">&#061;<\/span>column_name<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            topic<span class=\"token operator\">&#061;<\/span>topic<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            digitization_status<span class=\"token operator\">&#061;<\/span>digitization_status<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            url<span class=\"token operator\">&#061;<\/span>url<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">)<\/span><br \/>\n        record<span class=\"token punctuation\">.<\/span>fill_hash<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> record<\/p>\n<p>    <span class=\"token decorator annotation punctuation\">&#064;staticmethod<\/span><br \/>\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">normalize_date<\/span><span class=\"token punctuation\">(<\/span>value<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        value <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">(<\/span>value <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> value<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;&#034;<\/span><\/p>\n<p>        value <span class=\"token operator\">&#061;<\/span> value<span class=\"token punctuation\">.<\/span>replace<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u5e74&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;-&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>replace<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u6708&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;-&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>replace<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u65e5&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        value <span class=\"token operator\">&#061;<\/span> re<span class=\"token punctuation\">.<\/span>sub<span class=\"token punctuation\">(<\/span><span class=\"token string\">r&#034;[.\/]&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;-&#034;<\/span><span class=\"token punctuation\">,<\/span> value<span class=\"token punctuation\">)<\/span><br \/>\n        value <span class=\"token operator\">&#061;<\/span> re<span class=\"token punctuation\">.<\/span>sub<span class=\"token punctuation\">(<\/span><span class=\"token string\">r&#034;\\\\s&#043;&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span> value<span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            dt <span class=\"token operator\">&#061;<\/span> date_parser<span class=\"token punctuation\">.<\/span>parse<span class=\"token punctuation\">(<\/span>value<span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> dt<span class=\"token punctuation\">.<\/span>strftime<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;%Y-%m-%d&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">except<\/span> Exception<span class=\"token punctuation\">:<\/span><br \/>\n            logging<span class=\"token punctuation\">.<\/span>warning<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;date parse failed: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> value<span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> value<\/p>\n<p>    <span class=\"token decorator annotation punctuation\">&#064;staticmethod<\/span><br \/>\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">normalize_status<\/span><span class=\"token punctuation\">(<\/span>value<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        value <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">(<\/span>value <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> value<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;\u672a\u77e5&#034;<\/span><\/p>\n<p>        <span class=\"token keyword\">if<\/span> <span class=\"token string\">&#034;\u5df2&#034;<\/span> <span class=\"token keyword\">in<\/span> value <span class=\"token keyword\">and<\/span> <span class=\"token string\">&#034;\u6570\u5b57&#034;<\/span> <span class=\"token keyword\">in<\/span> value<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;\u5df2\u6570\u5b57\u5316&#034;<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token string\">&#034;\u5f85&#034;<\/span> <span class=\"token keyword\">in<\/span> value <span class=\"token keyword\">and<\/span> <span class=\"token string\">&#034;\u6570\u5b57&#034;<\/span> <span class=\"token keyword\">in<\/span> value<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;\u5f85\u6570\u5b57\u5316&#034;<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token string\">&#034;\u672a&#034;<\/span> <span class=\"token keyword\">in<\/span> value <span class=\"token keyword\">and<\/span> <span class=\"token string\">&#034;\u6570\u5b57&#034;<\/span> <span class=\"token keyword\">in<\/span> value<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;\u672a\u6570\u5b57\u5316&#034;<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token string\">&#034;\u76ee\u5f55&#034;<\/span> <span class=\"token keyword\">in<\/span> value<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;\u4ec5\u76ee\u5f55&#034;<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> value<\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">Storage<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n    SQLite \u5b58\u50a8\u5c42\u3002<br \/>\n    &#034;&#034;&#034;<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">__init__<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> db_path<span class=\"token punctuation\">:<\/span> Path<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>db_path <span class=\"token operator\">&#061;<\/span> db_path<br \/>\n        self<span class=\"token punctuation\">.<\/span>conn <span class=\"token operator\">&#061;<\/span> sqlite3<span class=\"token punctuation\">.<\/span>connect<span class=\"token punctuation\">(<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">(<\/span>db_path<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>conn<span class=\"token punctuation\">.<\/span>row_factory <span class=\"token operator\">&#061;<\/span> sqlite3<span class=\"token punctuation\">.<\/span>Row<\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">init_db<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        sql <span class=\"token operator\">&#061;<\/span> <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n        CREATE TABLE IF NOT EXISTS newspaper_issues (<br \/>\n            id INTEGER PRIMARY KEY AUTOINCREMENT,<br \/>\n            newspaper_name TEXT NOT NULL,<br \/>\n            issue_no TEXT,<br \/>\n            publish_date TEXT,<br \/>\n            column_name TEXT,<br \/>\n            topic TEXT,<br \/>\n            digitization_status TEXT,<br \/>\n            url TEXT NOT NULL UNIQUE,<br \/>\n            content_hash TEXT,<br \/>\n            created_at TEXT NOT NULL,<br \/>\n            updated_at TEXT NOT NULL<br \/>\n        );<br \/>\n        &#034;&#034;&#034;<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>conn<span class=\"token punctuation\">.<\/span>execute<span class=\"token punctuation\">(<\/span>sql<span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>conn<span class=\"token punctuation\">.<\/span>execute<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;CREATE INDEX IF NOT EXISTS idx_publish_date ON newspaper_issues(publish_date);&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>conn<span class=\"token punctuation\">.<\/span>execute<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;CREATE INDEX IF NOT EXISTS idx_issue_no ON newspaper_issues(issue_no);&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>conn<span class=\"token punctuation\">.<\/span>execute<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;CREATE INDEX IF NOT EXISTS idx_column_name ON newspaper_issues(column_name);&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>conn<span class=\"token punctuation\">.<\/span>commit<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">upsert<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> record<span class=\"token punctuation\">:<\/span> IssueRecord<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        now <span class=\"token operator\">&#061;<\/span> datetime<span class=\"token punctuation\">.<\/span>now<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strftime<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;%Y-%m-%d %H:%M:%S&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        sql <span class=\"token operator\">&#061;<\/span> <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n        INSERT INTO newspaper_issues (<br \/>\n            newspaper_name,<br \/>\n            issue_no,<br \/>\n            publish_date,<br \/>\n            column_name,<br \/>\n            topic,<br \/>\n            digitization_status,<br \/>\n            url,<br \/>\n            content_hash,<br \/>\n            created_at,<br \/>\n            updated_at<br \/>\n        )<br \/>\n        VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)<br \/>\n        ON CONFLICT(url) DO UPDATE SET<br \/>\n            newspaper_name&#061;excluded.newspaper_name,<br \/>\n            issue_no&#061;excluded.issue_no,<br \/>\n            publish_date&#061;excluded.publish_date,<br \/>\n            column_name&#061;excluded.column_name,<br \/>\n            topic&#061;excluded.topic,<br \/>\n            digitization_status&#061;excluded.digitization_status,<br \/>\n            content_hash&#061;excluded.content_hash,<br \/>\n            updated_at&#061;excluded.updated_at;<br \/>\n        &#034;&#034;&#034;<\/span><\/p>\n<p>        self<span class=\"token punctuation\">.<\/span>conn<span class=\"token punctuation\">.<\/span>execute<span class=\"token punctuation\">(<\/span>sql<span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">(<\/span><br \/>\n            record<span class=\"token punctuation\">.<\/span>newspaper_name<span class=\"token punctuation\">,<\/span><br \/>\n            record<span class=\"token punctuation\">.<\/span>issue_no<span class=\"token punctuation\">,<\/span><br \/>\n            record<span class=\"token punctuation\">.<\/span>publish_date<span class=\"token punctuation\">,<\/span><br \/>\n            record<span class=\"token punctuation\">.<\/span>column_name<span class=\"token punctuation\">,<\/span><br \/>\n            record<span class=\"token punctuation\">.<\/span>topic<span class=\"token punctuation\">,<\/span><br \/>\n            record<span class=\"token punctuation\">.<\/span>digitization_status<span class=\"token punctuation\">,<\/span><br \/>\n            record<span class=\"token punctuation\">.<\/span>url<span class=\"token punctuation\">,<\/span><br \/>\n            record<span class=\"token punctuation\">.<\/span>content_hash<span class=\"token punctuation\">,<\/span><br \/>\n            now<span class=\"token punctuation\">,<\/span><br \/>\n            now<span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>conn<span class=\"token punctuation\">.<\/span>commit<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">export_csv<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> csv_path<span class=\"token punctuation\">:<\/span> Path<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        query <span class=\"token operator\">&#061;<\/span> <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n        SELECT<br \/>\n            newspaper_name AS \u62a5\u520a\u540d,<br \/>\n            issue_no AS \u671f\u53f7,<br \/>\n            publish_date AS \u51fa\u7248\u65e5\u671f,<br \/>\n            column_name AS \u680f\u76ee,<br \/>\n            topic AS \u4e3b\u9898,<br \/>\n            digitization_status AS \u6570\u5b57\u5316\u72b6\u6001,<br \/>\n            url AS \u94fe\u63a5<br \/>\n        FROM newspaper_issues<br \/>\n        ORDER BY publish_date, issue_no, id;<br \/>\n        &#034;&#034;&#034;<\/span><br \/>\n        df <span class=\"token operator\">&#061;<\/span> pd<span class=\"token punctuation\">.<\/span>read_sql_query<span class=\"token punctuation\">(<\/span>query<span class=\"token punctuation\">,<\/span> self<span class=\"token punctuation\">.<\/span>conn<span class=\"token punctuation\">)<\/span><br \/>\n        df<span class=\"token punctuation\">.<\/span>to_csv<span class=\"token punctuation\">(<\/span>csv_path<span class=\"token punctuation\">,<\/span> index<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">False<\/span><span class=\"token punctuation\">,<\/span> encoding<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;utf-8-sig&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">preview<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> limit<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">int<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">5<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> List<span class=\"token punctuation\">[<\/span>sqlite3<span class=\"token punctuation\">.<\/span>Row<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        sql <span class=\"token operator\">&#061;<\/span> <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n        SELECT newspaper_name, issue_no, publish_date, column_name, topic, digitization_status, url<br \/>\n        FROM newspaper_issues<br \/>\n        ORDER BY id<br \/>\n        LIMIT ?;<br \/>\n        &#034;&#034;&#034;<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">.<\/span>conn<span class=\"token punctuation\">.<\/span>execute<span class=\"token punctuation\">(<\/span>sql<span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">(<\/span>limit<span class=\"token punctuation\">,<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">close<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>conn<span class=\"token punctuation\">.<\/span>close<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">NewspaperIssueCrawler<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n    \u722c\u866b\u8c03\u5ea6\u5c42\u3002<br \/>\n    &#034;&#034;&#034;<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">__init__<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>fetcher <span class=\"token operator\">&#061;<\/span> Fetcher<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>parser <span class=\"token operator\">&#061;<\/span> Parser<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>cleaner <span class=\"token operator\">&#061;<\/span> Cleaner<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>storage <span class=\"token operator\">&#061;<\/span> Storage<span class=\"token punctuation\">(<\/span>DB_PATH<span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">run<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>storage<span class=\"token punctuation\">.<\/span>init_db<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        years_months <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><br \/>\n            <span class=\"token punctuation\">(<\/span><span class=\"token number\">2024<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">5<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">]<\/span><\/p>\n<p>        total_saved <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">0<\/span><\/p>\n<p>        <span class=\"token keyword\">for<\/span> year<span class=\"token punctuation\">,<\/span> month <span class=\"token keyword\">in<\/span> years_months<span class=\"token punctuation\">:<\/span><br \/>\n            calendar_url <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>build_calendar_url<span class=\"token punctuation\">(<\/span>year<span class=\"token punctuation\">,<\/span> month<span class=\"token punctuation\">)<\/span><br \/>\n            logging<span class=\"token punctuation\">.<\/span>info<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;fetch calendar: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> calendar_url<span class=\"token punctuation\">)<\/span><br \/>\n            calendar_html <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>fetcher<span class=\"token punctuation\">.<\/span>fetch<span class=\"token punctuation\">(<\/span>calendar_url<span class=\"token punctuation\">)<\/span><\/p>\n<p>            issue_entry_urls <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>parser<span class=\"token punctuation\">.<\/span>parse_calendar<span class=\"token punctuation\">(<\/span>calendar_html<span class=\"token punctuation\">)<\/span><br \/>\n            logging<span class=\"token punctuation\">.<\/span>info<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;calendar parsed issue entries: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>issue_entry_urls<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>            <span class=\"token keyword\">for<\/span> issue_entry_url <span class=\"token keyword\">in<\/span> issue_entry_urls<span class=\"token punctuation\">:<\/span><br \/>\n                saved <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>crawl_issue_pages<span class=\"token punctuation\">(<\/span>issue_entry_url<span class=\"token punctuation\">)<\/span><br \/>\n                total_saved <span class=\"token operator\">&#043;&#061;<\/span> saved<\/p>\n<p>        self<span class=\"token punctuation\">.<\/span>storage<span class=\"token punctuation\">.<\/span>export_csv<span class=\"token punctuation\">(<\/span>CSV_PATH<span class=\"token punctuation\">)<\/span><br \/>\n        logging<span class=\"token punctuation\">.<\/span>info<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;done, saved&#061;%s, db&#061;%s, csv&#061;%s&#034;<\/span><span class=\"token punctuation\">,<\/span> total_saved<span class=\"token punctuation\">,<\/span> DB_PATH<span class=\"token punctuation\">,<\/span> CSV_PATH<span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\\\\n\u91c7\u96c6\u7ed3\u679c\u9884\u89c8&#xff1a;&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        rows <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>storage<span class=\"token punctuation\">.<\/span>preview<span class=\"token punctuation\">(<\/span><span class=\"token number\">5<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">for<\/span> row <span class=\"token keyword\">in<\/span> rows<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">(<\/span>row<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        self<span class=\"token punctuation\">.<\/span>storage<span class=\"token punctuation\">.<\/span>close<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">crawl_issue_pages<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> first_page_url<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        current_url <span class=\"token operator\">&#061;<\/span> first_page_url<br \/>\n        visited_pages <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">set<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        saved_count <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">0<\/span><\/p>\n<p>        <span class=\"token keyword\">while<\/span> current_url<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> current_url <span class=\"token keyword\">in<\/span> visited_pages<span class=\"token punctuation\">:<\/span><br \/>\n                logging<span class=\"token punctuation\">.<\/span>warning<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;page already visited, break loop: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> current_url<span class=\"token punctuation\">)<\/span><br \/>\n                <span class=\"token keyword\">break<\/span><\/p>\n<p>            visited_pages<span class=\"token punctuation\">.<\/span>add<span class=\"token punctuation\">(<\/span>current_url<span class=\"token punctuation\">)<\/span><\/p>\n<p>            logging<span class=\"token punctuation\">.<\/span>info<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;fetch issue list page: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> current_url<span class=\"token punctuation\">)<\/span><br \/>\n            html <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>fetcher<span class=\"token punctuation\">.<\/span>fetch<span class=\"token punctuation\">(<\/span>current_url<span class=\"token punctuation\">)<\/span><br \/>\n            parsed <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>parser<span class=\"token punctuation\">.<\/span>parse_issue_list<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">,<\/span> current_url<span class=\"token punctuation\">)<\/span><\/p>\n<p>            page_context <span class=\"token operator\">&#061;<\/span> parsed<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;page_context&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">{<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            items <span class=\"token operator\">&#061;<\/span> parsed<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;items&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            next_url <span class=\"token operator\">&#061;<\/span> parsed<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;next_url&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>            logging<span class=\"token punctuation\">.<\/span>info<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;items found: %s next&#061;%s&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>items<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span> next_url<span class=\"token punctuation\">)<\/span><\/p>\n<p>            <span class=\"token keyword\">for<\/span> item <span class=\"token keyword\">in<\/span> items<span class=\"token punctuation\">:<\/span><br \/>\n                detail_url <span class=\"token operator\">&#061;<\/span> item<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;url&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n                <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> detail_url<span class=\"token punctuation\">:<\/span><br \/>\n                    <span class=\"token keyword\">continue<\/span><\/p>\n<p>                logging<span class=\"token punctuation\">.<\/span>info<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;fetch detail: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> detail_url<span class=\"token punctuation\">)<\/span><br \/>\n                detail_html <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>fetcher<span class=\"token punctuation\">.<\/span>fetch<span class=\"token punctuation\">(<\/span>detail_url<span class=\"token punctuation\">,<\/span> referer<span class=\"token operator\">&#061;<\/span>current_url<span class=\"token punctuation\">)<\/span><br \/>\n                detail_data <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>parser<span class=\"token punctuation\">.<\/span>parse_detail<span class=\"token punctuation\">(<\/span>detail_html<span class=\"token punctuation\">,<\/span> detail_url<span class=\"token punctuation\">)<\/span><\/p>\n<p>                fallback <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><span class=\"token punctuation\">}<\/span><br \/>\n                fallback<span class=\"token punctuation\">.<\/span>update<span class=\"token punctuation\">(<\/span>page_context<span class=\"token punctuation\">)<\/span><br \/>\n                fallback<span class=\"token punctuation\">.<\/span>update<span class=\"token punctuation\">(<\/span>item<span class=\"token punctuation\">)<\/span><\/p>\n<p>                record <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>cleaner<span class=\"token punctuation\">.<\/span>clean_record<span class=\"token punctuation\">(<\/span>detail_data<span class=\"token punctuation\">,<\/span> fallback<span class=\"token punctuation\">)<\/span><br \/>\n                <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> record<span class=\"token punctuation\">:<\/span><br \/>\n                    logging<span class=\"token punctuation\">.<\/span>warning<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;record cleaned empty: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> detail_url<span class=\"token punctuation\">)<\/span><br \/>\n                    <span class=\"token keyword\">continue<\/span><\/p>\n<p>                self<span class=\"token punctuation\">.<\/span>storage<span class=\"token punctuation\">.<\/span>upsert<span class=\"token punctuation\">(<\/span>record<span class=\"token punctuation\">)<\/span><br \/>\n                saved_count <span class=\"token operator\">&#043;&#061;<\/span> <span class=\"token number\">1<\/span><\/p>\n<p>            current_url <span class=\"token operator\">&#061;<\/span> next_url<\/p>\n<p>        <span class=\"token keyword\">return<\/span> saved_count<\/p>\n<p>    <span class=\"token decorator annotation punctuation\">&#064;staticmethod<\/span><br \/>\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">build_calendar_url<\/span><span class=\"token punctuation\">(<\/span>year<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">,<\/span> month<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> <span class=\"token string-interpolation\"><span class=\"token string\">f&#034;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>BASE_URL<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">\/archive\/<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>year<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">\/<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>month<span class=\"token punctuation\">:<\/span><span class=\"token format-spec\">02d<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">\/calendar.html&#034;<\/span><\/span><\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">main<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    ensure_dirs<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    write_fixture_files<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    crawler <span class=\"token operator\">&#061;<\/span> NewspaperIssueCrawler<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    crawler<span class=\"token punctuation\">.<\/span>run<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">if<\/span> __name__ <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token string\">&#034;__main__&#034;<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    main<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<h4>9.1 \u8fd0\u884c\u7ed3\u679c<\/h4>\n<p>\u8fd0\u884c&#xff1a;<\/p>\n<p>python main.py<\/p>\n<p>\u4f60\u4f1a\u770b\u5230\u7c7b\u4f3c\u8f93\u51fa&#xff1a;<\/p>\n<p>2026-06-17 10:00:01 | INFO | fetch calendar: https:\/\/example.com\/archive\/2024\/05\/calendar.html<br \/>\n2026-06-17 10:00:02 | INFO | calendar parsed issue entries: 2<br \/>\n2026-06-17 10:00:03 | INFO | fetch issue list page: https:\/\/example.com\/archive\/2024\/05\/01\/page\/1.html<br \/>\n2026-06-17 10:00:04 | INFO | items found: 2 next&#061;https:\/\/example.com\/archive\/2024\/05\/01\/page\/2.html<br \/>\n&#8230;<\/p>\n<p>\u8f93\u51fa\u6587\u4ef6&#xff1a;<\/p>\n<p>data\/newspaper_issues.db<br \/>\ndata\/newspaper_issues.csv<\/p>\n<p>CSV \u793a\u4f8b&#xff1a;<\/p>\n<table>\n<tr>\u62a5\u520a\u540d\u671f\u53f7\u51fa\u7248\u65e5\u671f\u680f\u76ee\u4e3b\u9898\u6570\u5b57\u5316\u72b6\u6001\u94fe\u63a5<\/tr>\n<tbody>\n<tr>\n<td>\u793a\u4f8b\u65e5\u62a5<\/td>\n<td>2024\u5e74\u7b2c05\u671f<\/td>\n<td>2024-05-01<\/td>\n<td>\u7efc\u5408\u65b0\u95fb<\/td>\n<td>\u57ce\u5e02\u5efa\u8bbe\u4e13\u9898<\/td>\n<td>\u5df2\u6570\u5b57\u5316<\/td>\n<td>https:\/\/example.com\/detail\/001.html<\/td>\n<\/tr>\n<tr>\n<td>\u793a\u4f8b\u65e5\u62a5<\/td>\n<td>2024\u5e74\u7b2c05\u671f<\/td>\n<td>2024-05-01<\/td>\n<td>\u6587\u5316\u526f\u520a<\/td>\n<td>\u8001\u7167\u7247\u91cc\u7684\u8857\u533a\u8bb0\u5fc6<\/td>\n<td>\u4ec5\u76ee\u5f55<\/td>\n<td>https:\/\/example.com\/detail\/002.html<\/td>\n<\/tr>\n<tr>\n<td>\u793a\u4f8b\u65e5\u62a5<\/td>\n<td>2024\u5e74\u7b2c05\u671f<\/td>\n<td>2024-05-01<\/td>\n<td>\u8d44\u6599\u7d22\u5f15<\/td>\n<td>\u5386\u53f2\u7248\u9762\u6570\u5b57\u5316\u8bf4\u660e<\/td>\n<td>\u5f85\u6570\u5b57\u5316<\/td>\n<td>https:\/\/example.com\/detail\/003.html<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<hr \/>\n<h3>10. \u771f\u5b9e\u7ad9\u70b9\u6539\u9020\u65b9\u6cd5<\/h3>\n<p>\u4e0a\u9762\u7684\u4ee3\u7801\u9ed8\u8ba4\u4f7f\u7528\u672c\u5730\u6837\u4f8b\u9875\u9762\u3002\u5982\u679c\u8981\u6539\u6210\u771f\u5b9e\u7ad9\u70b9&#xff0c;\u9700\u8981\u505a\u51e0\u5904\u8c03\u6574\u3002<\/p>\n<h4>10.1 \u5173\u95ed\u6837\u4f8b\u6a21\u5f0f<\/h4>\n<p>USE_FIXTURE <span class=\"token operator\">&#061;<\/span> <span class=\"token boolean\">False<\/span><br \/>\nBASE_URL <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;https:\/\/\u76ee\u6807\u7ad9\u70b9\u57df\u540d&#034;<\/span><\/p>\n<h4>10.2 \u4fee\u6539\u65e5\u5386 URL \u89c4\u5219<\/h4>\n<p>\u793a\u4f8b\u4ee3\u7801&#xff1a;<\/p>\n<p><span class=\"token decorator annotation punctuation\">&#064;staticmethod<\/span><br \/>\n<span class=\"token keyword\">def<\/span> <span class=\"token function\">build_calendar_url<\/span><span class=\"token punctuation\">(<\/span>year<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">,<\/span> month<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">return<\/span> <span class=\"token string-interpolation\"><span class=\"token string\">f&#034;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>BASE_URL<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">\/archive\/<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>year<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">\/<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>month<span class=\"token punctuation\">:<\/span><span class=\"token format-spec\">02d<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">\/calendar.html&#034;<\/span><\/span><\/p>\n<p>\u771f\u5b9e\u7ad9\u70b9\u53ef\u80fd\u662f&#xff1a;<\/p>\n<p><span class=\"token keyword\">return<\/span> <span class=\"token string-interpolation\"><span class=\"token string\">f&#034;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>BASE_URL<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">\/paper\/history?year&#061;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>year<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&amp;month&#061;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>month<span class=\"token punctuation\">:<\/span><span class=\"token format-spec\">02d<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><\/p>\n<p>\u4e5f\u53ef\u80fd\u662f&#xff1a;<\/p>\n<p><span class=\"token keyword\">return<\/span> <span class=\"token string-interpolation\"><span class=\"token string\">f&#034;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>BASE_URL<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">\/index.php?m&#061;archive&amp;y&#061;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>year<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&amp;mth&#061;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>month<span class=\"token punctuation\">:<\/span><span class=\"token format-spec\">02d<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><\/p>\n<p>\u4e0d\u8981\u731c\u3002\u7528\u6d4f\u89c8\u5668\u6253\u5f00\u76ee\u6807\u7ad9\u70b9&#xff0c;\u5207\u6362\u5e74\u6708&#xff0c;\u770b\u5730\u5740\u680f\u548c Network \u9762\u677f\u3002<\/p>\n<h4>10.3 \u4fee\u6539 CSS \u9009\u62e9\u5668<\/h4>\n<p>\u793a\u4f8b\u65e5\u5386\u9009\u62e9\u5668&#xff1a;<\/p>\n<p>soup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;a.issue-day&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u771f\u5b9e\u7ad9\u70b9\u53ef\u80fd\u662f&#xff1a;<\/p>\n<p>soup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.calendar a&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\nsoup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;td.has-paper a&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\nsoup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;div.date-list a&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u5217\u8868\u9875\u8be6\u60c5\u94fe\u63a5\u53ef\u80fd\u662f&#xff1a;<\/p>\n<p>soup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.issue-list .issue-item a.detail-link&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u771f\u5b9e\u7ad9\u70b9\u53ef\u80fd\u662f&#xff1a;<\/p>\n<p>soup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;ul.news-list li a&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\nsoup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;table.archive-table tr td.title a&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\nsoup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.list-con h3 a&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u8be6\u60c5\u9875\u5b57\u6bb5\u4e5f\u8981\u6309\u771f\u5b9e\u9875\u9762\u6539&#xff1a;<\/p>\n<p>soup<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;h1.topic&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\nsoup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;ul.meta li&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u91cd\u70b9\u4e0d\u662f\u8bb0\u4f4f\u67d0\u4e2a\u9009\u62e9\u5668&#xff0c;\u800c\u662f\u628a\u5b57\u6bb5\u62bd\u53d6\u903b\u8f91\u5199\u5728 Parser \u91cc&#xff0c;\u540e\u7eed\u53ea\u6539 Parser&#xff0c;\u4e0d\u52a8 Fetcher \u548c Storage\u3002<\/p>\n<hr \/>\n<h3>11. \u5e74\u6708\u671f\u53f7\u7ea7\u8054\u89e3\u6790<\/h3>\n<p>\u62a5\u520a\u5386\u53f2\u5e73\u53f0\u6700\u5bb9\u6613\u8e29\u5751\u7684\u5730\u65b9\u5c31\u662f\u5c42\u7ea7\u3002\u5f88\u591a\u521d\u5b66\u8005\u4f1a\u76f4\u63a5\u4ece\u9996\u9875\u5f00\u59cb\u627e\u6240\u6709\u94fe\u63a5&#xff0c;\u7136\u540e\u4e00\u5c42\u4e00\u5c42\u722c\u3002\u8fd9\u79cd\u65b9\u5f0f\u770b\u4f3c\u7b80\u5355&#xff0c;\u5b9e\u9645\u5f88\u5bb9\u6613\u5931\u63a7\u3002<\/p>\n<p>\u66f4\u597d\u7684\u65b9\u5f0f\u662f\u663e\u5f0f\u5efa\u7acb\u5c42\u7ea7\u3002<\/p>\n<h4>11.1 \u5e74\u4efd\u5c42<\/h4>\n<p>\u5e74\u4efd\u5c42\u8d1f\u8d23\u786e\u5b9a\u91c7\u96c6\u8303\u56f4\u3002<\/p>\n<p>years <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">range<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">2020<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">2025<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u771f\u5b9e\u9879\u76ee\u4e2d&#xff0c;\u6211\u4f1a\u628a\u5e74\u4efd\u5199\u8fdb\u914d\u7f6e\u6587\u4ef6&#xff1a;<\/p>\n<p>CRAWL_YEARS <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token number\">2021<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">2022<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">2023<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">2024<\/span><span class=\"token punctuation\">]<\/span><\/p>\n<p>\u5982\u679c\u7ad9\u70b9\u6709\u5e74\u4efd\u5217\u8868\u9875&#xff0c;\u53ef\u4ee5\u89e3\u6790\u5b83&#xff1a;<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">parse_years<\/span><span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> List<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">int<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    soup <span class=\"token operator\">&#061;<\/span> BeautifulSoup<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;lxml&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    years <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n    <span class=\"token keyword\">for<\/span> a <span class=\"token keyword\">in<\/span> soup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.year-list a&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        text <span class=\"token operator\">&#061;<\/span> a<span class=\"token punctuation\">.<\/span>get_text<span class=\"token punctuation\">(<\/span>strip<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">match<\/span> <span class=\"token operator\">&#061;<\/span> re<span class=\"token punctuation\">.<\/span>search<span class=\"token punctuation\">(<\/span><span class=\"token string\">r&#034;(19|20)\\\\d{2}&#034;<\/span><span class=\"token punctuation\">,<\/span> text<span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">match<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            years<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span><span class=\"token builtin\">int<\/span><span class=\"token punctuation\">(<\/span><span class=\"token keyword\">match<\/span><span class=\"token punctuation\">.<\/span>group<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">return<\/span> <span class=\"token builtin\">sorted<\/span><span class=\"token punctuation\">(<\/span><span class=\"token builtin\">set<\/span><span class=\"token punctuation\">(<\/span>years<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<h4>11.2 \u6708\u4efd\u5c42<\/h4>\n<p>\u6708\u4efd\u901a\u5e38\u662f 1 \u5230 12&#xff0c;\u4f46\u4e0d\u662f\u6bcf\u4e2a\u6708\u90fd\u6709\u5185\u5bb9\u3002\u53ef\u4ee5\u5148\u6784\u9020&#xff0c;\u518d\u8bf7\u6c42&#xff1a;<\/p>\n<p><span class=\"token keyword\">for<\/span> year <span class=\"token keyword\">in<\/span> years<span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">for<\/span> month <span class=\"token keyword\">in<\/span> <span class=\"token builtin\">range<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">13<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        url <span class=\"token operator\">&#061;<\/span> build_calendar_url<span class=\"token punctuation\">(<\/span>year<span class=\"token punctuation\">,<\/span> month<span class=\"token punctuation\">)<\/span><\/p>\n<p>\u4e5f\u53ef\u4ee5\u4ece\u9875\u9762\u89e3\u6790\u53ef\u7528\u6708\u4efd&#xff1a;<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">parse_months<\/span><span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> List<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">int<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    soup <span class=\"token operator\">&#061;<\/span> BeautifulSoup<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;lxml&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    months <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n    <span class=\"token keyword\">for<\/span> a <span class=\"token keyword\">in<\/span> soup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.month-list a&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        text <span class=\"token operator\">&#061;<\/span> a<span class=\"token punctuation\">.<\/span>get_text<span class=\"token punctuation\">(<\/span>strip<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">match<\/span> <span class=\"token operator\">&#061;<\/span> re<span class=\"token punctuation\">.<\/span>search<span class=\"token punctuation\">(<\/span><span class=\"token string\">r&#034;(\\\\d{1,2})\u6708&#034;<\/span><span class=\"token punctuation\">,<\/span> text<span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">match<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            months<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span><span class=\"token builtin\">int<\/span><span class=\"token punctuation\">(<\/span><span class=\"token keyword\">match<\/span><span class=\"token punctuation\">.<\/span>group<span class=\"token punctuation\">(<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">return<\/span> <span class=\"token builtin\">sorted<\/span><span class=\"token punctuation\">(<\/span><span class=\"token builtin\">set<\/span><span class=\"token punctuation\">(<\/span>months<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<h4>11.3 \u65e5\u671f\u5c42<\/h4>\n<p>\u62a5\u520a\u4e0d\u4e00\u5b9a\u6bcf\u5929\u51fa\u7248\u3002\u65e5\u62a5\u901a\u5e38\u65e5\u671f\u591a&#xff0c;\u5468\u62a5\u3001\u6708\u520a\u3001\u4e13\u520a\u5219\u65e5\u671f\u5c11\u3002\u65e5\u5386\u9875\u7684\u4ef7\u503c\u5c31\u5728\u8fd9\u91cc&#xff1a;\u5b83\u544a\u8bc9\u6211\u4eec\u54ea\u4e9b\u65e5\u671f\u6709\u671f\u53f7\u3002<\/p>\n<p>\u793a\u4f8b&#xff1a;<\/p>\n<p><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>a<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>issue-day<span class=\"token punctuation\">&#034;<\/span><\/span> <span class=\"token attr-name\">data-date<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>2024-05-01<span class=\"token punctuation\">&#034;<\/span><\/span> <span class=\"token attr-name\">href<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>\/archive\/2024\/05\/01\/page\/1.html<span class=\"token punctuation\">&#034;<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>1<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>a<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><br \/>\n<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>a<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>issue-day<span class=\"token punctuation\">&#034;<\/span><\/span> <span class=\"token attr-name\">data-date<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>2024-05-08<span class=\"token punctuation\">&#034;<\/span><\/span> <span class=\"token attr-name\">href<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>\/archive\/2024\/05\/08\/page\/1.html<span class=\"token punctuation\">&#034;<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>8<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>a<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><\/p>\n<p>\u89e3\u6790&#xff1a;<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">parse_issue_days<\/span><span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> List<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    soup <span class=\"token operator\">&#061;<\/span> BeautifulSoup<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;lxml&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    result <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n    <span class=\"token keyword\">for<\/span> a <span class=\"token keyword\">in<\/span> soup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;a.issue-day&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        href <span class=\"token operator\">&#061;<\/span> a<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;href&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        date <span class=\"token operator\">&#061;<\/span> a<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;data-date&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> href<span class=\"token punctuation\">:<\/span><br \/>\n            result<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">{<\/span><br \/>\n                <span class=\"token string\">&#034;date&#034;<\/span><span class=\"token punctuation\">:<\/span> date<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;url&#034;<\/span><span class=\"token punctuation\">:<\/span> urljoin<span class=\"token punctuation\">(<\/span>BASE_URL<span class=\"token punctuation\">,<\/span> href<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">return<\/span> result<\/p>\n<h4>11.4 \u671f\u53f7\u5c42<\/h4>\n<p>\u6709\u4e9b\u5e73\u53f0\u7684\u67d0\u4e00\u5929\u53ea\u6709\u4e00\u671f&#xff0c;\u6709\u4e9b\u5e73\u53f0\u67d0\u4e00\u5929\u53ef\u80fd\u6709\u591a\u4e2a\u7248\u9762\u6216\u589e\u520a\u3002\u671f\u53f7\u5c42\u6700\u597d\u4e0d\u8981\u5199\u6b7b\u3002<\/p>\n<p>\u53ef\u4ee5\u4ece\u9875\u9762\u4e2d\u63d0\u53d6&#xff1a;<\/p>\n<p>issue_no <span class=\"token operator\">&#061;<\/span> soup<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.issue-no&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>get_text<span class=\"token punctuation\">(<\/span>strip<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u4e5f\u53ef\u4ee5\u4ece\u6807\u9898\u4e2d\u63d0\u53d6&#xff1a;<\/p>\n<p>title <span class=\"token operator\">&#061;<\/span> soup<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;title&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>get_text<span class=\"token punctuation\">(<\/span>strip<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">match<\/span> <span class=\"token operator\">&#061;<\/span> re<span class=\"token punctuation\">.<\/span>search<span class=\"token punctuation\">(<\/span><span class=\"token string\">r&#034;(\\\\d{4}\u5e74\u7b2c\\\\d&#043;\u671f|\u603b\u7b2c\\\\d&#043;\u671f)&#034;<\/span><span class=\"token punctuation\">,<\/span> title<span class=\"token punctuation\">)<\/span><\/p>\n<h4>11.5 \u5206\u9875\u5c42<\/h4>\n<p>\u5386\u53f2\u5206\u9875\u4e00\u822c\u6709\u51e0\u79cd\u5f62\u5f0f\u3002<\/p>\n<p>\u7b2c\u4e00\u79cd&#xff1a;\u4e0b\u4e00\u9875\u6309\u94ae\u3002<\/p>\n<p><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>a<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>next<span class=\"token punctuation\">&#034;<\/span><\/span> <span class=\"token attr-name\">href<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>\/archive\/2024\/05\/01\/page\/2.html<span class=\"token punctuation\">&#034;<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u4e0b\u4e00\u9875<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>a<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><\/p>\n<p>\u7b2c\u4e8c\u79cd&#xff1a;\u9875\u7801\u5217\u8868\u3002<\/p>\n<p><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>a<\/span> <span class=\"token attr-name\">href<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>?page&#061;1<span class=\"token punctuation\">&#034;<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>1<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>a<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><br \/>\n<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>a<\/span> <span class=\"token attr-name\">href<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>?page&#061;2<span class=\"token punctuation\">&#034;<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>2<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>a<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><br \/>\n<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>a<\/span> <span class=\"token attr-name\">href<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>?page&#061;3<span class=\"token punctuation\">&#034;<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>3<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>a<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><\/p>\n<p>\u7b2c\u4e09\u79cd&#xff1a;\u63a5\u53e3\u5206\u9875\u3002<\/p>\n<p>\/api\/archive?year&#061;2024&amp;month&#061;05&amp;page&#061;1<br \/>\n\/api\/archive?year&#061;2024&amp;month&#061;05&amp;page&#061;2<\/p>\n<p>\u793a\u4f8b\u4ee3\u7801\u4e2d\u91c7\u7528\u201c\u4e0b\u4e00\u9875\u6309\u94ae\u201d\u65b9\u5f0f\u3002\u4f18\u70b9\u662f\u4e0d\u7528\u63d0\u524d\u77e5\u9053\u603b\u9875\u6570&#xff0c;\u89e3\u6790\u5230\u6ca1\u6709\u4e0b\u4e00\u9875\u4e3a\u6b62\u3002<\/p>\n<p><span class=\"token keyword\">while<\/span> current_url<span class=\"token punctuation\">:<\/span><br \/>\n    html <span class=\"token operator\">&#061;<\/span> fetcher<span class=\"token punctuation\">.<\/span>fetch<span class=\"token punctuation\">(<\/span>current_url<span class=\"token punctuation\">)<\/span><br \/>\n    parsed <span class=\"token operator\">&#061;<\/span> parser<span class=\"token punctuation\">.<\/span>parse_issue_list<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">,<\/span> current_url<span class=\"token punctuation\">)<\/span><br \/>\n    current_url <span class=\"token operator\">&#061;<\/span> parsed<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;next_url&#034;<\/span><span class=\"token punctuation\">]<\/span><\/p>\n<p>\u4e3a\u4e86\u907f\u514d\u6b7b\u5faa\u73af&#xff0c;\u9700\u8981\u52a0\u8bbf\u95ee\u96c6\u5408&#xff1a;<\/p>\n<p>visited_pages <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">set<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">if<\/span> current_url <span class=\"token keyword\">in<\/span> visited_pages<span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">break<\/span><\/p>\n<p>visited_pages<span class=\"token punctuation\">.<\/span>add<span class=\"token punctuation\">(<\/span>current_url<span class=\"token punctuation\">)<\/span><\/p>\n<p>\u8fd9\u70b9\u5f88\u91cd\u8981\u3002\u6709\u4e9b\u8001\u7ad9\u70b9\u7684\u201c\u4e0b\u4e00\u9875\u201d\u4f1a\u9519\u8bef\u5730\u6307\u5411\u5f53\u524d\u9875&#xff0c;\u5982\u679c\u6ca1\u6709\u9632\u62a4&#xff0c;\u7a0b\u5e8f\u4f1a\u4e00\u76f4\u8dd1\u3002<\/p>\n<hr \/>\n<h3>12. \u52a8\u6001\u65e5\u5386\u89e3\u6790<\/h3>\n<h4>12.1 \u4ec0\u4e48\u662f\u52a8\u6001\u65e5\u5386<\/h4>\n<p>\u52a8\u6001\u65e5\u5386\u901a\u5e38\u4e0d\u662f\u76f4\u63a5\u5199\u5728 HTML \u4e2d&#xff0c;\u800c\u662f\u7531 JavaScript \u8bf7\u6c42\u63a5\u53e3\u540e\u6e32\u67d3\u3002\u4f8b\u5982\u9875\u9762\u6e90\u4ee3\u7801\u91cc\u53ea\u6709&#xff1a;<\/p>\n<p><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>div<\/span> <span class=\"token attr-name\">id<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>calendar<span class=\"token punctuation\">&#034;<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>div<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><br \/>\n<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>script<\/span> <span class=\"token attr-name\">src<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>\/static\/calendar.js<span class=\"token punctuation\">&#034;<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span><span class=\"token script\"><\/span><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>script<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><\/p>\n<p>\u6d4f\u89c8\u5668\u5b9e\u9645\u770b\u5230\u7684\u65e5\u671f&#xff0c;\u662f JS \u8fd0\u884c\u540e\u751f\u6210\u7684\u3002<\/p>\n<p>\u9047\u5230\u8fd9\u79cd\u60c5\u51b5&#xff0c;\u4e0d\u8981\u6025\u7740\u4e0a Playwright\u3002\u5148\u6253\u5f00\u6d4f\u89c8\u5668\u5f00\u53d1\u8005\u5de5\u5177&#xff0c;\u5207\u5230 Network \u9762\u677f&#xff0c;\u770b\u6709\u6ca1\u6709\u7c7b\u4f3c\u63a5\u53e3&#xff1a;<\/p>\n<p>\/api\/calendar?year&#061;2024&amp;month&#061;05<br \/>\n\/api\/issues\/dates?y&#061;2024&amp;m&#061;05<br \/>\n\/archive\/calendar.json?year&#061;2024&amp;month&#061;05<\/p>\n<p>\u5982\u679c\u80fd\u627e\u5230\u63a5\u53e3&#xff0c;\u4f18\u5148\u8bf7\u6c42\u63a5\u53e3&#xff0c;\u56e0\u4e3a\u5b83\u66f4\u8f7b\u3001\u66f4\u7a33\u5b9a\u3002<\/p>\n<h4>12.2 JSON \u65e5\u5386\u89e3\u6790\u793a\u4f8b<\/h4>\n<p>\u5047\u8bbe\u63a5\u53e3\u8fd4\u56de&#xff1a;<\/p>\n<p><span class=\"token punctuation\">{<\/span><br \/>\n  <span class=\"token string-property property\">&#034;year&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">2024<\/span><span class=\"token punctuation\">,<\/span><br \/>\n  <span class=\"token string-property property\">&#034;month&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">5<\/span><span class=\"token punctuation\">,<\/span><br \/>\n  <span class=\"token string-property property\">&#034;days&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">[<\/span><br \/>\n    <span class=\"token punctuation\">{<\/span><br \/>\n      <span class=\"token string-property property\">&#034;date&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;2024-05-01&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n      <span class=\"token string-property property\">&#034;url&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;\/archive\/2024\/05\/01\/page\/1.html&#034;<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token punctuation\">{<\/span><br \/>\n      <span class=\"token string-property property\">&#034;date&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;2024-05-08&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n      <span class=\"token string-property property\">&#034;url&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;\/archive\/2024\/05\/08\/page\/1.html&#034;<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><br \/>\n  <span class=\"token punctuation\">]<\/span><br \/>\n<span class=\"token punctuation\">}<\/span><\/p>\n<p>\u53ef\u4ee5\u8fd9\u6837\u89e3\u6790&#xff1a;<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">parse_calendar_json<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> List<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    urls <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n    <span class=\"token keyword\">for<\/span> item <span class=\"token keyword\">in<\/span> data<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;days&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        url <span class=\"token operator\">&#061;<\/span> item<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;url&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> url<span class=\"token punctuation\">:<\/span><br \/>\n            urls<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span>urljoin<span class=\"token punctuation\">(<\/span>BASE_URL<span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">return<\/span> urls<\/p>\n<p>\u8bf7\u6c42\u63a5\u53e3&#xff1a;<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">fetch_json<\/span><span class=\"token punctuation\">(<\/span>session<span class=\"token punctuation\">:<\/span> requests<span class=\"token punctuation\">.<\/span>Session<span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    response <span class=\"token operator\">&#061;<\/span> session<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">,<\/span> timeout<span class=\"token operator\">&#061;<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">5<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">20<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    response<span class=\"token punctuation\">.<\/span>raise_for_status<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">return<\/span> response<span class=\"token punctuation\">.<\/span>json<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<h4>12.3 \u53ea\u6709\u6e32\u67d3\u7ed3\u679c&#xff0c;\u6ca1\u6709\u63a5\u53e3\u600e\u4e48\u529e<\/h4>\n<p>\u5982\u679c\u9875\u9762\u662f\u7eaf\u524d\u7aef\u6e32\u67d3&#xff0c;\u63a5\u53e3\u53c8\u4e0d\u597d\u62c6&#xff0c;\u53ef\u4ee5\u8003\u8651 Playwright\u3002<\/p>\n<p>\u793a\u4f8b&#xff1a;<\/p>\n<p><span class=\"token keyword\">from<\/span> playwright<span class=\"token punctuation\">.<\/span>sync_api <span class=\"token keyword\">import<\/span> sync_playwright<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">render_html_with_playwright<\/span><span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> wait_selector<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;.issue-day&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">with<\/span> sync_playwright<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">as<\/span> p<span class=\"token punctuation\">:<\/span><br \/>\n        browser <span class=\"token operator\">&#061;<\/span> p<span class=\"token punctuation\">.<\/span>chromium<span class=\"token punctuation\">.<\/span>launch<span class=\"token punctuation\">(<\/span>headless<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        page <span class=\"token operator\">&#061;<\/span> browser<span class=\"token punctuation\">.<\/span>new_page<span class=\"token punctuation\">(<\/span><br \/>\n            user_agent<span class=\"token operator\">&#061;<\/span><span class=\"token punctuation\">(<\/span><br \/>\n                <span class=\"token string\">&#034;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) &#034;<\/span><br \/>\n                <span class=\"token string\">&#034;AppleWebKit\/537.36 (KHTML, like Gecko) &#034;<\/span><br \/>\n                <span class=\"token string\">&#034;Chrome\/124.0 Safari\/537.36&#034;<\/span><br \/>\n            <span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token punctuation\">)<\/span><br \/>\n        page<span class=\"token punctuation\">.<\/span>goto<span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">,<\/span> wait_until<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;networkidle&#034;<\/span><span class=\"token punctuation\">,<\/span> timeout<span class=\"token operator\">&#061;<\/span><span class=\"token number\">30000<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        page<span class=\"token punctuation\">.<\/span>wait_for_selector<span class=\"token punctuation\">(<\/span>wait_selector<span class=\"token punctuation\">,<\/span> timeout<span class=\"token operator\">&#061;<\/span><span class=\"token number\">10000<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        html <span class=\"token operator\">&#061;<\/span> page<span class=\"token punctuation\">.<\/span>content<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        browser<span class=\"token punctuation\">.<\/span>close<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> html<\/p>\n<p>\u4f46 Playwright \u4e0d\u5e94\u8be5\u88ab\u6ee5\u7528\u3002\u5b83\u542f\u52a8\u6d4f\u89c8\u5668&#xff0c;\u8d44\u6e90\u6d88\u8017\u6bd4 requests \u9ad8\u5f88\u591a\u3002\u5982\u679c\u63a5\u53e3\u80fd\u89e3\u51b3\u95ee\u9898&#xff0c;\u5c3d\u91cf\u4e0d\u8981\u7528\u6d4f\u89c8\u5668\u6e32\u67d3\u3002<\/p>\n<hr \/>\n<h3>13. \u5386\u53f2\u5206\u9875\u89e3\u6790\u7ec6\u8282<\/h3>\n<h4>13.1 \u4ece\u7b2c\u4e00\u9875\u987a\u7740\u4e0b\u4e00\u9875\u8d70<\/h4>\n<p>\u8fd9\u79cd\u65b9\u5f0f\u6700\u7a33\u3002<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">crawl_by_next<\/span><span class=\"token punctuation\">(<\/span>first_url<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    current_url <span class=\"token operator\">&#061;<\/span> first_url<br \/>\n    visited <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">set<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">while<\/span> current_url<span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> current_url <span class=\"token keyword\">in<\/span> visited<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">break<\/span><\/p>\n<p>        visited<span class=\"token punctuation\">.<\/span>add<span class=\"token punctuation\">(<\/span>current_url<span class=\"token punctuation\">)<\/span><br \/>\n        html <span class=\"token operator\">&#061;<\/span> fetcher<span class=\"token punctuation\">.<\/span>fetch<span class=\"token punctuation\">(<\/span>current_url<span class=\"token punctuation\">)<\/span><br \/>\n        parsed <span class=\"token operator\">&#061;<\/span> parser<span class=\"token punctuation\">.<\/span>parse_issue_list<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">,<\/span> current_url<span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">for<\/span> item <span class=\"token keyword\">in<\/span> parsed<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;items&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">yield<\/span> item<\/p>\n<p>        current_url <span class=\"token operator\">&#061;<\/span> parsed<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;next_url&#034;<\/span><span class=\"token punctuation\">]<\/span><\/p>\n<p>\u4f18\u70b9&#xff1a;<\/p>\n<p>\u4e0d\u9700\u8981\u77e5\u9053\u603b\u9875\u6570<br \/>\n\u9875\u9762\u7ed3\u6784\u7a0d\u5fae\u53d8\u5316\u4e5f\u80fd\u9002\u914d<br \/>\n\u4e0d\u4f1a\u8bf7\u6c42\u4e0d\u5b58\u5728\u7684 page&#061;999<\/p>\n<h4>13.2 \u6839\u636e\u603b\u9875\u6570\u6784\u9020 URL<\/h4>\n<p>\u5982\u679c\u9875\u9762\u63d0\u4f9b\u603b\u9875\u6570&#xff1a;<\/p>\n<p><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>span<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>total-page<span class=\"token punctuation\">&#034;<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u5171 12 \u9875<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>span<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><\/p>\n<p>\u53ef\u4ee5\u89e3\u6790\u540e\u6784\u9020&#xff1a;<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">parse_total_pages<\/span><span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    soup <span class=\"token operator\">&#061;<\/span> BeautifulSoup<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;lxml&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    text <span class=\"token operator\">&#061;<\/span> soup<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.total-page&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>get_text<span class=\"token punctuation\">(<\/span>strip<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">match<\/span> <span class=\"token operator\">&#061;<\/span> re<span class=\"token punctuation\">.<\/span>search<span class=\"token punctuation\">(<\/span><span class=\"token string\">r&#034;\u5171\\\\s*(\\\\d&#043;)\\\\s*\u9875&#034;<\/span><span class=\"token punctuation\">,<\/span> text<span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">return<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">(<\/span><span class=\"token keyword\">match<\/span><span class=\"token punctuation\">.<\/span>group<span class=\"token punctuation\">(<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">match<\/span> <span class=\"token keyword\">else<\/span> <span class=\"token number\">1<\/span><\/p>\n<p>\u7136\u540e&#xff1a;<\/p>\n<p><span class=\"token keyword\">for<\/span> page <span class=\"token keyword\">in<\/span> <span class=\"token builtin\">range<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span> total_pages <span class=\"token operator\">&#043;<\/span> <span class=\"token number\">1<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    url <span class=\"token operator\">&#061;<\/span> <span class=\"token string-interpolation\"><span class=\"token string\">f&#034;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>base_url<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">?page&#061;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>page<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><\/p>\n<p>\u8fd9\u79cd\u65b9\u5f0f\u901f\u5ea6\u7565\u5feb&#xff0c;\u4f46\u5bf9\u5206\u9875\u89c4\u5219\u4f9d\u8d56\u66f4\u5f3a\u3002<\/p>\n<h4>13.3 \u7a7a\u9875\u5904\u7406<\/h4>\n<p>\u8001\u7ad9\u70b9\u5e38\u89c1\u7a7a\u9875\u3002\u6bd4\u5982\u603b\u9875\u6570\u663e\u793a 10&#xff0c;\u4f46\u7b2c 10 \u9875\u6ca1\u6709\u6570\u636e\u3002\u5904\u7406\u65b9\u5f0f&#xff1a;<\/p>\n<p><span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> items<span class=\"token punctuation\">:<\/span><br \/>\n    logging<span class=\"token punctuation\">.<\/span>warning<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;empty list page: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> current_url<span class=\"token punctuation\">)<\/span><\/p>\n<p>\u5982\u679c\u8fde\u7eed\u591a\u4e2a\u7a7a\u9875&#xff0c;\u53ef\u4ee5\u505c\u6b62&#xff1a;<\/p>\n<p>empty_count <span class=\"token operator\">&#043;&#061;<\/span> <span class=\"token number\">1<\/span><br \/>\n<span class=\"token keyword\">if<\/span> empty_count <span class=\"token operator\">&gt;&#061;<\/span> <span class=\"token number\">3<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">break<\/span><\/p>\n<p>\u4f46\u5728\u672c\u6587\u8fd9\u79cd\u201c\u4e0b\u4e00\u9875\u6309\u94ae\u201d\u6a21\u5f0f\u4e0b&#xff0c;\u4e00\u822c\u4e0d\u9700\u8981\u8fde\u7eed\u7a7a\u9875\u5224\u65ad\u3002<\/p>\n<hr \/>\n<h3>14. \u6570\u636e\u6e05\u6d17\u7b56\u7565<\/h3>\n<h4>14.1 \u65e5\u671f\u6e05\u6d17<\/h4>\n<p>\u5386\u53f2\u62a5\u520a\u7ad9\u70b9\u7684\u65e5\u671f\u683c\u5f0f\u975e\u5e38\u6df7\u4e71&#xff1a;<\/p>\n<p>2024-05-01<br \/>\n2024\/05\/01<br \/>\n2024.05.01<br \/>\n2024\u5e745\u67081\u65e5<br \/>\n\u4e8c\u3007\u4e8c\u56db\u5e74\u4e94\u6708\u4e00\u65e5<\/p>\n<p>\u672c\u6587\u793a\u4f8b\u5904\u7406\u524d\u4e09\u7c7b\u548c\u5e38\u89c1\u4e2d\u6587\u5e74\u6708\u65e5&#xff1a;<\/p>\n<p>value <span class=\"token operator\">&#061;<\/span> value<span class=\"token punctuation\">.<\/span>replace<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u5e74&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;-&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>replace<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u6708&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;-&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>replace<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u65e5&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\ndt <span class=\"token operator\">&#061;<\/span> date_parser<span class=\"token punctuation\">.<\/span>parse<span class=\"token punctuation\">(<\/span>value<span class=\"token punctuation\">)<\/span><\/p>\n<p>\u5982\u679c\u9047\u5230\u4e2d\u6587\u6570\u5b57\u65e5\u671f&#xff0c;\u6bd4\u5982\u201c\u4e8c\u3007\u4e8c\u56db\u5e74\u4e94\u6708\u4e00\u65e5\u201d&#xff0c;\u53ef\u4ee5\u989d\u5916\u5199\u6620\u5c04\u51fd\u6570\u3002\u4f46\u6211\u5efa\u8bae\u5148\u770b\u76ee\u6807\u7ad9\u70b9\u662f\u5426\u771f\u7684\u51fa\u73b0\u8fd9\u79cd\u683c\u5f0f&#xff0c;\u4e0d\u8981\u63d0\u524d\u628a\u4ee3\u7801\u5199\u5f97\u8fc7\u5ea6\u590d\u6742\u3002<\/p>\n<h4>14.2 \u6570\u5b57\u5316\u72b6\u6001\u6e05\u6d17<\/h4>\n<p>\u6570\u5b57\u5316\u72b6\u6001\u53ef\u80fd\u6709\u5f88\u591a\u5199\u6cd5&#xff1a;<\/p>\n<p>\u5df2\u6570\u5b57\u5316<br \/>\n\u5df2\u5b8c\u6210\u6570\u5b57\u5316<br \/>\n\u672a\u6570\u5b57\u5316<br \/>\n\u5f85\u6570\u5b57\u5316<br \/>\n\u4ec5\u76ee\u5f55<br \/>\n\u76ee\u5f55\u5df2\u5f00\u653e<br \/>\n\u6682\u65e0\u5168\u6587<br \/>\n\u7f3a\u9875<\/p>\n<p>\u53ef\u4ee5\u5148\u5f52\u4e00\u6210\u51e0\u4e2a\u6838\u5fc3\u72b6\u6001&#xff1a;<\/p>\n<p>\u5df2\u6570\u5b57\u5316<br \/>\n\u672a\u6570\u5b57\u5316<br \/>\n\u5f85\u6570\u5b57\u5316<br \/>\n\u4ec5\u76ee\u5f55<br \/>\n\u672a\u77e5<\/p>\n<p>\u793a\u4f8b&#xff1a;<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">normalize_status<\/span><span class=\"token punctuation\">(<\/span>value<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">if<\/span> <span class=\"token string\">&#034;\u5df2&#034;<\/span> <span class=\"token keyword\">in<\/span> value <span class=\"token keyword\">and<\/span> <span class=\"token string\">&#034;\u6570\u5b57&#034;<\/span> <span class=\"token keyword\">in<\/span> value<span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;\u5df2\u6570\u5b57\u5316&#034;<\/span><br \/>\n    <span class=\"token keyword\">if<\/span> <span class=\"token string\">&#034;\u5f85&#034;<\/span> <span class=\"token keyword\">in<\/span> value <span class=\"token keyword\">and<\/span> <span class=\"token string\">&#034;\u6570\u5b57&#034;<\/span> <span class=\"token keyword\">in<\/span> value<span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;\u5f85\u6570\u5b57\u5316&#034;<\/span><br \/>\n    <span class=\"token keyword\">if<\/span> <span class=\"token string\">&#034;\u672a&#034;<\/span> <span class=\"token keyword\">in<\/span> value <span class=\"token keyword\">and<\/span> <span class=\"token string\">&#034;\u6570\u5b57&#034;<\/span> <span class=\"token keyword\">in<\/span> value<span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;\u672a\u6570\u5b57\u5316&#034;<\/span><br \/>\n    <span class=\"token keyword\">if<\/span> <span class=\"token string\">&#034;\u76ee\u5f55&#034;<\/span> <span class=\"token keyword\">in<\/span> value<span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;\u4ec5\u76ee\u5f55&#034;<\/span><br \/>\n    <span class=\"token keyword\">return<\/span> value <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#034;\u672a\u77e5&#034;<\/span><\/p>\n<p>\u540e\u7eed\u5982\u679c\u5206\u6790\u9700\u8981&#xff0c;\u518d\u7ec6\u5206\u72b6\u6001\u4e5f\u4e0d\u8fdf\u3002<\/p>\n<h4>14.3 URL \u8865\u5168<\/h4>\n<p>\u8be6\u60c5\u94fe\u63a5\u7ecf\u5e38\u662f\u76f8\u5bf9\u8def\u5f84&#xff1a;<\/p>\n<p><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>a<\/span> <span class=\"token attr-name\">href<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>\/detail\/001.html<span class=\"token punctuation\">&#034;<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u57ce\u5e02\u5efa\u8bbe\u4e13\u9898<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>a<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><\/p>\n<p>\u5fc5\u987b\u8865\u5168&#xff1a;<\/p>\n<p>urljoin<span class=\"token punctuation\">(<\/span>BASE_URL<span class=\"token punctuation\">,<\/span> href<span class=\"token punctuation\">)<\/span><\/p>\n<p>\u4e0d\u8981\u624b\u52a8\u5b57\u7b26\u4e32\u62fc\u63a5&#xff1a;<\/p>\n<p>BASE_URL <span class=\"token operator\">&#043;<\/span> href<\/p>\n<p>\u56e0\u4e3a\u9047\u5230 ..\/detail\/001.html \u6216 detail\/001.html \u65f6&#xff0c;\u624b\u52a8\u62fc\u63a5\u5f88\u5bb9\u6613\u51fa\u9519\u3002<\/p>\n<hr \/>\n<h3>15. \u8fd0\u884c\u65b9\u5f0f\u4e0e\u7ed3\u679c\u5c55\u793a<\/h3>\n<h4>15.1 \u542f\u52a8\u547d\u4ee4<\/h4>\n<p>\u5b89\u88c5\u4f9d\u8d56&#xff1a;<\/p>\n<p>pip <span class=\"token function\">install<\/span> requests beautifulsoup4 lxml pandas python-dateutil<\/p>\n<p>\u8fd0\u884c&#xff1a;<\/p>\n<p>python main.py<\/p>\n<h4>15.2 \u8f93\u51fa\u4f4d\u7f6e<\/h4>\n<p>SQLite \u6570\u636e\u5e93&#xff1a;<br \/>\ndata\/newspaper_issues.db<\/p>\n<p>CSV \u6587\u4ef6&#xff1a;<br \/>\ndata\/newspaper_issues.csv<\/p>\n<h4>15.3 \u67e5\u770b SQLite \u6570\u636e<\/h4>\n<p>\u53ef\u4ee5\u7528 DB Browser for SQLite \u6253\u5f00&#xff0c;\u4e5f\u53ef\u4ee5\u7528\u547d\u4ee4\u884c&#xff1a;<\/p>\n<p>sqlite3 data\/newspaper_issues.db<\/p>\n<p>\u8fdb\u5165\u540e\u6267\u884c&#xff1a;<\/p>\n<p><span class=\"token keyword\">SELECT<\/span> newspaper_name<span class=\"token punctuation\">,<\/span> issue_no<span class=\"token punctuation\">,<\/span> publish_date<span class=\"token punctuation\">,<\/span> column_name<span class=\"token punctuation\">,<\/span> topic<span class=\"token punctuation\">,<\/span> digitization_status<span class=\"token punctuation\">,<\/span> url<br \/>\n<span class=\"token keyword\">FROM<\/span> newspaper_issues<br \/>\n<span class=\"token keyword\">LIMIT<\/span> <span class=\"token number\">5<\/span><span class=\"token punctuation\">;<\/span><\/p>\n<h4>15.4 \u793a\u4f8b\u7ed3\u679c<\/h4>\n<p>\u62a5\u520a\u540d      \u671f\u53f7          \u51fa\u7248\u65e5\u671f      \u680f\u76ee      \u4e3b\u9898              \u6570\u5b57\u5316\u72b6\u6001<br \/>\n\u793a\u4f8b\u65e5\u62a5    2024\u5e74\u7b2c05\u671f  2024-05-01  \u7efc\u5408\u65b0\u95fb  \u57ce\u5e02\u5efa\u8bbe\u4e13\u9898        \u5df2\u6570\u5b57\u5316<br \/>\n\u793a\u4f8b\u65e5\u62a5    2024\u5e74\u7b2c05\u671f  2024-05-01  \u6587\u5316\u526f\u520a  \u8001\u7167\u7247\u91cc\u7684\u8857\u533a\u8bb0\u5fc6  \u4ec5\u76ee\u5f55<br \/>\n\u793a\u4f8b\u65e5\u62a5    2024\u5e74\u7b2c05\u671f  2024-05-01  \u8d44\u6599\u7d22\u5f15  \u5386\u53f2\u7248\u9762\u6570\u5b57\u5316\u8bf4\u660e  \u5f85\u6570\u5b57\u5316<\/p>\n<p>CSV \u6253\u5f00\u540e\u5b57\u6bb5\u66f4\u76f4\u89c2&#xff1a;<\/p>\n<p>\u62a5\u520a\u540d,\u671f\u53f7,\u51fa\u7248\u65e5\u671f,\u680f\u76ee,\u4e3b\u9898,\u6570\u5b57\u5316\u72b6\u6001,\u94fe\u63a5<br \/>\n\u793a\u4f8b\u65e5\u62a5,2024\u5e74\u7b2c05\u671f,2024-05-01,\u7efc\u5408\u65b0\u95fb,\u57ce\u5e02\u5efa\u8bbe\u4e13\u9898,\u5df2\u6570\u5b57\u5316,https:\/\/example.com\/detail\/001.html<br \/>\n\u793a\u4f8b\u65e5\u62a5,2024\u5e74\u7b2c05\u671f,2024-05-01,\u6587\u5316\u526f\u520a,\u8001\u7167\u7247\u91cc\u7684\u8857\u533a\u8bb0\u5fc6,\u4ec5\u76ee\u5f55,https:\/\/example.com\/detail\/002.html<br \/>\n\u793a\u4f8b\u65e5\u62a5,2024\u5e74\u7b2c05\u671f,2024-05-01,\u8d44\u6599\u7d22\u5f15,\u5386\u53f2\u7248\u9762\u6570\u5b57\u5316\u8bf4\u660e,\u5f85\u6570\u5b57\u5316,https:\/\/example.com\/detail\/003.html<\/p>\n<hr \/>\n<h3>16. \u5e38\u89c1\u95ee\u9898\u4e0e\u6392\u9519<\/h3>\n<h4>16.1 403 \u600e\u4e48\u529e<\/h4>\n<p>403 \u8868\u793a\u8bbf\u95ee\u88ab\u62d2\u7edd\u3002\u539f\u56e0\u53ef\u80fd\u5f88\u591a&#xff1a;<\/p>\n<p>\u7f3a\u5c11 User-Agent<br \/>\n\u7f3a\u5c11 Referer<br \/>\n\u8bf7\u6c42\u9891\u7387\u8fc7\u9ad8<br \/>\n\u8bbf\u95ee\u4e86\u4e0d\u5141\u8bb8\u6293\u53d6\u7684\u8def\u5f84<br \/>\n\u7ad9\u70b9\u6709\u8bbf\u95ee\u7b56\u7565<\/p>\n<p>\u5904\u7406\u5efa\u8bae&#xff1a;<\/p>\n<li>\u5148\u68c0\u67e5 URL \u662f\u5426\u80fd\u5728\u6d4f\u89c8\u5668\u4e2d\u76f4\u63a5\u6253\u5f00\u3002<\/li>\n<li>\u68c0\u67e5 robots.txt \u548c\u7ad9\u70b9\u8bf4\u660e\u3002<\/li>\n<li>\u589e\u52a0\u5e38\u89c4 headers\u3002<\/li>\n<li>\u964d\u4f4e\u8bf7\u6c42\u9891\u7387\u3002<\/li>\n<li>\u4e0d\u8981\u5c1d\u8bd5\u7ed5\u8fc7\u767b\u5f55\u6216\u4ed8\u8d39\u9650\u5236\u3002<\/li>\n<p>\u4ee3\u7801\u91cc\u53ef\u4ee5\u52a0\u65e5\u5fd7&#xff1a;<\/p>\n<p><span class=\"token keyword\">if<\/span> response<span class=\"token punctuation\">.<\/span>status_code <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token number\">403<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    logging<span class=\"token punctuation\">.<\/span>warning<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;403 forbidden, check access policy and headers: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">)<\/span><\/p>\n<h4>16.2 429 \u600e\u4e48\u529e<\/h4>\n<p>429 \u901a\u5e38\u8868\u793a\u8bf7\u6c42\u592a\u9891\u7e41\u3002\u5904\u7406\u65b9\u5f0f&#xff1a;<\/p>\n<p>\u964d\u4f4e\u9891\u7387<br \/>\n\u589e\u52a0\u968f\u673a sleep<br \/>\n\u51cf\u5c11\u5e76\u53d1<br \/>\n\u4f7f\u7528\u6307\u6570\u9000\u907f<br \/>\n\u5206\u6279\u91c7\u96c6<\/p>\n<p>\u793a\u4f8b&#xff1a;<\/p>\n<p><span class=\"token keyword\">if<\/span> response<span class=\"token punctuation\">.<\/span>status_code <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token number\">429<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    time<span class=\"token punctuation\">.<\/span>sleep<span class=\"token punctuation\">(<\/span><span class=\"token number\">30<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">continue<\/span><\/p>\n<p>\u6211\u4e2a\u4eba\u66f4\u559c\u6b22\u4fdd\u5b88\u4e00\u4e9b\u3002\u5386\u53f2\u7d22\u5f15\u4e0d\u662f\u5b9e\u65f6\u884c\u60c5&#xff0c;\u4e0d\u503c\u5f97\u4e3a\u4e86\u5feb\u51e0\u5206\u949f\u628a\u7ad9\u70b9\u6253\u51fa\u538b\u529b\u3002<\/p>\n<h4>16.3 HTML \u6293\u5230\u7a7a\u58f3\u600e\u4e48\u529e<\/h4>\n<p>\u5982\u679c requests \u6293\u5230\u7684 HTML \u91cc\u6ca1\u6709\u6570\u636e&#xff0c;\u6d4f\u89c8\u5668\u91cc\u5374\u80fd\u770b\u5230\u5185\u5bb9&#xff0c;\u901a\u5e38\u8bf4\u660e\u9875\u9762\u7531 JavaScript \u6e32\u67d3\u3002<\/p>\n<p>\u6392\u67e5\u6b65\u9aa4&#xff1a;<\/p>\n<li>\u53f3\u952e\u67e5\u770b\u7f51\u9875\u6e90\u4ee3\u7801&#xff0c;\u770b\u662f\u5426\u6709\u76ee\u6807\u5b57\u6bb5\u3002<\/li>\n<li>\u6253\u5f00\u5f00\u53d1\u8005\u5de5\u5177 Network\u3002<\/li>\n<li>\u5207\u6362\u5e74\u6708\u6216\u7ffb\u9875\u3002<\/li>\n<li>\u627e XHR \u6216 Fetch \u8bf7\u6c42\u3002<\/li>\n<li>\u4f18\u5148\u8bf7\u6c42\u63a5\u53e3\u3002<\/li>\n<li>\u627e\u4e0d\u5230\u63a5\u53e3\u518d\u8003\u8651 Playwright\u3002<\/li>\n<p>\u5178\u578b\u7a7a\u58f3&#xff1a;<\/p>\n<p><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>div<\/span> <span class=\"token attr-name\">id<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>app<span class=\"token punctuation\">&#034;<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>div<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><br \/>\n<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>script<\/span> <span class=\"token attr-name\">src<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">&#061;<\/span><span class=\"token punctuation\">&#034;<\/span>\/assets\/index.js<span class=\"token punctuation\">&#034;<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span><span class=\"token script\"><\/span><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>script<\/span><span class=\"token punctuation\">&gt;<\/span><\/span><\/p>\n<p>\u8fd9\u79cd\u9875\u9762\u7528 bs4 \u76f4\u63a5\u89e3\u6790\u901a\u5e38\u62ff\u4e0d\u5230\u6570\u636e\u3002<\/p>\n<h4>16.4 \u89e3\u6790\u62a5\u9519\u600e\u4e48\u529e<\/h4>\n<p>\u5e38\u89c1\u9519\u8bef&#xff1a;<\/p>\n<p>AttributeError: &#039;NoneType&#039; object has no attribute &#039;get_text&#039;<\/p>\n<p>\u539f\u56e0\u662f\u9009\u62e9\u5668\u6ca1\u5339\u914d\u5230\u8282\u70b9\u3002<\/p>\n<p>\u9519\u8bef\u5199\u6cd5&#xff1a;<\/p>\n<p>title <span class=\"token operator\">&#061;<\/span> soup<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;h1.topic&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>get_text<span class=\"token punctuation\">(<\/span>strip<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u7a33\u59a5\u5199\u6cd5&#xff1a;<\/p>\n<p>node <span class=\"token operator\">&#061;<\/span> soup<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;h1.topic&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\ntitle <span class=\"token operator\">&#061;<\/span> node<span class=\"token punctuation\">.<\/span>get_text<span class=\"token punctuation\">(<\/span>strip<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">if<\/span> node <span class=\"token keyword\">else<\/span> <span class=\"token string\">&#034;&#034;<\/span><\/p>\n<p>\u6216\u8005\u5c01\u88c5&#xff1a;<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">text_or_empty<\/span><span class=\"token punctuation\">(<\/span>node<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">return<\/span> node<span class=\"token punctuation\">.<\/span>get_text<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034; &#034;<\/span><span class=\"token punctuation\">,<\/span> strip<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">if<\/span> node <span class=\"token keyword\">else<\/span> <span class=\"token string\">&#034;&#034;<\/span><\/p>\n<h4>16.5 \u7f16\u7801\u4e71\u7801\u600e\u4e48\u529e<\/h4>\n<p>\u6709\u4e9b\u8001\u7ad9\u70b9\u4e0d\u662f UTF-8&#xff0c;\u800c\u662f GBK \u6216 GB2312\u3002\u8868\u73b0\u4e3a&#xff1a;<\/p>\n<p>\u00e5\u0178\u017d\u00e5\u00b8\u201a\u00e5\u00bb\u00ba\u00e8\u00ae\u00be<\/p>\n<p>\u5904\u7406\u65b9\u5f0f&#xff1a;<\/p>\n<p><span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> response<span class=\"token punctuation\">.<\/span>encoding <span class=\"token keyword\">or<\/span> response<span class=\"token punctuation\">.<\/span>encoding<span class=\"token punctuation\">.<\/span>lower<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token string\">&#034;iso-8859-1&#034;<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    response<span class=\"token punctuation\">.<\/span>encoding <span class=\"token operator\">&#061;<\/span> response<span class=\"token punctuation\">.<\/span>apparent_encoding<\/p>\n<p>\u5982\u679c\u77e5\u9053\u7ad9\u70b9\u7f16\u7801&#xff0c;\u4e5f\u53ef\u4ee5\u5f3a\u5236&#xff1a;<\/p>\n<p>response<span class=\"token punctuation\">.<\/span>encoding <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;gb18030&#034;<\/span><\/p>\n<p>CSV \u5efa\u8bae\u7528&#xff1a;<\/p>\n<p>encoding<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;utf-8-sig&#034;<\/span><\/p>\n<p>\u8fd9\u6837 Excel \u6253\u5f00\u4e2d\u6587\u66f4\u7a33\u3002<\/p>\n<h4>16.6 \u65e5\u671f\u89e3\u6790\u5931\u8d25\u600e\u4e48\u529e<\/h4>\n<p>\u9047\u5230\u5947\u602a\u65e5\u671f&#xff1a;<\/p>\n<p>\u6c11\u56fd\u4e09\u5341\u516d\u5e74\u4e94\u6708\u4e00\u65e5<br \/>\n\u4e8c\u3007\u4e8c\u56db\u5e74\u4e94\u6708\u4e00\u65e5<br \/>\n2024\u5e74\u7b2c\u4e94\u671f<\/p>\n<p>\u4e0d\u8981\u786c\u731c\u3002\u53ef\u4ee5\u5148\u4fdd\u7559\u539f\u503c&#xff0c;\u540c\u65f6\u8bb0\u5f55\u65e5\u5fd7&#xff1a;<\/p>\n<p>logging<span class=\"token punctuation\">.<\/span>warning<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;date parse failed: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> value<span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">return<\/span> value<\/p>\n<p>\u5982\u679c\u540e\u7eed\u786e\u5b9e\u8981\u5206\u6790&#xff0c;\u518d\u5355\u72ec\u5199\u65e5\u671f\u6807\u51c6\u5316\u811a\u672c\u3002<\/p>\n<h4>16.7 \u91cd\u590d\u6570\u636e\u592a\u591a\u600e\u4e48\u529e<\/h4>\n<p>\u68c0\u67e5\u552f\u4e00\u952e\u662f\u5426\u5408\u7406\u3002<\/p>\n<p>\u5982\u679c URL \u552f\u4e00&#xff1a;<\/p>\n<p>url <span class=\"token keyword\">TEXT<\/span> <span class=\"token keyword\">UNIQUE<\/span><\/p>\n<p>\u5982\u679c URL \u4e0d\u552f\u4e00&#xff0c;\u53ef\u4ee5\u5efa\u7acb\u8054\u5408\u552f\u4e00\u952e&#xff1a;<\/p>\n<p><span class=\"token keyword\">UNIQUE<\/span><span class=\"token punctuation\">(<\/span>newspaper_name<span class=\"token punctuation\">,<\/span> issue_no<span class=\"token punctuation\">,<\/span> publish_date<span class=\"token punctuation\">,<\/span> column_name<span class=\"token punctuation\">,<\/span> topic<span class=\"token punctuation\">)<\/span><\/p>\n<p>\u4f46\u8054\u5408\u552f\u4e00\u952e\u8981\u5c0f\u5fc3\u3002\u6807\u9898\u76f8\u540c\u3001\u680f\u76ee\u76f8\u540c\u3001\u65e5\u671f\u76f8\u540c\u7684\u60c5\u51b5\u5e76\u4e0d\u662f\u5b8c\u5168\u4e0d\u53ef\u80fd\u3002<\/p>\n<h4>16.8 \u4e0b\u4e00\u9875\u6b7b\u5faa\u73af\u600e\u4e48\u529e<\/h4>\n<p>\u6709\u4e9b\u7ad9\u70b9\u6700\u540e\u4e00\u9875\u7684\u201c\u4e0b\u4e00\u9875\u201d\u4ecd\u7136\u6307\u5411\u5f53\u524d\u9875\u3002\u89e3\u51b3\u65b9\u5f0f&#xff1a;<\/p>\n<p>visited_pages <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">set<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">if<\/span> current_url <span class=\"token keyword\">in<\/span> visited_pages<span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">break<\/span><\/p>\n<p>visited_pages<span class=\"token punctuation\">.<\/span>add<span class=\"token punctuation\">(<\/span>current_url<span class=\"token punctuation\">)<\/span><\/p>\n<p>\u8fd9\u884c\u4ee3\u7801\u770b\u8d77\u6765\u666e\u901a&#xff0c;\u4f46\u5728\u771f\u5b9e\u9879\u76ee\u91cc\u975e\u5e38\u6551\u547d\u3002<\/p>\n<hr \/>\n<h3>17. \u8fdb\u9636\u4f18\u5316<\/h3>\n<h4>17.1 \u5e76\u53d1\u91c7\u96c6<\/h4>\n<p>\u5f53\u5b57\u6bb5\u89c4\u5219\u7a33\u5b9a\u540e&#xff0c;\u53ef\u4ee5\u8003\u8651\u5e76\u53d1\u3002\u4f46\u5efa\u8bae\u4ece\u8be6\u60c5\u9875\u5e76\u53d1\u5f00\u59cb&#xff0c;\u4e0d\u8981\u4e00\u5f00\u59cb\u5c31\u5e76\u53d1\u6240\u6709\u5c42\u7ea7\u3002<\/p>\n<p>\u4f8b\u5982&#xff1a;<\/p>\n<p><span class=\"token keyword\">from<\/span> concurrent<span class=\"token punctuation\">.<\/span>futures <span class=\"token keyword\">import<\/span> ThreadPoolExecutor<span class=\"token punctuation\">,<\/span> as_completed<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">fetch_detail_task<\/span><span class=\"token punctuation\">(<\/span>detail_url<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    html <span class=\"token operator\">&#061;<\/span> fetcher<span class=\"token punctuation\">.<\/span>fetch<span class=\"token punctuation\">(<\/span>detail_url<span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">return<\/span> parser<span class=\"token punctuation\">.<\/span>parse_detail<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">,<\/span> detail_url<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">with<\/span> ThreadPoolExecutor<span class=\"token punctuation\">(<\/span>max_workers<span class=\"token operator\">&#061;<\/span><span class=\"token number\">3<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">as<\/span> executor<span class=\"token punctuation\">:<\/span><br \/>\n    futures <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span>executor<span class=\"token punctuation\">.<\/span>submit<span class=\"token punctuation\">(<\/span>fetch_detail_task<span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">for<\/span> url <span class=\"token keyword\">in<\/span> detail_urls<span class=\"token punctuation\">]<\/span><\/p>\n<p>    <span class=\"token keyword\">for<\/span> future <span class=\"token keyword\">in<\/span> as_completed<span class=\"token punctuation\">(<\/span>futures<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        data <span class=\"token operator\">&#061;<\/span> future<span class=\"token punctuation\">.<\/span>result<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>max_workers&#061;3 \u5df2\u7ecf\u8db3\u591f\u6e29\u548c\u3002\u9664\u975e\u4f60\u5f97\u5230\u7ad9\u70b9\u6388\u6743\u6216\u660e\u786e\u63a5\u53e3\u9650\u989d&#xff0c;\u5426\u5219\u4e0d\u5efa\u8bae\u5f00\u592a\u9ad8\u3002<\/p>\n<h4>17.2 asyncio<\/h4>\n<p>\u5982\u679c\u8bf7\u6c42\u91cf\u8f83\u5927&#xff0c;\u53ef\u4ee5\u7528 aiohttp\u3002\u4e0d\u8fc7\u5f02\u6b65\u722c\u866b\u7684\u9519\u8bef\u5904\u7406\u3001\u9650\u901f\u3001\u91cd\u8bd5\u4f1a\u66f4\u590d\u6742\u3002\u4e0d\u8981\u4e3a\u4e86\u201c\u770b\u8d77\u6765\u9ad8\u7ea7\u201d\u800c\u5f15\u5165\u5f02\u6b65\u3002<\/p>\n<p>\u9002\u5408 asyncio \u7684\u573a\u666f&#xff1a;<\/p>\n<p>\u8be6\u60c5\u9875\u6570\u91cf\u5927<br \/>\n\u63a5\u53e3\u54cd\u5e94\u7a33\u5b9a<br \/>\n\u6709\u660e\u786e\u9650\u901f\u89c4\u5219<br \/>\n\u9700\u8981\u63d0\u9ad8\u541e\u5410<\/p>\n<p>\u4e0d\u9002\u5408\u7684\u573a\u666f&#xff1a;<\/p>\n<p>\u7ad9\u70b9\u7ed3\u6784\u8fd8\u6ca1\u6478\u6e05<br \/>\n\u9009\u62e9\u5668\u7ecf\u5e38\u53d8\u5316<br \/>\n\u53cd\u590d\u51fa\u73b0 403\/429<br \/>\n\u9700\u8981\u5927\u91cf\u4eba\u5de5\u6821\u9a8c<\/p>\n<h4>17.3 Scrapy \u6539\u9020\u65b9\u5411<\/h4>\n<p>\u5982\u679c\u9879\u76ee\u53d8\u6210\u591a\u7ad9\u70b9\u3001\u591a\u4efb\u52a1\u3001\u957f\u671f\u8fd0\u884c&#xff0c;\u53ef\u4ee5\u8fc1\u79fb\u5230 Scrapy\u3002<\/p>\n<p>Scrapy \u4f18\u52bf&#xff1a;<\/p>\n<p>\u8bf7\u6c42\u8c03\u5ea6<br \/>\n\u53bb\u91cd\u961f\u5217<br \/>\n\u4e2d\u95f4\u4ef6<br \/>\n\u5931\u8d25\u91cd\u8bd5<br \/>\n\u65e5\u5fd7\u4f53\u7cfb<br \/>\n\u5bfc\u51fa\u7ba1\u9053<br \/>\n\u589e\u91cf\u91c7\u96c6<\/p>\n<p>Scrapy \u4e2d\u53ef\u4ee5\u628a\u5b57\u6bb5\u5b9a\u4e49\u4e3a Item&#xff1a;<\/p>\n<p><span class=\"token keyword\">import<\/span> scrapy<\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">NewspaperIssueItem<\/span><span class=\"token punctuation\">(<\/span>scrapy<span class=\"token punctuation\">.<\/span>Item<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    newspaper_name <span class=\"token operator\">&#061;<\/span> scrapy<span class=\"token punctuation\">.<\/span>Field<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    issue_no <span class=\"token operator\">&#061;<\/span> scrapy<span class=\"token punctuation\">.<\/span>Field<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    publish_date <span class=\"token operator\">&#061;<\/span> scrapy<span class=\"token punctuation\">.<\/span>Field<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    column_name <span class=\"token operator\">&#061;<\/span> scrapy<span class=\"token punctuation\">.<\/span>Field<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    topic <span class=\"token operator\">&#061;<\/span> scrapy<span class=\"token punctuation\">.<\/span>Field<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    digitization_status <span class=\"token operator\">&#061;<\/span> scrapy<span class=\"token punctuation\">.<\/span>Field<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    url <span class=\"token operator\">&#061;<\/span> scrapy<span class=\"token punctuation\">.<\/span>Field<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u7136\u540e\u5199 Pipeline \u5b58 SQLite \u6216 MySQL\u3002<\/p>\n<h4>17.4 \u65ad\u70b9\u7eed\u8dd1<\/h4>\n<p>\u65ad\u70b9\u7eed\u8dd1\u975e\u5e38\u5b9e\u7528\u3002\u601d\u8def\u6709\u4e24\u79cd\u3002<\/p>\n<p>\u7b2c\u4e00\u79cd&#xff1a;\u4f9d\u8d56\u6570\u636e\u5e93\u552f\u4e00\u952e\u3002\u5df2\u7ecf\u6293\u8fc7\u7684 URL \u518d\u63d2\u5165\u65f6\u81ea\u52a8\u66f4\u65b0\u3002<\/p>\n<p>\u7b2c\u4e8c\u79cd&#xff1a;\u7ef4\u62a4\u5df2\u6293\u96c6\u5408\u3002<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">load_done_urls<\/span><span class=\"token punctuation\">(<\/span>conn<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">set<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    rows <span class=\"token operator\">&#061;<\/span> conn<span class=\"token punctuation\">.<\/span>execute<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;SELECT url FROM newspaper_issues&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>fetchall<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">return<\/span> <span class=\"token punctuation\">{<\/span>row<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;url&#034;<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token keyword\">for<\/span> row <span class=\"token keyword\">in<\/span> rows<span class=\"token punctuation\">}<\/span><\/p>\n<p>\u8bf7\u6c42\u8be6\u60c5\u9875\u524d\u5224\u65ad&#xff1a;<\/p>\n<p><span class=\"token keyword\">if<\/span> detail_url <span class=\"token keyword\">in<\/span> done_urls<span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">continue<\/span><\/p>\n<h4>17.5 \u6e38\u6807\u8bb0\u5f55<\/h4>\n<p>\u53ef\u4ee5\u5355\u72ec\u5efa\u4e00\u5f20\u4efb\u52a1\u8fdb\u5ea6\u8868&#xff1a;<\/p>\n<p><span class=\"token keyword\">CREATE<\/span> <span class=\"token keyword\">TABLE<\/span> <span class=\"token keyword\">IF<\/span> <span class=\"token operator\">NOT<\/span> <span class=\"token keyword\">EXISTS<\/span> crawl_cursor <span class=\"token punctuation\">(<\/span><br \/>\n    task_name <span class=\"token keyword\">TEXT<\/span> <span class=\"token keyword\">PRIMARY<\/span> <span class=\"token keyword\">KEY<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token keyword\">year<\/span> <span class=\"token keyword\">INTEGER<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token keyword\">month<\/span> <span class=\"token keyword\">INTEGER<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    page_url <span class=\"token keyword\">TEXT<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    updated_at <span class=\"token keyword\">TEXT<\/span><br \/>\n<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span><\/p>\n<p>\u6bcf\u5904\u7406\u5b8c\u4e00\u4e2a\u6708\u4efd\u5c31\u66f4\u65b0\u6e38\u6807\u3002\u7a0b\u5e8f\u5f02\u5e38\u9000\u51fa\u540e&#xff0c;\u4ece\u6700\u8fd1\u6e38\u6807\u7ee7\u7eed\u3002<\/p>\n<h4>17.6 \u65e5\u5fd7\u4e0e\u76d1\u63a7<\/h4>\n<p>\u81f3\u5c11\u8bb0\u5f55\u8fd9\u4e9b\u6307\u6807&#xff1a;<\/p>\n<p>\u8bf7\u6c42\u6210\u529f\u6570<br \/>\n\u8bf7\u6c42\u5931\u8d25\u6570<br \/>\n\u89e3\u6790\u6210\u529f\u6570<br \/>\n\u89e3\u6790\u5931\u8d25\u6570<br \/>\n\u5165\u5e93\u6570\u91cf<br \/>\n\u91cd\u590d\u6570\u91cf<br \/>\n\u7a7a\u5b57\u6bb5\u6570\u91cf<br \/>\n\u5e73\u5747\u54cd\u5e94\u65f6\u95f4<\/p>\n<p>\u7b80\u5355\u65e5\u5fd7\u793a\u4f8b&#xff1a;<\/p>\n<p>logging<span class=\"token punctuation\">.<\/span>info<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;items found: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>items<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\nlogging<span class=\"token punctuation\">.<\/span>warning<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;field missing topic url&#061;%s&#034;<\/span><span class=\"token punctuation\">,<\/span> detail_url<span class=\"token punctuation\">)<\/span><br \/>\nlogging<span class=\"token punctuation\">.<\/span>error<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;request finally failed url&#061;%s&#034;<\/span><span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">)<\/span><\/p>\n<p>\u957f\u671f\u4efb\u52a1\u53ef\u4ee5\u628a\u65e5\u5fd7\u5199\u5165\u6587\u4ef6&#xff1a;<\/p>\n<p>logging<span class=\"token punctuation\">.<\/span>basicConfig<span class=\"token punctuation\">(<\/span><br \/>\n    filename<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;crawler.log&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    level<span class=\"token operator\">&#061;<\/span>logging<span class=\"token punctuation\">.<\/span>INFO<span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token builtin\">format<\/span><span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;%(asctime)s | %(levelname)s | %(message)s&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n<span class=\"token punctuation\">)<\/span><\/p>\n<h4>17.7 \u5b9a\u65f6\u4efb\u52a1<\/h4>\n<p>Linux cron \u793a\u4f8b&#xff1a;<\/p>\n<p><span class=\"token number\">0<\/span> <span class=\"token number\">2<\/span> * * * \/usr\/bin\/python3 \/opt\/newspaper_index_crawler\/main.py <span class=\"token operator\">&gt;&gt;<\/span> \/opt\/newspaper_index_crawler\/run.log <span class=\"token operator\"><span class=\"token file-descriptor important\">2<\/span>&gt;<\/span><span class=\"token file-descriptor important\">&amp;1<\/span><\/p>\n<p>\u8868\u793a\u6bcf\u5929\u51cc\u6668 2 \u70b9\u8fd0\u884c\u4e00\u6b21\u3002<\/p>\n<p>\u5982\u679c\u4efb\u52a1\u66f4\u590d\u6742&#xff0c;\u53ef\u4ee5\u7528 Airflow\u3001Prefect \u6216\u5176\u4ed6\u5de5\u4f5c\u6d41\u5de5\u5177\u3002\u4f46\u5bf9\u4e8e\u5355\u7ad9\u70b9\u6bcf\u65e5\u589e\u91cf\u91c7\u96c6&#xff0c;cron \u5df2\u7ecf\u591f\u7528\u3002<\/p>\n<h4>17.8 \u589e\u91cf\u91c7\u96c6<\/h4>\n<p>\u62a5\u520a\u7d22\u5f15\u5f88\u9002\u5408\u589e\u91cf\u91c7\u96c6\u3002\u6bd4\u5982\u53ea\u91c7\u96c6\u6700\u8fd1 3 \u4e2a\u6708&#xff1a;<\/p>\n<p>years_months <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><br \/>\n    <span class=\"token punctuation\">(<\/span><span class=\"token number\">2024<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">3<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token punctuation\">(<\/span><span class=\"token number\">2024<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">4<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token punctuation\">(<\/span><span class=\"token number\">2024<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">5<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n<span class=\"token punctuation\">]<\/span><\/p>\n<p>\u6216\u8005\u6839\u636e\u5f53\u524d\u65e5\u671f\u81ea\u52a8\u751f\u6210&#xff1a;<\/p>\n<p><span class=\"token keyword\">from<\/span> datetime <span class=\"token keyword\">import<\/span> date<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">recent_year_months<\/span><span class=\"token punctuation\">(<\/span>n<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">int<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">3<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    today <span class=\"token operator\">&#061;<\/span> date<span class=\"token punctuation\">.<\/span>today<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    result <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n    year <span class=\"token operator\">&#061;<\/span> today<span class=\"token punctuation\">.<\/span>year<br \/>\n    month <span class=\"token operator\">&#061;<\/span> today<span class=\"token punctuation\">.<\/span>month<\/p>\n<p>    <span class=\"token keyword\">for<\/span> _ <span class=\"token keyword\">in<\/span> <span class=\"token builtin\">range<\/span><span class=\"token punctuation\">(<\/span>n<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        result<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">(<\/span>year<span class=\"token punctuation\">,<\/span> month<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        month <span class=\"token operator\">-&#061;<\/span> <span class=\"token number\">1<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> month <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token number\">0<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            month <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">12<\/span><br \/>\n            year <span class=\"token operator\">-&#061;<\/span> <span class=\"token number\">1<\/span><\/p>\n<p>    <span class=\"token keyword\">return<\/span> result<\/p>\n<hr \/>\n<h3>18. \u5de5\u7a0b\u5316\u62c6\u5206\u5efa\u8bae<\/h3>\n<p>\u5355\u6587\u4ef6\u4ee3\u7801\u9002\u5408\u6f14\u793a&#xff0c;\u4f46\u771f\u5b9e\u9879\u76ee\u5efa\u8bae\u62c6\u5206\u3002<\/p>\n<h4>18.1 config.py<\/h4>\n<p><span class=\"token keyword\">from<\/span> pathlib <span class=\"token keyword\">import<\/span> Path<\/p>\n<p>BASE_DIR <span class=\"token operator\">&#061;<\/span> Path<span class=\"token punctuation\">(<\/span>__file__<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>resolve<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>parent<br \/>\nDATA_DIR <span class=\"token operator\">&#061;<\/span> BASE_DIR <span class=\"token operator\">\/<\/span> <span class=\"token string\">&#034;data&#034;<\/span><br \/>\nDB_PATH <span class=\"token operator\">&#061;<\/span> DATA_DIR <span class=\"token operator\">\/<\/span> <span class=\"token string\">&#034;newspaper_issues.db&#034;<\/span><br \/>\nCSV_PATH <span class=\"token operator\">&#061;<\/span> DATA_DIR <span class=\"token operator\">\/<\/span> <span class=\"token string\">&#034;newspaper_issues.csv&#034;<\/span><\/p>\n<p>BASE_URL <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;https:\/\/example.com&#034;<\/span><br \/>\nDEFAULT_NEWSPAPER_NAME <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;\u793a\u4f8b\u65e5\u62a5&#034;<\/span><\/p>\n<p>REQUEST_TIMEOUT <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">(<\/span><span class=\"token number\">5<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">20<\/span><span class=\"token punctuation\">)<\/span><br \/>\nMIN_DELAY <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">1.0<\/span><br \/>\nMAX_DELAY <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">2.5<\/span><br \/>\nMAX_RETRIES <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">3<\/span><\/p>\n<p>CRAWL_YEARS_MONTHS <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><br \/>\n    <span class=\"token punctuation\">(<\/span><span class=\"token number\">2024<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">5<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n<span class=\"token punctuation\">]<\/span><\/p>\n<h4>18.2 crawler\/fetcher.py<\/h4>\n<p><span class=\"token keyword\">import<\/span> logging<br \/>\n<span class=\"token keyword\">import<\/span> random<br \/>\n<span class=\"token keyword\">import<\/span> time<br \/>\n<span class=\"token keyword\">from<\/span> typing <span class=\"token keyword\">import<\/span> Optional<\/p>\n<p><span class=\"token keyword\">import<\/span> requests<\/p>\n<p><span class=\"token keyword\">from<\/span> config <span class=\"token keyword\">import<\/span> REQUEST_TIMEOUT<span class=\"token punctuation\">,<\/span> MIN_DELAY<span class=\"token punctuation\">,<\/span> MAX_DELAY<span class=\"token punctuation\">,<\/span> MAX_RETRIES<\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">Fetcher<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">__init__<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>session <span class=\"token operator\">&#061;<\/span> requests<span class=\"token punctuation\">.<\/span>Session<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>session<span class=\"token punctuation\">.<\/span>headers<span class=\"token punctuation\">.<\/span>update<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">{<\/span><br \/>\n            <span class=\"token string\">&#034;User-Agent&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token punctuation\">(<\/span><br \/>\n                <span class=\"token string\">&#034;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) &#034;<\/span><br \/>\n                <span class=\"token string\">&#034;AppleWebKit\/537.36 (KHTML, like Gecko) &#034;<\/span><br \/>\n                <span class=\"token string\">&#034;Chrome\/124.0 Safari\/537.36&#034;<\/span><br \/>\n            <span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;Accept-Language&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;zh-CN,zh;q&#061;0.9,en;q&#061;0.8&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">get_text<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> referer<span class=\"token punctuation\">:<\/span> Optional<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        headers <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><span class=\"token punctuation\">}<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> referer<span class=\"token punctuation\">:<\/span><br \/>\n            headers<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;Referer&#034;<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> referer<\/p>\n<p>        <span class=\"token keyword\">for<\/span> attempt <span class=\"token keyword\">in<\/span> <span class=\"token builtin\">range<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span> MAX_RETRIES <span class=\"token operator\">&#043;<\/span> <span class=\"token number\">1<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                time<span class=\"token punctuation\">.<\/span>sleep<span class=\"token punctuation\">(<\/span>random<span class=\"token punctuation\">.<\/span>uniform<span class=\"token punctuation\">(<\/span>MIN_DELAY<span class=\"token punctuation\">,<\/span> MAX_DELAY<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n                response <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>session<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><br \/>\n                    url<span class=\"token punctuation\">,<\/span><br \/>\n                    headers<span class=\"token operator\">&#061;<\/span>headers<span class=\"token punctuation\">,<\/span><br \/>\n                    timeout<span class=\"token operator\">&#061;<\/span>REQUEST_TIMEOUT<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token punctuation\">)<\/span><\/p>\n<p>                <span class=\"token keyword\">if<\/span> response<span class=\"token punctuation\">.<\/span>status_code <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token number\">404<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                    logging<span class=\"token punctuation\">.<\/span>warning<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;404: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">)<\/span><br \/>\n                    <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;&#034;<\/span><\/p>\n<p>                <span class=\"token keyword\">if<\/span> response<span class=\"token punctuation\">.<\/span>status_code <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token number\">429<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                    wait <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">2<\/span> <span class=\"token operator\">**<\/span> attempt <span class=\"token operator\">*<\/span> <span class=\"token number\">3<\/span><br \/>\n                    logging<span class=\"token punctuation\">.<\/span>warning<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;429, sleep %s seconds: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> wait<span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">)<\/span><br \/>\n                    time<span class=\"token punctuation\">.<\/span>sleep<span class=\"token punctuation\">(<\/span>wait<span class=\"token punctuation\">)<\/span><br \/>\n                    <span class=\"token keyword\">continue<\/span><\/p>\n<p>                response<span class=\"token punctuation\">.<\/span>raise_for_status<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>                <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> response<span class=\"token punctuation\">.<\/span>encoding <span class=\"token keyword\">or<\/span> response<span class=\"token punctuation\">.<\/span>encoding<span class=\"token punctuation\">.<\/span>lower<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token string\">&#034;iso-8859-1&#034;<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                    response<span class=\"token punctuation\">.<\/span>encoding <span class=\"token operator\">&#061;<\/span> response<span class=\"token punctuation\">.<\/span>apparent_encoding<\/p>\n<p>                <span class=\"token keyword\">return<\/span> response<span class=\"token punctuation\">.<\/span>text<\/p>\n<p>            <span class=\"token keyword\">except<\/span> requests<span class=\"token punctuation\">.<\/span>RequestException <span class=\"token keyword\">as<\/span> exc<span class=\"token punctuation\">:<\/span><br \/>\n                wait <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">2<\/span> <span class=\"token operator\">**<\/span> attempt<br \/>\n                logging<span class=\"token punctuation\">.<\/span>warning<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;request error attempt&#061;%s url&#061;%s err&#061;%s&#034;<\/span><span class=\"token punctuation\">,<\/span> attempt<span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">,<\/span> exc<span class=\"token punctuation\">)<\/span><br \/>\n                time<span class=\"token punctuation\">.<\/span>sleep<span class=\"token punctuation\">(<\/span>wait<span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;&#034;<\/span><\/p>\n<h4>18.3 crawler\/parser.py<\/h4>\n<p><span class=\"token keyword\">import<\/span> re<br \/>\n<span class=\"token keyword\">from<\/span> typing <span class=\"token keyword\">import<\/span> Dict<span class=\"token punctuation\">,<\/span> List<br \/>\n<span class=\"token keyword\">from<\/span> urllib<span class=\"token punctuation\">.<\/span>parse <span class=\"token keyword\">import<\/span> urljoin<\/p>\n<p><span class=\"token keyword\">from<\/span> bs4 <span class=\"token keyword\">import<\/span> BeautifulSoup<\/p>\n<p><span class=\"token keyword\">from<\/span> config <span class=\"token keyword\">import<\/span> BASE_URL<\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">Parser<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">soup<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> html<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> BeautifulSoup<span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> BeautifulSoup<span class=\"token punctuation\">(<\/span>html <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;lxml&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">parse_calendar<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> html<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> List<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        soup <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>soup<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">)<\/span><br \/>\n        urls <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n        <span class=\"token keyword\">for<\/span> a <span class=\"token keyword\">in<\/span> soup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;a.issue-day&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            href <span class=\"token operator\">&#061;<\/span> a<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;href&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> href<span class=\"token punctuation\">:<\/span><br \/>\n                urls<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span>urljoin<span class=\"token punctuation\">(<\/span>BASE_URL<span class=\"token punctuation\">,<\/span> href<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">(<\/span><span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">.<\/span>fromkeys<span class=\"token punctuation\">(<\/span>urls<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">parse_issue_list<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> html<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> Dict<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">object<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        soup <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>soup<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">)<\/span><\/p>\n<p>        context <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n            <span class=\"token string\">&#034;newspaper_name&#034;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>text<span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.issue-head .newspaper&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;issue_no&#034;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>text<span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.issue-head .issue-no&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;publish_date&#034;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>text<span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.issue-head .publish-date&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">}<\/span><\/p>\n<p>        items <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n        <span class=\"token keyword\">for<\/span> item <span class=\"token keyword\">in<\/span> soup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.issue-list .issue-item&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            a <span class=\"token operator\">&#061;<\/span> item<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;a.detail-link&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> a<span class=\"token punctuation\">:<\/span><br \/>\n                <span class=\"token keyword\">continue<\/span><\/p>\n<p>            href <span class=\"token operator\">&#061;<\/span> a<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;href&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> href<span class=\"token punctuation\">:<\/span><br \/>\n                <span class=\"token keyword\">continue<\/span><\/p>\n<p>            items<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">{<\/span><br \/>\n                <span class=\"token string\">&#034;topic&#034;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>text<span class=\"token punctuation\">(<\/span>a<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;url&#034;<\/span><span class=\"token punctuation\">:<\/span> urljoin<span class=\"token punctuation\">(<\/span>BASE_URL<span class=\"token punctuation\">,<\/span> href<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;column_name&#034;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>text<span class=\"token punctuation\">(<\/span>item<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.column&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;digitization_status&#034;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>text<span class=\"token punctuation\">(<\/span>item<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.status&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        next_url <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;&#034;<\/span><br \/>\n        next_node <span class=\"token operator\">&#061;<\/span> soup<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.pagination a.next&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> next_node <span class=\"token keyword\">and<\/span> next_node<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;href&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            next_url <span class=\"token operator\">&#061;<\/span> urljoin<span class=\"token punctuation\">(<\/span>BASE_URL<span class=\"token punctuation\">,<\/span> next_node<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;href&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">return<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n            <span class=\"token string\">&#034;page_context&#034;<\/span><span class=\"token punctuation\">:<\/span> context<span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;items&#034;<\/span><span class=\"token punctuation\">:<\/span> items<span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;next_url&#034;<\/span><span class=\"token punctuation\">:<\/span> next_url<span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">}<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">parse_detail<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> html<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> Dict<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        soup <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>soup<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">)<\/span><br \/>\n        data <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n            <span class=\"token string\">&#034;newspaper_name&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;issue_no&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;publish_date&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;column_name&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;topic&#034;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>text<span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;h1.topic&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;digitization_status&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;url&#034;<\/span><span class=\"token punctuation\">:<\/span> url<span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">}<\/span><\/p>\n<p>        mapping <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n            <span class=\"token string\">&#034;\u62a5\u520a\u540d&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;newspaper_name&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;\u671f\u53f7&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;issue_no&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;\u51fa\u7248\u65e5\u671f&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;publish_date&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;\u680f\u76ee&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;column_name&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;\u6570\u5b57\u5316\u72b6\u6001&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;digitization_status&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">}<\/span><\/p>\n<p>        <span class=\"token keyword\">for<\/span> li <span class=\"token keyword\">in<\/span> soup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;ul.meta li&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            span <span class=\"token operator\">&#061;<\/span> li<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;span&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            b <span class=\"token operator\">&#061;<\/span> li<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;b&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>            key <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>text<span class=\"token punctuation\">(<\/span>span<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>replace<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;&#xff1a;&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>replace<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;:&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            value <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>text<span class=\"token punctuation\">(<\/span>b<span class=\"token punctuation\">)<\/span><\/p>\n<p>            field <span class=\"token operator\">&#061;<\/span> mapping<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span>key<span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> field<span class=\"token punctuation\">:<\/span><br \/>\n                data<span class=\"token punctuation\">[<\/span>field<span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> value<\/p>\n<p>        <span class=\"token keyword\">return<\/span> data<\/p>\n<p>    <span class=\"token decorator annotation punctuation\">&#064;staticmethod<\/span><br \/>\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">text<\/span><span class=\"token punctuation\">(<\/span>node<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> node<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;&#034;<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> re<span class=\"token punctuation\">.<\/span>sub<span class=\"token punctuation\">(<\/span><span class=\"token string\">r&#034;\\\\s&#043;&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034; &#034;<\/span><span class=\"token punctuation\">,<\/span> node<span class=\"token punctuation\">.<\/span>get_text<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034; &#034;<\/span><span class=\"token punctuation\">,<\/span> strip<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<h4>18.4 crawler\/storage.py<\/h4>\n<p><span class=\"token keyword\">import<\/span> sqlite3<br \/>\n<span class=\"token keyword\">from<\/span> datetime <span class=\"token keyword\">import<\/span> datetime<br \/>\n<span class=\"token keyword\">from<\/span> pathlib <span class=\"token keyword\">import<\/span> Path<\/p>\n<p><span class=\"token keyword\">import<\/span> pandas <span class=\"token keyword\">as<\/span> pd<\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">Storage<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">__init__<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> db_path<span class=\"token punctuation\">:<\/span> Path<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>conn <span class=\"token operator\">&#061;<\/span> sqlite3<span class=\"token punctuation\">.<\/span>connect<span class=\"token punctuation\">(<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">(<\/span>db_path<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">init_db<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>conn<span class=\"token punctuation\">.<\/span>execute<span class=\"token punctuation\">(<\/span><span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n        CREATE TABLE IF NOT EXISTS newspaper_issues (<br \/>\n            id INTEGER PRIMARY KEY AUTOINCREMENT,<br \/>\n            newspaper_name TEXT NOT NULL,<br \/>\n            issue_no TEXT,<br \/>\n            publish_date TEXT,<br \/>\n            column_name TEXT,<br \/>\n            topic TEXT,<br \/>\n            digitization_status TEXT,<br \/>\n            url TEXT NOT NULL UNIQUE,<br \/>\n            content_hash TEXT,<br \/>\n            created_at TEXT NOT NULL,<br \/>\n            updated_at TEXT NOT NULL<br \/>\n        );<br \/>\n        &#034;&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>conn<span class=\"token punctuation\">.<\/span>commit<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">upsert_dict<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> item<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        now <span class=\"token operator\">&#061;<\/span> datetime<span class=\"token punctuation\">.<\/span>now<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strftime<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;%Y-%m-%d %H:%M:%S&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>conn<span class=\"token punctuation\">.<\/span>execute<span class=\"token punctuation\">(<\/span><span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n        INSERT INTO newspaper_issues (<br \/>\n            newspaper_name,<br \/>\n            issue_no,<br \/>\n            publish_date,<br \/>\n            column_name,<br \/>\n            topic,<br \/>\n            digitization_status,<br \/>\n            url,<br \/>\n            content_hash,<br \/>\n            created_at,<br \/>\n            updated_at<br \/>\n        )<br \/>\n        VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)<br \/>\n        ON CONFLICT(url) DO UPDATE SET<br \/>\n            newspaper_name&#061;excluded.newspaper_name,<br \/>\n            issue_no&#061;excluded.issue_no,<br \/>\n            publish_date&#061;excluded.publish_date,<br \/>\n            column_name&#061;excluded.column_name,<br \/>\n            topic&#061;excluded.topic,<br \/>\n            digitization_status&#061;excluded.digitization_status,<br \/>\n            content_hash&#061;excluded.content_hash,<br \/>\n            updated_at&#061;excluded.updated_at;<br \/>\n        &#034;&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">(<\/span><br \/>\n            item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;newspaper_name&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;issue_no&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;publish_date&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;column_name&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;topic&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;digitization_status&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;url&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;content_hash&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            now<span class=\"token punctuation\">,<\/span><br \/>\n            now<span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>conn<span class=\"token punctuation\">.<\/span>commit<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">export_csv<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> csv_path<span class=\"token punctuation\">:<\/span> Path<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        df <span class=\"token operator\">&#061;<\/span> pd<span class=\"token punctuation\">.<\/span>read_sql_query<span class=\"token punctuation\">(<\/span><span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n        SELECT<br \/>\n            newspaper_name AS \u62a5\u520a\u540d,<br \/>\n            issue_no AS \u671f\u53f7,<br \/>\n            publish_date AS \u51fa\u7248\u65e5\u671f,<br \/>\n            column_name AS \u680f\u76ee,<br \/>\n            topic AS \u4e3b\u9898,<br \/>\n            digitization_status AS \u6570\u5b57\u5316\u72b6\u6001,<br \/>\n            url AS \u94fe\u63a5<br \/>\n        FROM newspaper_issues<br \/>\n        ORDER BY publish_date, issue_no, id<br \/>\n        &#034;&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span> self<span class=\"token punctuation\">.<\/span>conn<span class=\"token punctuation\">)<\/span><br \/>\n        df<span class=\"token punctuation\">.<\/span>to_csv<span class=\"token punctuation\">(<\/span>csv_path<span class=\"token punctuation\">,<\/span> index<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">False<\/span><span class=\"token punctuation\">,<\/span> encoding<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;utf-8-sig&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">close<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>conn<span class=\"token punctuation\">.<\/span>close<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u62c6\u5206\u4e4b\u540e&#xff0c;\u4ee3\u7801\u66f4\u9002\u5408\u56e2\u961f\u7ef4\u62a4&#xff0c;\u4e5f\u66f4\u65b9\u4fbf\u5199\u5355\u5143\u6d4b\u8bd5\u3002<\/p>\n<hr \/>\n<h3>19. \u5b57\u6bb5\u8d28\u91cf\u68c0\u67e5<\/h3>\n<p>\u722c\u866b\u4e0d\u662f\u8dd1\u5b8c\u5c31\u7ed3\u675f\u3002\u6570\u636e\u8d28\u91cf\u68c0\u67e5\u975e\u5e38\u5173\u952e\u3002<\/p>\n<h4>19.1 \u68c0\u67e5\u7a7a\u5b57\u6bb5<\/h4>\n<p><span class=\"token keyword\">SELECT<\/span> <span class=\"token function\">COUNT<\/span><span class=\"token punctuation\">(<\/span><span class=\"token operator\">*<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">FROM<\/span> newspaper_issues <span class=\"token keyword\">WHERE<\/span> topic <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#039;&#039;<\/span><span class=\"token punctuation\">;<\/span><br \/>\n<span class=\"token keyword\">SELECT<\/span> <span class=\"token function\">COUNT<\/span><span class=\"token punctuation\">(<\/span><span class=\"token operator\">*<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">FROM<\/span> newspaper_issues <span class=\"token keyword\">WHERE<\/span> publish_date <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#039;&#039;<\/span><span class=\"token punctuation\">;<\/span><br \/>\n<span class=\"token keyword\">SELECT<\/span> <span class=\"token function\">COUNT<\/span><span class=\"token punctuation\">(<\/span><span class=\"token operator\">*<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">FROM<\/span> newspaper_issues <span class=\"token keyword\">WHERE<\/span> digitization_status <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#039;\u672a\u77e5&#039;<\/span><span class=\"token punctuation\">;<\/span><\/p>\n<p>\u5982\u679c\u7a7a\u5b57\u6bb5\u6bd4\u4f8b\u5f88\u9ad8&#xff0c;\u8bf4\u660e\u9009\u62e9\u5668\u53ef\u80fd\u4e0d\u7a33\u5b9a\u3002<\/p>\n<h4>19.2 \u68c0\u67e5\u65e5\u671f\u8303\u56f4<\/h4>\n<p><span class=\"token keyword\">SELECT<\/span> <span class=\"token function\">MIN<\/span><span class=\"token punctuation\">(<\/span>publish_date<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token function\">MAX<\/span><span class=\"token punctuation\">(<\/span>publish_date<span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">FROM<\/span> newspaper_issues<span class=\"token punctuation\">;<\/span><\/p>\n<p>\u5982\u679c\u4f60\u672c\u6765\u53ea\u6293 2024 \u5e74&#xff0c;\u7ed3\u679c\u51fa\u73b0 1970 \u6216\u7a7a\u65e5\u671f&#xff0c;\u5c31\u8981\u68c0\u67e5\u6e05\u6d17\u903b\u8f91\u3002<\/p>\n<h4>19.3 \u68c0\u67e5\u91cd\u590d\u4e3b\u9898<\/h4>\n<p><span class=\"token keyword\">SELECT<\/span> publish_date<span class=\"token punctuation\">,<\/span> topic<span class=\"token punctuation\">,<\/span> <span class=\"token function\">COUNT<\/span><span class=\"token punctuation\">(<\/span><span class=\"token operator\">*<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">AS<\/span> cnt<br \/>\n<span class=\"token keyword\">FROM<\/span> newspaper_issues<br \/>\n<span class=\"token keyword\">GROUP<\/span> <span class=\"token keyword\">BY<\/span> publish_date<span class=\"token punctuation\">,<\/span> topic<br \/>\n<span class=\"token keyword\">HAVING<\/span> cnt <span class=\"token operator\">&gt;<\/span> <span class=\"token number\">1<\/span><br \/>\n<span class=\"token keyword\">ORDER<\/span> <span class=\"token keyword\">BY<\/span> cnt <span class=\"token keyword\">DESC<\/span><span class=\"token punctuation\">;<\/span><\/p>\n<p>\u91cd\u590d\u4e0d\u4e00\u5b9a\u662f\u9519&#xff0c;\u4f46\u503c\u5f97\u770b\u4e00\u773c\u3002<\/p>\n<h4>19.4 \u68c0\u67e5\u72b6\u6001\u5206\u5e03<\/h4>\n<p><span class=\"token keyword\">SELECT<\/span> digitization_status<span class=\"token punctuation\">,<\/span> <span class=\"token function\">COUNT<\/span><span class=\"token punctuation\">(<\/span><span class=\"token operator\">*<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">AS<\/span> cnt<br \/>\n<span class=\"token keyword\">FROM<\/span> newspaper_issues<br \/>\n<span class=\"token keyword\">GROUP<\/span> <span class=\"token keyword\">BY<\/span> digitization_status<br \/>\n<span class=\"token keyword\">ORDER<\/span> <span class=\"token keyword\">BY<\/span> cnt <span class=\"token keyword\">DESC<\/span><span class=\"token punctuation\">;<\/span><\/p>\n<p>\u5982\u679c\u5168\u90e8\u90fd\u662f\u201c\u672a\u77e5\u201d&#xff0c;\u5927\u6982\u7387\u662f\u72b6\u6001\u5b57\u6bb5\u6ca1\u6709\u89e3\u6790\u5230\u3002<\/p>\n<hr \/>\n<h3>20. MySQL \u5b58\u50a8\u6269\u5c55\u793a\u4f8b<\/h3>\n<p>\u5982\u679c\u540e\u7eed\u6570\u636e\u91cf\u53d8\u5927&#xff0c;SQLite \u53ef\u4ee5\u8fc1\u79fb\u5230 MySQL\u3002\u8868\u7ed3\u6784\u53ef\u4ee5\u8fd9\u6837\u8bbe\u8ba1&#xff1a;<\/p>\n<p><span class=\"token keyword\">CREATE<\/span> <span class=\"token keyword\">TABLE<\/span> newspaper_issues <span class=\"token punctuation\">(<\/span><br \/>\n    id <span class=\"token keyword\">BIGINT<\/span> <span class=\"token keyword\">PRIMARY<\/span> <span class=\"token keyword\">KEY<\/span> <span class=\"token keyword\">AUTO_INCREMENT<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    newspaper_name <span class=\"token keyword\">VARCHAR<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">255<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">NOT<\/span> <span class=\"token boolean\">NULL<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    issue_no <span class=\"token keyword\">VARCHAR<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">100<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    publish_date <span class=\"token keyword\">DATE<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    column_name <span class=\"token keyword\">VARCHAR<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">255<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    topic <span class=\"token keyword\">VARCHAR<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">500<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    digitization_status <span class=\"token keyword\">VARCHAR<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">100<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    url <span class=\"token keyword\">VARCHAR<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">1000<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">NOT<\/span> <span class=\"token boolean\">NULL<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    content_hash <span class=\"token keyword\">CHAR<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">32<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    created_at <span class=\"token keyword\">DATETIME<\/span> <span class=\"token operator\">NOT<\/span> <span class=\"token boolean\">NULL<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    updated_at <span class=\"token keyword\">DATETIME<\/span> <span class=\"token operator\">NOT<\/span> <span class=\"token boolean\">NULL<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token keyword\">UNIQUE<\/span> <span class=\"token keyword\">KEY<\/span> uk_url <span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token keyword\">KEY<\/span> idx_publish_date <span class=\"token punctuation\">(<\/span>publish_date<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token keyword\">KEY<\/span> idx_issue_no <span class=\"token punctuation\">(<\/span>issue_no<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token keyword\">KEY<\/span> idx_column_name <span class=\"token punctuation\">(<\/span>column_name<span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">ENGINE<\/span><span class=\"token operator\">&#061;<\/span><span class=\"token keyword\">InnoDB<\/span> <span class=\"token keyword\">DEFAULT<\/span> <span class=\"token keyword\">CHARSET<\/span><span class=\"token operator\">&#061;<\/span>utf8mb4<span class=\"token punctuation\">;<\/span><\/p>\n<p>Python \u5199\u5165\u53ef\u4ee5\u4f7f\u7528 pymysql&#xff1a;<\/p>\n<p>pip <span class=\"token function\">install<\/span> pymysql<\/p>\n<p>\u793a\u4f8b&#xff1a;<\/p>\n<p><span class=\"token keyword\">import<\/span> pymysql<\/p>\n<p>conn <span class=\"token operator\">&#061;<\/span> pymysql<span class=\"token punctuation\">.<\/span>connect<span class=\"token punctuation\">(<\/span><br \/>\n    host<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;127.0.0.1&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    port<span class=\"token operator\">&#061;<\/span><span class=\"token number\">3306<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    user<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;root&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    password<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;your_password&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    database<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;crawler_db&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    charset<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;utf8mb4&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">with<\/span> conn<span class=\"token punctuation\">.<\/span>cursor<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">as<\/span> cursor<span class=\"token punctuation\">:<\/span><br \/>\n    cursor<span class=\"token punctuation\">.<\/span>execute<span class=\"token punctuation\">(<\/span><span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n    INSERT INTO newspaper_issues (<br \/>\n        newspaper_name,<br \/>\n        issue_no,<br \/>\n        publish_date,<br \/>\n        column_name,<br \/>\n        topic,<br \/>\n        digitization_status,<br \/>\n        url,<br \/>\n        content_hash,<br \/>\n        created_at,<br \/>\n        updated_at<br \/>\n    )<br \/>\n    VALUES (%s, %s, %s, %s, %s, %s, %s, %s, NOW(), NOW())<br \/>\n    ON DUPLICATE KEY UPDATE<br \/>\n        newspaper_name&#061;VALUES(newspaper_name),<br \/>\n        issue_no&#061;VALUES(issue_no),<br \/>\n        publish_date&#061;VALUES(publish_date),<br \/>\n        column_name&#061;VALUES(column_name),<br \/>\n        topic&#061;VALUES(topic),<br \/>\n        digitization_status&#061;VALUES(digitization_status),<br \/>\n        content_hash&#061;VALUES(content_hash),<br \/>\n        updated_at&#061;NOW()<br \/>\n    &#034;&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">(<\/span><br \/>\n        item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;newspaper_name&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;issue_no&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;publish_date&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;column_name&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;topic&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;digitization_status&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;url&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;content_hash&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\nconn<span class=\"token punctuation\">.<\/span>commit<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u4e0d\u8fc7\u5bf9\u4e8e\u672c\u6587\u8fd9\u79cd\u7d22\u5f15\u5e73\u53f0\u5165\u95e8\u9879\u76ee&#xff0c;SQLite \u5df2\u7ecf\u8db3\u591f\u3002\u5148\u628a\u91c7\u96c6\u94fe\u8def\u6253\u901a&#xff0c;\u6bd4\u4e00\u5f00\u59cb\u5c31\u642d\u6570\u636e\u5e93\u670d\u52a1\u66f4\u5b9e\u9645\u3002<\/p>\n<hr \/>\n<h3>21. \u9009\u62e9\u5668\u7a33\u5b9a\u6027\u5efa\u8bae<\/h3>\n<p>\u771f\u5b9e\u7ad9\u70b9\u6539\u7248\u662f\u5e38\u6001\u3002\u9009\u62e9\u5668\u5199\u5f97\u592a\u6b7b&#xff0c;\u540e\u9762\u7ef4\u62a4\u4f1a\u5f88\u75db\u82e6\u3002<\/p>\n<h4>21.1 \u4e0d\u5efa\u8bae\u7684\u5199\u6cd5<\/h4>\n<p>soup<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;body &gt; div:nth-child(3) &gt; div:nth-child(2) &gt; ul &gt; li:nth-child(1) &gt; a&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u8fd9\u79cd\u9009\u62e9\u5668\u6781\u5176\u8106\u5f31&#xff0c;\u9875\u9762\u591a\u4e00\u4e2a\u5e7f\u544a\u4f4d\u5c31\u4f1a\u5931\u6548\u3002<\/p>\n<h4>21.2 \u63a8\u8350\u5199\u6cd5<\/h4>\n<p>\u4f18\u5148\u627e\u8bed\u4e49\u7c7b\u540d&#xff1a;<\/p>\n<p>soup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.issue-list .issue-item&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\nsoup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;a.detail-link&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\nsoup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.publish-date&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u5982\u679c\u6ca1\u6709\u7c7b\u540d&#xff0c;\u53ef\u4ee5\u7ed3\u5408\u6587\u672c&#xff1a;<\/p>\n<p><span class=\"token keyword\">for<\/span> li <span class=\"token keyword\">in<\/span> soup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;li&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    text <span class=\"token operator\">&#061;<\/span> li<span class=\"token punctuation\">.<\/span>get_text<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034; &#034;<\/span><span class=\"token punctuation\">,<\/span> strip<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">if<\/span> <span class=\"token string\">&#034;\u51fa\u7248\u65e5\u671f&#034;<\/span> <span class=\"token keyword\">in<\/span> text<span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token punctuation\">.<\/span><span class=\"token punctuation\">.<\/span><span class=\"token punctuation\">.<\/span><\/p>\n<h4>21.3 \u591a\u9009\u62e9\u5668\u515c\u5e95<\/h4>\n<p>\u53ef\u4ee5\u5199\u4e00\u4e2a\u515c\u5e95\u51fd\u6570&#xff1a;<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">first_text<\/span><span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">,<\/span> selectors<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">for<\/span> selector <span class=\"token keyword\">in<\/span> selectors<span class=\"token punctuation\">:<\/span><br \/>\n        node <span class=\"token operator\">&#061;<\/span> soup<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span>selector<span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> node<span class=\"token punctuation\">:<\/span><br \/>\n            text <span class=\"token operator\">&#061;<\/span> node<span class=\"token punctuation\">.<\/span>get_text<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034; &#034;<\/span><span class=\"token punctuation\">,<\/span> strip<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> text<span class=\"token punctuation\">:<\/span><br \/>\n                <span class=\"token keyword\">return<\/span> text<br \/>\n    <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;&#034;<\/span><\/p>\n<p>\u4f7f\u7528&#xff1a;<\/p>\n<p>topic <span class=\"token operator\">&#061;<\/span> first_text<span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">[<\/span><br \/>\n    <span class=\"token string\">&#034;h1.topic&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;.article-title&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;.detail-title&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;h1&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u8fd9\u79cd\u65b9\u5f0f\u5728\u7ad9\u70b9\u5c0f\u6539\u7248\u65f6\u5f88\u6709\u7528\u3002<\/p>\n<hr \/>\n<h3>22. \u8bf7\u6c42\u5931\u8d25 URL \u7684\u8865\u6293<\/h3>\n<p>\u957f\u671f\u91c7\u96c6\u65f6&#xff0c;\u4e0d\u8981\u8ba9\u5931\u8d25 URL \u6d88\u5931\u5728\u65e5\u5fd7\u91cc\u3002\u53ef\u4ee5\u5199\u5165\u6587\u4ef6&#xff1a;<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">append_failed_url<\/span><span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> reason<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">with<\/span> <span class=\"token builtin\">open<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;data\/failed_urls.csv&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;a&#034;<\/span><span class=\"token punctuation\">,<\/span> encoding<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;utf-8-sig&#034;<\/span><span class=\"token punctuation\">,<\/span> newline<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">as<\/span> f<span class=\"token punctuation\">:<\/span><br \/>\n        writer <span class=\"token operator\">&#061;<\/span> csv<span class=\"token punctuation\">.<\/span>writer<span class=\"token punctuation\">(<\/span>f<span class=\"token punctuation\">)<\/span><br \/>\n        writer<span class=\"token punctuation\">.<\/span>writerow<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><br \/>\n            datetime<span class=\"token punctuation\">.<\/span>now<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strftime<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;%Y-%m-%d %H:%M:%S&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            url<span class=\"token punctuation\">,<\/span><br \/>\n            reason<span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u8bf7\u6c42\u5931\u8d25\u65f6&#xff1a;<\/p>\n<p>append_failed_url<span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;timeout&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u540e\u7eed\u53ef\u4ee5\u5355\u72ec\u8865\u6293&#xff1a;<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">load_failed_urls<\/span><span class=\"token punctuation\">(<\/span>path<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    urls <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n    <span class=\"token keyword\">with<\/span> <span class=\"token builtin\">open<\/span><span class=\"token punctuation\">(<\/span>path<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;r&#034;<\/span><span class=\"token punctuation\">,<\/span> encoding<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;utf-8-sig&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">as<\/span> f<span class=\"token punctuation\">:<\/span><br \/>\n        reader <span class=\"token operator\">&#061;<\/span> csv<span class=\"token punctuation\">.<\/span>reader<span class=\"token punctuation\">(<\/span>f<span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">for<\/span> row <span class=\"token keyword\">in<\/span> reader<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>row<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&gt;&#061;<\/span> <span class=\"token number\">2<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                urls<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span>row<span class=\"token punctuation\">[<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">return<\/span> urls<\/p>\n<p>\u8fd9\u6bd4\u201c\u5931\u8d25\u4e86\u5c31\u7b97\u4e86\u201d\u9760\u8c31\u5f88\u591a\u3002<\/p>\n<hr \/>\n<h3>23. \u9762\u5411\u771f\u5b9e\u4e1a\u52a1\u7684\u91c7\u96c6\u8fb9\u754c<\/h3>\n<p>\u62a5\u520a\u5386\u53f2\u7d22\u5f15\u722c\u866b\u5f88\u5bb9\u6613\u88ab\u8bef\u89e3\u6210\u201c\u6211\u8981\u628a\u6240\u6709\u5185\u5bb9\u90fd\u642c\u4e0b\u6765\u201d\u3002\u4f46\u5728\u5b9e\u9645\u9879\u76ee\u91cc&#xff0c;\u6211\u66f4\u5efa\u8bae\u628a\u5b83\u5b9a\u4f4d\u4e3a\u201c\u7d22\u5f15\u6574\u7406\u5de5\u5177\u201d\u3002<\/p>\n<p>\u5408\u7406\u91c7\u96c6&#xff1a;<\/p>\n<p>\u516c\u5f00\u76ee\u5f55<br \/>\n\u516c\u5f00\u65e5\u671f<br \/>\n\u516c\u5f00\u671f\u53f7<br \/>\n\u516c\u5f00\u680f\u76ee<br \/>\n\u516c\u5f00\u6807\u9898<br \/>\n\u516c\u5f00\u8be6\u60c5\u94fe\u63a5<br \/>\n\u516c\u5f00\u6570\u5b57\u5316\u72b6\u6001<\/p>\n<p>\u8c28\u614e\u5904\u7406&#xff1a;<\/p>\n<p>\u6b63\u6587\u5168\u6587<br \/>\n\u56fe\u7247\u7248\u9762<br \/>\nPDF \u6587\u4ef6<br \/>\n\u9700\u8981\u767b\u5f55\u540e\u7684\u5185\u5bb9<br \/>\n\u9700\u8981\u6388\u6743\u7684\u6570\u636e\u5e93\u5185\u5bb9<\/p>\n<p>\u4e0d\u5efa\u8bae\u5904\u7406&#xff1a;<\/p>\n<p>\u8d26\u53f7\u76f8\u5173\u6570\u636e<br \/>\n\u4e2a\u4eba\u654f\u611f\u4fe1\u606f<br \/>\n\u540e\u53f0\u63a5\u53e3<br \/>\n\u7ed5\u8fc7\u8bbf\u95ee\u9650\u5236\u7684\u5185\u5bb9<\/p>\n<p>\u8fd9\u7c7b\u8fb9\u754c\u5199\u6e05\u695a&#xff0c;\u9879\u76ee\u4f1a\u66f4\u5065\u5eb7&#xff0c;\u4e5f\u66f4\u5bb9\u6613\u957f\u671f\u7ef4\u62a4\u3002<\/p>\n<hr \/>\n<h3>24. \u603b\u7ed3\u4e0e\u5ef6\u4f38\u9605\u8bfb<\/h3>\n<p>\u672c\u6587\u5b8c\u6210\u4e86\u4e00\u4e2a\u201c\u62a5\u520a\u5386\u53f2\u671f\u53f7\u7d22\u5f15\u5e73\u53f0\u201d\u7684\u722c\u866b\u65b9\u6848\u8bbe\u8ba1\u548c\u4ee3\u7801\u5b9e\u73b0\u3002\u6211\u4eec\u4ece\u9700\u6c42\u5206\u6790\u5f00\u59cb&#xff0c;\u660e\u786e\u4e86\u76ee\u6807\u5b57\u6bb5&#xff0c;\u7136\u540e\u8ba8\u8bba\u4e86\u5408\u89c4\u8981\u6c42\u3001\u6280\u672f\u9009\u578b\u3001\u8bf7\u6c42\u5c42\u3001\u89e3\u6790\u5c42\u3001\u5b58\u50a8\u5c42\u3001\u8fd0\u884c\u65b9\u5f0f\u548c\u5e38\u89c1\u6392\u9519\u3002\u6700\u540e\u7ed9\u51fa\u4e86\u4e00\u4efd\u53ef\u4ee5\u76f4\u63a5\u8fd0\u884c\u7684 Python \u793a\u4f8b\u4ee3\u7801&#xff0c;\u6a21\u62df\u4e86\u5e74\u6708\u671f\u53f7\u7ea7\u8054\u3001\u52a8\u6001\u65e5\u5386\u5165\u53e3\u3001\u5386\u53f2\u5206\u9875\u89e3\u6790\u548c\u8be6\u60c5\u9875\u5b57\u6bb5\u62bd\u53d6\u3002<\/p>\n<p>\u8fd9\u5957\u65b9\u6848\u7684\u6838\u5fc3\u4e0d\u662f\u67d0\u4e2a\u9009\u62e9\u5668&#xff0c;\u4e5f\u4e0d\u662f\u67d0\u4e2a\u5e93&#xff0c;\u800c\u662f\u7ed3\u6784\u5316\u601d\u7ef4&#xff1a;<\/p>\n<p>\u5148\u786e\u5b9a\u5c42\u7ea7<br \/>\n\u518d\u5904\u7406\u8bf7\u6c42<br \/>\n\u518d\u62bd\u53d6\u5b57\u6bb5<br \/>\n\u518d\u6e05\u6d17\u5165\u5e93<br \/>\n\u6700\u540e\u505a\u589e\u91cf\u548c\u76d1\u63a7<\/p>\n<p>\u4e0b\u4e00\u6b65\u53ef\u4ee5\u7ee7\u7eed\u505a\u8fd9\u4e9b\u4f18\u5316&#xff1a;<\/p>\n<li>\u7528 Scrapy \u91cd\u6784\u9879\u76ee&#xff0c;\u652f\u6301\u591a\u7ad9\u70b9\u91c7\u96c6\u3002<\/li>\n<li>\u63a5\u5165 Playwright&#xff0c;\u5904\u7406\u5f3a\u52a8\u6001\u6e32\u67d3\u9875\u9762\u3002<\/li>\n<li>\u589e\u52a0\u65ad\u70b9\u7eed\u8dd1\u548c\u5931\u8d25\u8865\u6293\u3002<\/li>\n<li>\u52a0\u5165\u5b57\u6bb5\u8d28\u91cf\u62a5\u544a&#xff0c;\u6bd4\u5982\u7a7a\u5b57\u6bb5\u7387\u3001\u72b6\u6001\u5206\u5e03\u3001\u65e5\u671f\u8986\u76d6\u8303\u56f4\u3002<\/li>\n<li>\u505a\u4e00\u4e2a\u7b80\u5355\u7684\u68c0\u7d22\u524d\u7aef&#xff0c;\u628a SQLite \u6570\u636e\u5c55\u793a\u6210\u53ef\u641c\u7d22\u9875\u9762\u3002<\/li>\n<li>\u5c06 CSV \u5bfc\u5165\u5206\u6790\u5de5\u5177&#xff0c;\u7edf\u8ba1\u4e0d\u540c\u5e74\u4efd\u3001\u4e0d\u540c\u680f\u76ee\u548c\u4e0d\u540c\u4e3b\u9898\u7684\u53d8\u5316\u8d8b\u52bf\u3002<\/li>\n<p>\u6211\u4e00\u76f4\u89c9\u5f97&#xff0c;\u722c\u866b\u5199\u5230\u540e\u9762\u6bd4\u7684\u4e0d\u662f\u8c01\u80fd\u66f4\u5feb\u5730\u8bf7\u6c42\u9875\u9762&#xff0c;\u800c\u662f\u8c01\u80fd\u66f4\u7a33\u5730\u628a\u6570\u636e\u53d8\u6210\u53ef\u4ee5\u957f\u671f\u4f7f\u7528\u7684\u8d44\u4ea7\u3002\u62a5\u520a\u5386\u53f2\u7d22\u5f15\u8fd9\u79cd\u573a\u666f\u5c24\u5176\u5982\u6b64\u3002\u5b83\u770b\u8d77\u6765\u6734\u7d20&#xff0c;\u4f46\u4e00\u65e6\u7ed3\u6784\u5316\u5b8c\u6210&#xff0c;\u540e\u7eed\u68c0\u7d22\u3001\u5206\u6790\u3001\u5f52\u6863\u90fd\u4f1a\u8f7b\u677e\u5f88\u591a\u3002\u6280\u672f\u6700\u7ec8\u8fd8\u662f\u8981\u843d\u5230\u53ef\u7ef4\u62a4\u3001\u53ef\u590d\u67e5\u3001\u53ef\u590d\u7528\u4e0a&#xff0c;\u8fd9\u4e5f\u662f\u8fd9\u7c7b\u9879\u76ee\u6700\u6709\u4ef7\u503c\u7684\u5730\u65b9\u3002<\/p>\n<h3>&#x1f31f; \u6587\u672b<\/h3>\n<p>\u597d\u5566&#xff5e;\u4ee5\u4e0a\u5c31\u662f\u672c\u671f\u7684\u5168\u90e8\u5185\u5bb9\u5566&#xff01;\u5982\u679c\u4f60\u5728\u5b9e\u8df5\u8fc7\u7a0b\u4e2d\u9047\u5230\u4efb\u4f55\u7591\u95ee&#xff0c;\u6b22\u8fce\u5728\u8bc4\u8bba\u533a\u7559\u8a00\u4ea4\u6d41&#xff0c;\u6211\u770b\u5230\u90fd\u4f1a\u5c3d\u91cf\u56de\u590d&#xff5e;\u54b1\u4eec\u4e0b\u671f\u89c1&#xff01;<\/p>\n<p>\u5c0f\u4f19\u4f34\u4eec\u5728\u6279\u9605\u7684\u8fc7\u7a0b\u4e2d&#xff0c;\u5982\u679c\u89c9\u5f97\u6587\u7ae0\u4e0d\u9519&#xff0c;\u6b22\u8fce\u70b9\u8d5e\u3001\u6536\u85cf\u3001\u5173\u6ce8\u54e6&#xff5e; \u4e09\u8fde\u5c31\u662f\u5bf9\u6211\u5199\u4f5c\u9053\u8def\u4e0a\u6700\u597d\u7684\u9f13\u52b1\u4e0e\u652f\u6301&#xff01; \u2764\ufe0f&#x1f525;<\/p>\n<h4>\u2705 \u4e13\u680f\u6301\u7eed\u66f4\u65b0\u4e2d&#xff5c;\u5efa\u8bae\u6536\u85cf &#043; \u8ba2\u9605<\/h4>\n<p>\u5899\u88c2\u63a8\u8350\u8ba2\u9605\u4e13\u680f &#x1f449; \u300aPython\u722c\u866b\u5b9e\u6218\u300b&#xff0c;\u672c\u4e13\u680f\u79c9\u627f\u7740\u4ee5\u201c\u5165\u95e8 \u2192 \u8fdb\u9636 \u2192 \u5de5\u7a0b\u5316 \u2192 \u9879\u76ee\u843d\u5730\u201d\u7684\u8def\u7ebf\u6301\u7eed\u66f4\u65b0&#xff0c;\u4e89\u53d6\u8ba9\u6bcf\u4e00\u671f\u5185\u5bb9\u90fd\u505a\u5230&#xff1a;<\/p>\n<p>\u2705 \u8bb2\u5f97\u6e05\u695a&#xff08;\u539f\u7406&#xff09;&#xff5c;\u2705 \u8dd1\u5f97\u8d77\u6765&#xff08;\u4ee3\u7801&#xff09;&#xff5c;\u2705 \u7528\u5f97\u4e0a&#xff08;\u573a\u666f&#xff09;&#xff5c;\u2705 \u625b\u5f97\u4f4f&#xff08;\u5de5\u7a0b\u5316&#xff09;<\/p>\n<p>&#x1f4e3; \u60f3\u7cfb\u7edf\u63d0\u5347\u7684\u5c0f\u4f19\u4f34&#xff1a;\u5f3a\u70c8\u5efa\u8bae\u5148\u8ba2\u9605\u4e13\u680f \u300aPython\u722c\u866b\u5b9e\u6218\u300b&#xff0c;\u518d\u6309\u76ee\u5f55\u5927\u7eb2\u987a\u5e8f\u5b66\u4e60&#xff0c;\u6548\u7387\u5341\u500d\u4e0a\u5347&#xff5e;<\/p>\n<p> <img decoding=\"async\" width=\"1000\" src=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/09\/20260929005652-6abb0cd4c998d.png\" \/> <\/p>\n<h4>\u2705 \u4e92\u52a8\u5f81\u96c6<\/h4>\n<p>\u60f3\u8ba9\u6211\u628a\u3010\u67d0\u7ad9\u70b9\/\u67d0\u53cd\u722c\/\u67d0\u9a8c\u8bc1\u7801\/\u67d0\u5206\u5e03\u5f0f\u65b9\u6848\u3011\u7b49\u5199\u6210\u67d0\u671f\u5b9e\u6218&#xff1f;<\/p>\n<p>\u8bc4\u8bba\u533a\u7559\u8a00\u544a\u8bc9\u6211\u4f60\u7684\u9700\u6c42&#xff0c;\u6211\u4f1a\u4f18\u5148\u5b89\u6392\u5b9e\u73b0(\u66f4\u65b0)\u54d2~<\/p>\n<hr \/>\n<p>\u2b50\ufe0f \u82e5\u559c\u6b22\u6211&#xff0c;\u5c31\u8bf7\u5173\u6ce8\u6211\u53ed&#xff5e;&#xff08;\u66f4\u65b0\u4e0d\u8ff7\u8def&#xff09; \u2b50\ufe0f \u82e5\u5bf9\u4f60\u6709\u7528&#xff0c;\u5c31\u8bf7\u70b9\u8d5e\u652f\u6301\u4e00\u4e0b\u53ed&#xff5e;&#xff08;\u7ed9\u6211\u4e00\u70b9\u70b9\u52a8\u529b&#xff09; \u2b50\ufe0f \u82e5\u6709\u7591\u95ee&#xff0c;\u5c31\u8bf7\u8bc4\u8bba\u7559\u8a00\u544a\u8bc9\u6211\u53ed&#xff5e;&#xff08;\u6211\u4f1a\u8865\u5751 &amp; \u66f4\u65b0\u8fed\u4ee3&#xff09;<\/p>\n<hr \/>\n<h4>\u2705 \u514d\u8d23\u58f0\u660e<\/h4>\n<p><font color=\"red\"> \u672c\u6587\u722c\u866b\u601d\u8def\u3001\u76f8\u5173\u6280\u672f\u548c\u4ee3\u7801\u4ec5\u7528\u4e8e\u5b66\u4e60\u53c2\u8003&#xff0c;\u5bf9\u9605\u8bfb\u672c\u6587\u540e\u7684\u8fdb\u884c\u722c\u866b\u884c\u4e3a\u7684\u7528\u6237\u672c\u4f5c\u8005\u4e0d\u627f\u62c5\u4efb\u4f55\u6cd5\u5f8b\u8d23\u4efb\u3002<\/font><\/p>\n<p>\u4f7f\u7528\u6216\u8005\u53c2\u8003\u672c\u9879\u76ee\u5373\u8868\u793a\u60a8\u5df2\u9605\u8bfb\u5e76\u540c\u610f\u4ee5\u4e0b\u6761\u6b3e&#xff1a;<\/p>\n<ul>\n<li>\u5408\u6cd5\u4f7f\u7528&#xff1a; \u4e0d\u5f97\u5c06\u672c\u9879\u76ee\u7528\u4e8e\u4efb\u4f55\u8fdd\u6cd5\u3001\u8fdd\u89c4\u6216\u4fb5\u72af\u4ed6\u4eba\u6743\u76ca\u7684\u884c\u4e3a&#xff0c;\u5305\u62ec\u4f46\u4e0d\u9650\u4e8e\u7f51\u7edc\u653b\u51fb\u3001\u8bc8\u9a97\u3001\u7ed5\u8fc7\u8eab\u4efd\u9a8c\u8bc1\u3001\u672a\u7ecf\u6388\u6743\u7684\u6570\u636e\u6293\u53d6\u7b49\u3002<\/li>\n<li>\u98ce\u9669\u81ea\u8d1f&#xff1a; \u4efb\u4f55\u56e0\u4f7f\u7528\u672c\u9879\u76ee\u800c\u4ea7\u751f\u7684\u6cd5\u5f8b\u8d23\u4efb\u3001\u6280\u672f\u98ce\u9669\u6216\u7ecf\u6d4e\u635f\u5931&#xff0c;\u7531\u4f7f\u7528\u8005\u81ea\u884c\u627f\u62c5&#xff0c;\u9879\u76ee\u4f5c\u8005\u4e0d\u627f\u62c5\u4efb\u4f55\u5f62\u5f0f\u7684\u8d23\u4efb\u3002<\/li>\n<li>\u7981\u6b62\u6ee5\u7528&#xff1a; \u4e0d\u5f97\u5c06\u672c\u9879\u76ee\u7528\u4e8e\u8fdd\u6cd5\u725f\u5229\u3001\u9ed1\u4ea7\u6d3b\u52a8\u6216\u5176\u4ed6\u4e0d\u5f53\u5546\u4e1a\u7528\u9014\u3002<\/li>\n<li>\u4f7f\u7528\u6216\u8005\u53c2\u8003\u672c\u9879\u76ee\u5373\u89c6\u4e3a\u540c\u610f\u4e0a\u8ff0\u6761\u6b3e,\u5373 \u201c\u8c01\u4f7f\u7528&#xff0c;\u8c01\u8d1f\u8d23\u201d \u3002\u5982\u4e0d\u540c\u610f&#xff0c;\u8bf7\u7acb\u5373\u505c\u6b62\u4f7f\u7528\u5e76\u5220\u9664\u672c\u9879\u76ee\u3002&#xff01;&#xff01;&#xff01;<\/li>\n<\/ul>\n<p> <img decoding=\"async\" width=\"1000\" src=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/09\/20260929005652-6abb0cd4eb539.jpg\" \/> <\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u3297\ufe0f\u672c\u671f\u5185\u5bb9\u5df2\u6536\u5f55\u81f3\u4e13\u680f\u300aPython\u722c\u866b\u5b9e\u6218\u300b&#xff0c;\u6301\u7eed\u5b8c\u5584\u77e5\u8bc6\u4f53\u7cfb\u4e0e\u9879\u76ee\u5b9e\u6218&#xff0c;\u5efa\u8bae\u5148\u8ba2\u9605\u6536\u85cf&#xff0c;\u540e\u7eed\u67e5\u9605\u66f4\u65b9\u4fbf&#xff5e; \u3299\ufe0f\u672c\u671f\u722c\u866b\u96be\u5ea6\u6307\u6570&#xff1a;\u2b50\u2b50\u2b50\u2b50\u2606&#xff08;\u9ad8\u7ea7&#xff09; &#x1f250;\u798f\u5229&#xff1a; \u4e00\u6b21\u8ba2\u9605\u540e&#xff0c;\u4e13\u680f\u5185\u7684\u6240\u6709\u6587\u7ae0\u53ef\u6c38\u4e45\u514d\u8d39\u770b&#xff0c;\u6301\u7eed\u66f4\u65b0\u4e2d&#xff0c;\u4fdd\u5e951000(\u7bc7)\u786c\u6838\u5b9e\u6218\u5185\u5bb9\u3002 \u5168\u6587\u76ee\u5f55&#xff1a;&#x1f31f; \u5f00\u7bc7\u8bed0\ufe0f\u20e3 <\/p>\n","protected":false},"author":2,"featured_media":110692,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[12614,11815,11229,11228,81,677],"topic":[],"class_list":["post-110695","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-server","tag-12614","tag-11815","tag-11229","tag-python","tag-677"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v20.3 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>\u62a5\u520a\u5386\u53f2\u671f\u53f7\u7d22\u5f15\u5e73\u53f0\u722c\u866b\u5b9e\u6218\uff1a\u5e74\u6708\u671f\u53f7\u7ea7\u8054\u3001\u52a8\u6001\u65e5\u5386\u4e0e\u5386\u53f2\u5206\u9875\u89e3\u6790 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.wsisp.com\/helps\/110695.html\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u62a5\u520a\u5386\u53f2\u671f\u53f7\u7d22\u5f15\u5e73\u53f0\u722c\u866b\u5b9e\u6218\uff1a\u5e74\u6708\u671f\u53f7\u7ea7\u8054\u3001\u52a8\u6001\u65e5\u5386\u4e0e\u5386\u53f2\u5206\u9875\u89e3\u6790 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"og:description\" content=\"\u3297\ufe0f\u672c\u671f\u5185\u5bb9\u5df2\u6536\u5f55\u81f3\u4e13\u680f\u300aPython\u722c\u866b\u5b9e\u6218\u300b&#xff0c;\u6301\u7eed\u5b8c\u5584\u77e5\u8bc6\u4f53\u7cfb\u4e0e\u9879\u76ee\u5b9e\u6218&#xff0c;\u5efa\u8bae\u5148\u8ba2\u9605\u6536\u85cf&#xff0c;\u540e\u7eed\u67e5\u9605\u66f4\u65b9\u4fbf&#xff5e; \u3299\ufe0f\u672c\u671f\u722c\u866b\u96be\u5ea6\u6307\u6570&#xff1a;\u2b50\u2b50\u2b50\u2b50\u2606&#xff08;\u9ad8\u7ea7&#xff09; &#x1f250;\u798f\u5229&#xff1a; \u4e00\u6b21\u8ba2\u9605\u540e&#xff0c;\u4e13\u680f\u5185\u7684\u6240\u6709\u6587\u7ae0\u53ef\u6c38\u4e45\u514d\u8d39\u770b&#xff0c;\u6301\u7eed\u66f4\u65b0\u4e2d&#xff0c;\u4fdd\u5e951000(\u7bc7)\u786c\u6838\u5b9e\u6218\u5185\u5bb9\u3002 \u5168\u6587\u76ee\u5f55&#xff1a;&#x1f31f; \u5f00\u7bc7\u8bed0\ufe0f\u20e3\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wsisp.com\/helps\/110695.html\" \/>\n<meta property=\"og:site_name\" content=\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"article:published_time\" content=\"2026-09-29T00:56:58+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/09\/20260929005652-6abb0cd402c34.png\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"35 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/110695.html\",\"url\":\"https:\/\/www.wsisp.com\/helps\/110695.html\",\"name\":\"\u62a5\u520a\u5386\u53f2\u671f\u53f7\u7d22\u5f15\u5e73\u53f0\u722c\u866b\u5b9e\u6218\uff1a\u5e74\u6708\u671f\u53f7\u7ea7\u8054\u3001\u52a8\u6001\u65e5\u5386\u4e0e\u5386\u53f2\u5206\u9875\u89e3\u6790 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"isPartOf\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\"},\"datePublished\":\"2026-09-29T00:56:58+00:00\",\"dateModified\":\"2026-09-29T00:56:58+00:00\",\"author\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/110695.html#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.wsisp.com\/helps\/110695.html\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/110695.html#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.wsisp.com\/helps\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u62a5\u520a\u5386\u53f2\u671f\u53f7\u7d22\u5f15\u5e73\u53f0\u722c\u866b\u5b9e\u6218\uff1a\u5e74\u6708\u671f\u53f7\u7ea7\u8054\u3001\u52a8\u6001\u65e5\u5386\u4e0e\u5386\u53f2\u5206\u9875\u89e3\u6790\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\",\"url\":\"https:\/\/www.wsisp.com\/helps\/\",\"name\":\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"description\":\"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"contentUrl\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"caption\":\"admin\"},\"sameAs\":[\"http:\/\/wp.wsisp.com\"],\"url\":\"https:\/\/www.wsisp.com\/helps\/author\/admin\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"\u62a5\u520a\u5386\u53f2\u671f\u53f7\u7d22\u5f15\u5e73\u53f0\u722c\u866b\u5b9e\u6218\uff1a\u5e74\u6708\u671f\u53f7\u7ea7\u8054\u3001\u52a8\u6001\u65e5\u5386\u4e0e\u5386\u53f2\u5206\u9875\u89e3\u6790 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.wsisp.com\/helps\/110695.html","og_locale":"zh_CN","og_type":"article","og_title":"\u62a5\u520a\u5386\u53f2\u671f\u53f7\u7d22\u5f15\u5e73\u53f0\u722c\u866b\u5b9e\u6218\uff1a\u5e74\u6708\u671f\u53f7\u7ea7\u8054\u3001\u52a8\u6001\u65e5\u5386\u4e0e\u5386\u53f2\u5206\u9875\u89e3\u6790 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","og_description":"\u3297\ufe0f\u672c\u671f\u5185\u5bb9\u5df2\u6536\u5f55\u81f3\u4e13\u680f\u300aPython\u722c\u866b\u5b9e\u6218\u300b&#xff0c;\u6301\u7eed\u5b8c\u5584\u77e5\u8bc6\u4f53\u7cfb\u4e0e\u9879\u76ee\u5b9e\u6218&#xff0c;\u5efa\u8bae\u5148\u8ba2\u9605\u6536\u85cf&#xff0c;\u540e\u7eed\u67e5\u9605\u66f4\u65b9\u4fbf&#xff5e; \u3299\ufe0f\u672c\u671f\u722c\u866b\u96be\u5ea6\u6307\u6570&#xff1a;\u2b50\u2b50\u2b50\u2b50\u2606&#xff08;\u9ad8\u7ea7&#xff09; &#x1f250;\u798f\u5229&#xff1a; \u4e00\u6b21\u8ba2\u9605\u540e&#xff0c;\u4e13\u680f\u5185\u7684\u6240\u6709\u6587\u7ae0\u53ef\u6c38\u4e45\u514d\u8d39\u770b&#xff0c;\u6301\u7eed\u66f4\u65b0\u4e2d&#xff0c;\u4fdd\u5e951000(\u7bc7)\u786c\u6838\u5b9e\u6218\u5185\u5bb9\u3002 \u5168\u6587\u76ee\u5f55&#xff1a;&#x1f31f; \u5f00\u7bc7\u8bed0\ufe0f\u20e3","og_url":"https:\/\/www.wsisp.com\/helps\/110695.html","og_site_name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","article_published_time":"2026-09-29T00:56:58+00:00","og_image":[{"url":"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/09\/20260929005652-6abb0cd402c34.png"}],"author":"admin","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"admin","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"35 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wsisp.com\/helps\/110695.html","url":"https:\/\/www.wsisp.com\/helps\/110695.html","name":"\u62a5\u520a\u5386\u53f2\u671f\u53f7\u7d22\u5f15\u5e73\u53f0\u722c\u866b\u5b9e\u6218\uff1a\u5e74\u6708\u671f\u53f7\u7ea7\u8054\u3001\u52a8\u6001\u65e5\u5386\u4e0e\u5386\u53f2\u5206\u9875\u89e3\u6790 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","isPartOf":{"@id":"https:\/\/www.wsisp.com\/helps\/#website"},"datePublished":"2026-09-29T00:56:58+00:00","dateModified":"2026-09-29T00:56:58+00:00","author":{"@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41"},"breadcrumb":{"@id":"https:\/\/www.wsisp.com\/helps\/110695.html#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wsisp.com\/helps\/110695.html"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wsisp.com\/helps\/110695.html#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.wsisp.com\/helps"},{"@type":"ListItem","position":2,"name":"\u62a5\u520a\u5386\u53f2\u671f\u53f7\u7d22\u5f15\u5e73\u53f0\u722c\u866b\u5b9e\u6218\uff1a\u5e74\u6708\u671f\u53f7\u7ea7\u8054\u3001\u52a8\u6001\u65e5\u5386\u4e0e\u5386\u53f2\u5206\u9875\u89e3\u6790"}]},{"@type":"WebSite","@id":"https:\/\/www.wsisp.com\/helps\/#website","url":"https:\/\/www.wsisp.com\/helps\/","name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","description":"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41","name":"admin","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/","url":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","contentUrl":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","caption":"admin"},"sameAs":["http:\/\/wp.wsisp.com"],"url":"https:\/\/www.wsisp.com\/helps\/author\/admin"}]}},"_links":{"self":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/110695","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/comments?post=110695"}],"version-history":[{"count":0,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/110695\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media\/110692"}],"wp:attachment":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media?parent=110695"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/categories?post=110695"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/tags?post=110695"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/topic?post=110695"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}