{"id":97986,"date":"2026-08-30T21:42:08","date_gmt":"2026-08-30T13:42:08","guid":{"rendered":"https:\/\/www.wsisp.com\/helps\/97986.html"},"modified":"2026-08-30T21:42:08","modified_gmt":"2026-08-30T13:42:08","slug":"%e5%9c%a8%e7%ba%bf%e6%95%99%e8%82%b2%e5%b9%b3%e5%8f%b0%e5%85%ac%e5%bc%80%e7%9b%ae%e5%bd%95%e6%a0%91%e9%87%87%e9%9b%86%e5%ae%9e%e6%88%98%ef%bc%9a%e5%8a%a8%e6%80%81%e8%af%be%e7%a8%8b%e7%ab%a0%e8%8a%82","status":"publish","type":"post","link":"https:\/\/www.wsisp.com\/helps\/97986.html","title":{"rendered":"\u5728\u7ebf\u6559\u80b2\u5e73\u53f0\u516c\u5f00\u76ee\u5f55\u6811\u91c7\u96c6\u5b9e\u6218\uff1a\u52a8\u6001\u8bfe\u7a0b\u7ae0\u8282\u3001\u8bd5\u770b\u72b6\u6001\u3001\u65f6\u957f\u3001\u8bb2\u5e08\u4e0e\u6807\u7b7e\u89e3\u6790"},"content":{"rendered":"<p> <img decoding=\"async\" width=\"1000\" src=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/08\/20260830134202-6a94332a89e5c.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>\u4e3a\u4ec0\u4e48\u8981\u91c7\u96c6\u8bfe\u7a0b\u76ee\u5f55&#xff1f;<\/li>\n<li>\u76ee\u6807\u5b57\u6bb5<\/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\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\u4e0e API \u7684\u533a\u522b<\/li>\n<li>4.2 \u6574\u4f53\u6d41\u7a0b<\/li>\n<li>4.3 \u4e3a\u4ec0\u4e48\u9009\u62e9 requests<\/li>\n<li>4.4 \u4ec0\u4e48\u65f6\u5019\u7528 Playwright<\/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 \u5b89\u88c5\u4f9d\u8d56<\/li>\n<li>5.3 \u63a8\u8350\u9879\u76ee\u7ed3\u6784<\/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 \u914d\u7f6e\u6587\u4ef6<\/li>\n<li>6.2 \u793a\u4f8b JSON<\/li>\n<li>6.3 \u914d\u7f6e\u8bfb\u53d6<\/li>\n<li>6.4 \u5de5\u5177\u51fd\u6570<\/li>\n<li>6.5 Fetcher \u5b9e\u73b0<\/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 \u539f\u59cb JSON \u7ed3\u6784\u5206\u6790<\/li>\n<li>7.2 \u6570\u636e\u6a21\u578b<\/li>\n<li>7.3 \u89e3\u6790\u65b9\u5f0f\u8bf4\u660e<\/li>\n<li>7.4 \u5217\u8868\u9875\u5982\u4f55\u62ff\u8be6\u60c5\u94fe\u63a5<\/li>\n<li>7.5 \u8be6\u60c5\u9875\u5982\u4f55\u62bd\u5b57\u6bb5<\/li>\n<li>7.6 \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 \u5b57\u6bb5\u6620\u5c04\u8868<\/li>\n<li>8.2 Storage \u5b9e\u73b0<\/li>\n<li>8.3 \u53bb\u91cd\u7b56\u7565<\/li>\n<\/ul>\n<\/li>\n<li>9\ufe0f\u20e3 \u8fd0\u884c\u65b9\u5f0f\u4e0e\u7ed3\u679c\u5c55\u793a<\/li>\n<li>\n<ul>\n<li>9.1 \u4e3b\u5165\u53e3\u6587\u4ef6<\/li>\n<li>9.2 \u542f\u52a8\u547d\u4ee4<\/li>\n<li>9.3 \u8f93\u51fa\u4f4d\u7f6e<\/li>\n<li>9.4 \u793a\u4f8b\u7ed3\u679c<\/li>\n<\/ul>\n<\/li>\n<li>&#x1f51f; \u5e38\u89c1\u95ee\u9898\u4e0e\u6392\u9519<\/li>\n<li>\n<ul>\n<li>10.1 \u9047\u5230 403 \u600e\u4e48\u529e&#xff1f;<\/li>\n<li>10.2 \u9047\u5230 429 \u600e\u4e48\u529e&#xff1f;<\/li>\n<li>10.3 HTML \u6293\u5230\u7a7a\u58f3\u600e\u4e48\u529e&#xff1f;<\/li>\n<li>10.4 \u89e3\u6790\u62a5\u9519\u600e\u4e48\u529e&#xff1f;<\/li>\n<li>10.5 \u7f16\u7801\u4e71\u7801\u600e\u4e48\u529e&#xff1f;<\/li>\n<li>10.6 \u6570\u636e\u91cd\u590d\u600e\u4e48\u529e&#xff1f;<\/li>\n<li>10.7 \u8bd5\u770b\u5b57\u6bb5\u4e0d\u51c6\u600e\u4e48\u529e&#xff1f;<\/li>\n<\/ul>\n<\/li>\n<li>1\ufe0f\u20e31\ufe0f\u20e3 \u8fdb\u9636\u4f18\u5316<\/li>\n<li>\n<ul>\n<li>11.1 \u5e76\u53d1\u91c7\u96c6<\/li>\n<li>11.2 \u65ad\u70b9\u7eed\u8dd1<\/li>\n<li>11.3 \u65e5\u5fd7\u4e0e\u76d1\u63a7<\/li>\n<li>11.4 \u5b9a\u65f6\u4efb\u52a1<\/li>\n<li>11.5 \u7f13\u5b58\u539f\u59cb\u54cd\u5e94<\/li>\n<li>11.6 \u6570\u636e\u8d28\u91cf\u68c0\u67e5<\/li>\n<li>11.7 \u6269\u5c55\u5230 Scrapy<\/li>\n<li>11.8 \u6269\u5c55\u5230 Playwright<\/li>\n<\/ul>\n<\/li>\n<li>1\ufe0f\u20e32\ufe0f\u20e3 \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;\u91c7\u96c6\u4e00\u4e2a\u5728\u7ebf\u6559\u80b2\u5e73\u53f0\u516c\u5f00\u8bfe\u7a0b\u76ee\u5f55\u6811&#xff0c;\u7528 requests &#043; JSON \u9012\u5f52\u89e3\u6790 &#043; CSV\/JSON\/SQLite \u5b8c\u6210\u4ece\u8bfe\u7a0b\u3001\u7ae0\u8282\u3001\u8bd5\u770b\u3001\u65f6\u957f\u3001\u8bb2\u5e08\u5230\u6807\u7b7e\u5b57\u6bb5\u7684\u7ed3\u6784\u5316\u5bfc\u51fa\u3002<\/p>\n<p>\u8bfb\u5b8c\u8fd9\u7bc7\u6587\u7ae0&#xff0c;\u4f60\u53ef\u4ee5\u83b7\u5f97&#xff1a;<\/p>\n<li>\u7406\u89e3\u52a8\u6001\u76ee\u5f55\u6811\u6570\u636e\u4e3a\u4ec0\u4e48\u4e0d\u80fd\u53ea\u9760\u666e\u901a HTML \u9009\u62e9\u5668\u786c\u6252\u3002<\/li>\n<li>\u638c\u63e1\u5d4c\u5957 children \u7ed3\u6784\u7684\u9012\u5f52\u89e3\u6790\u65b9\u6cd5\u3002<\/li>\n<li>\u62ff\u5230\u4e00\u5957\u53ef\u8fd0\u884c\u3001\u53ef\u6269\u5c55\u3001\u5e26\u5bb9\u9519\u548c\u5b58\u50a8\u5c42\u7684 Python \u722c\u866b\u9879\u76ee\u9aa8\u67b6\u3002<\/li>\n<p>\u8fd9\u7bc7\u5185\u5bb9\u53ea\u8ba8\u8bba\u516c\u5f00\u76ee\u5f55\u6570\u636e\u7684\u6280\u672f\u91c7\u96c6&#xff0c;\u4e0d\u6d89\u53ca\u767b\u5f55\u7ed5\u8fc7\u3001\u4ed8\u8d39\u5185\u5bb9\u83b7\u53d6\u3001\u8d26\u53f7\u63a5\u53e3\u6ee5\u7528&#xff0c;\u4e5f\u4e0d\u8ba8\u8bba\u4efb\u4f55\u975e\u6280\u672f\u8bae\u9898\u3002\u6211\u7684\u6001\u5ea6\u6bd4\u8f83\u7b80\u5355&#xff1a;\u722c\u866b\u662f\u4e00\u628a\u5de5\u5177&#xff0c;\u5199\u5f97\u7a33\u3001\u7528\u5f97\u514b\u5236&#xff0c;\u624d\u6709\u957f\u671f\u4ef7\u503c\u3002<\/p>\n<hr \/>\n<h3>1\ufe0f\u20e3 \u6458\u8981&#xff08;Abstract&#xff09;<\/h3>\n<p>\u672c\u6587\u4ee5\u5728\u7ebf\u6559\u80b2\u5e73\u53f0\u516c\u5f00\u8bfe\u7a0b\u76ee\u5f55\u6811\u4e3a\u91c7\u96c6\u5bf9\u8c61&#xff0c;\u4f7f\u7528 Python \u7684 requests \u8bf7\u6c42\u516c\u5f00 JSON \u6570\u636e&#xff0c;\u9012\u5f52\u89e3\u6790\u5d4c\u5957 children \u8282\u70b9&#xff0c;\u5e76\u6700\u7ec8\u5c06\u8bfe\u7a0b\u3001\u7ae0\u8282\u3001\u8bd5\u770b\u3001\u65f6\u957f\u3001\u8bb2\u5e08\u3001\u6807\u7b7e\u7b49\u5b57\u6bb5\u5bfc\u51fa\u5230 CSV\u3001JSON \u548c SQLite\u3002<\/p>\n<p>\u8bfb\u5b8c\u4e4b\u540e&#xff0c;\u4f60\u5c06\u80fd\u591f&#xff1a;<\/p>\n<li>\u5224\u65ad\u9875\u9762\u662f\u9759\u6001 HTML\u3001\u52a8\u6001\u6e32\u67d3&#xff0c;\u8fd8\u662f\u63a5\u53e3\u9a71\u52a8\u3002<\/li>\n<li>\u8bbe\u8ba1\u4e00\u4e2a\u5206\u5c42\u6e05\u6670\u7684\u91c7\u96c6\u6d41\u7a0b&#xff1a;\u8bf7\u6c42\u3001\u89e3\u6790\u3001\u6e05\u6d17\u3001\u5b58\u50a8\u3002<\/li>\n<li>\u7f16\u5199\u80fd\u591f\u5904\u7406\u591a\u7ea7\u7ae0\u8282\u76ee\u5f55\u7684\u9012\u5f52\u89e3\u6790\u5668&#xff0c;\u907f\u514d\u53ea\u6293\u5230\u7b2c\u4e00\u5c42\u7ae0\u8282\u3002<\/li>\n<hr \/>\n<h3>2\ufe0f\u20e3 \u80cc\u666f\u4e0e\u9700\u6c42&#xff08;Why&#xff09;<\/h3>\n<p>\u5728\u7ebf\u6559\u80b2\u5e73\u53f0\u7684\u8bfe\u7a0b\u8be6\u60c5\u9875\u901a\u5e38\u4f1a\u5c55\u793a\u4e00\u4e2a\u76ee\u5f55\u6811\u3002\u4f8b\u5982&#xff1a;<\/p>\n<ul>\n<li>\n<p>\u7b2c\u4e00\u7ae0&#xff1a;Python \u57fa\u7840<\/p>\n<ul>\n<li>1.1 \u73af\u5883\u5b89\u88c5<\/li>\n<li>1.2 \u53d8\u91cf\u4e0e\u6570\u636e\u7c7b\u578b<\/li>\n<\/ul>\n<\/li>\n<li>\n<p>\u7b2c\u4e8c\u7ae0&#xff1a;\u7f51\u7edc\u8bf7\u6c42<\/p>\n<ul>\n<li>2.1 HTTP \u57fa\u7840<\/li>\n<li>2.2 requests \u5165\u95e8<\/li>\n<li>2.3 \u53cd\u722c\u4e0e\u9891\u63a7\u8bf4\u660e<\/li>\n<\/ul>\n<\/li>\n<li>\n<p>\u7b2c\u4e09\u7ae0&#xff1a;\u6570\u636e\u89e3\u6790<\/p>\n<ul>\n<li>3.1 JSON \u89e3\u6790<\/li>\n<li>3.2 XPath \u89e3\u6790<\/li>\n<li>3.3 \u9012\u5f52\u5904\u7406 children<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>\u8fd9\u79cd\u76ee\u5f55\u7ed3\u6784\u770b\u8d77\u6765\u50cf\u666e\u901a\u5217\u8868&#xff0c;\u5b9e\u9645\u5f88\u591a\u5e73\u53f0\u4f1a\u901a\u8fc7\u524d\u7aef\u6846\u67b6\u52a8\u6001\u6e32\u67d3\u3002\u4f60\u5728\u6d4f\u89c8\u5668\u91cc\u770b\u5230\u7684\u662f\u5b8c\u6574\u8bfe\u7a0b\u76ee\u5f55&#xff0c;\u4f46\u76f4\u63a5\u7528 requests.get(url).text \u62ff\u56de\u6765\u7684 HTML \u91cc\u53ef\u80fd\u6ca1\u6709\u7ae0\u8282\u6570\u636e&#xff0c;\u53ea\u6709\u4e00\u4e2a\u7a7a\u7684 &lt;div id&#061;&#034;app&#034;&gt;&lt;\/div&gt;\u3002<\/p>\n<p>\u8fd9\u7c7b\u9875\u9762\u7684\u771f\u5b9e\u6570\u636e\u7ecf\u5e38\u6765\u81ea\u516c\u5f00\u63a5\u53e3&#xff0c;\u4f8b\u5982&#xff1a;<\/p>\n<p>\/course\/detail?id&#061;1001<br \/>\n\/api\/course\/catalog?course_id&#061;1001<br \/>\n\/api\/course\/tree\/1001<\/p>\n<p>\u524d\u7aef\u62ff\u5230 JSON \u540e\u518d\u6e32\u67d3\u6210\u76ee\u5f55\u6811\u3002\u722c\u866b\u7684\u6838\u5fc3\u4efb\u52a1\u4e0d\u662f\u201c\u6a21\u62df\u70b9\u51fb\u9875\u9762\u201d&#xff0c;\u800c\u662f\u627e\u5230\u516c\u5f00\u6570\u636e\u6765\u6e90&#xff0c;\u5e76\u5bf9\u8fd4\u56de\u7ed3\u6784\u8fdb\u884c\u7a33\u5b9a\u89e3\u6790\u3002<\/p>\n<h4>\u4e3a\u4ec0\u4e48\u8981\u91c7\u96c6\u8bfe\u7a0b\u76ee\u5f55&#xff1f;<\/h4>\n<p>\u5e38\u89c1\u76ee\u7684\u6709\u4e09\u7c7b\u3002<\/p>\n<p>\u7b2c\u4e00\u7c7b\u662f\u6570\u636e\u5206\u6790\u3002\u6bd4\u5982\u5206\u6790\u4e0d\u540c\u8bfe\u7a0b\u7684\u7ae0\u8282\u6570\u91cf\u3001\u8bd5\u770b\u6bd4\u4f8b\u3001\u5e73\u5747\u8bfe\u65f6\u3001\u8bb2\u5e08\u8986\u76d6\u8303\u56f4\u3001\u6807\u7b7e\u5206\u5e03\u7b49\u3002<\/p>\n<p>\u7b2c\u4e8c\u7c7b\u662f\u4fe1\u606f\u805a\u5408\u3002\u6bd4\u5982\u628a\u591a\u4e2a\u516c\u5f00\u8bfe\u7a0b\u76ee\u5f55\u6c47\u603b\u5230\u4e00\u4e2a\u5185\u90e8\u77e5\u8bc6\u5e93&#xff0c;\u4fbf\u4e8e\u5b66\u4e60\u8def\u7ebf\u89c4\u5212\u3002<\/p>\n<p>\u7b2c\u4e09\u7c7b\u662f\u81ea\u52a8\u5316\u3002\u6bd4\u5982\u6bcf\u5929\u68c0\u67e5\u516c\u5f00\u76ee\u5f55\u662f\u5426\u65b0\u589e\u7ae0\u8282&#xff0c;\u6216\u8005\u8bfe\u7a0b\u6807\u9898\u3001\u8bb2\u5e08\u3001\u8bd5\u770b\u72b6\u6001\u662f\u5426\u53d8\u5316\u3002<\/p>\n<h4>\u76ee\u6807\u5b57\u6bb5<\/h4>\n<p>\u672c\u6587\u76ee\u6807\u5b57\u6bb5\u5982\u4e0b&#xff1a;<\/p>\n<table>\n<tr>\u5b57\u6bb5\u8bf4\u660e<\/tr>\n<tbody>\n<tr>\n<td>course_id<\/td>\n<td>\u8bfe\u7a0b ID<\/td>\n<\/tr>\n<tr>\n<td>course_title<\/td>\n<td>\u8bfe\u7a0b\u540d\u79f0<\/td>\n<\/tr>\n<tr>\n<td>teacher<\/td>\n<td>\u8bb2\u5e08<\/td>\n<\/tr>\n<tr>\n<td>tags<\/td>\n<td>\u8bfe\u7a0b\u6807\u7b7e<\/td>\n<\/tr>\n<tr>\n<td>chapter_id<\/td>\n<td>\u7ae0\u8282 ID<\/td>\n<\/tr>\n<tr>\n<td>chapter_title<\/td>\n<td>\u7ae0\u8282\u6807\u9898<\/td>\n<\/tr>\n<tr>\n<td>parent_id<\/td>\n<td>\u7236\u7ae0\u8282 ID<\/td>\n<\/tr>\n<tr>\n<td>level<\/td>\n<td>\u7ae0\u8282\u5c42\u7ea7<\/td>\n<\/tr>\n<tr>\n<td>is_preview<\/td>\n<td>\u662f\u5426\u8bd5\u770b<\/td>\n<\/tr>\n<tr>\n<td>duration_seconds<\/td>\n<td>\u65f6\u957f&#xff0c;\u5355\u4f4d\u79d2<\/td>\n<\/tr>\n<tr>\n<td>duration_text<\/td>\n<td>\u683c\u5f0f\u5316\u65f6\u957f<\/td>\n<\/tr>\n<tr>\n<td>sort_path<\/td>\n<td>\u7ae0\u8282\u6392\u5e8f\u8def\u5f84<\/td>\n<\/tr>\n<tr>\n<td>source_url<\/td>\n<td>\u6570\u636e\u6765\u6e90\u5730\u5740<\/td>\n<\/tr>\n<tr>\n<td>crawled_at<\/td>\n<td>\u91c7\u96c6\u65f6\u95f4<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>\u8fd9\u91cc\u7279\u522b\u9700\u8981\u6ce8\u610f\u7684\u662f parent_id\u3001level \u548c sort_path\u3002\u76ee\u5f55\u6811\u4e0d\u662f\u4e00\u5f20\u6241\u5e73\u8868&#xff0c;\u539f\u59cb\u6570\u636e\u901a\u5e38\u662f\u5d4c\u5957\u7ed3\u6784\u3002\u4e3a\u4e86\u540e\u7eed\u5206\u6790\u65b9\u4fbf&#xff0c;\u6211\u4eec\u4f1a\u628a\u6811\u5f62\u7ed3\u6784\u5c55\u5f00\u6210\u6241\u5e73\u8bb0\u5f55&#xff0c;\u540c\u65f6\u4fdd\u7559\u5c42\u7ea7\u5173\u7cfb\u3002<\/p>\n<hr \/>\n<h3>3\ufe0f\u20e3 \u5408\u89c4\u4e0e\u6ce8\u610f\u4e8b\u9879<\/h3>\n<p>\u6b63\u5f0f\u5199\u4ee3\u7801\u524d&#xff0c;\u5fc5\u987b\u5148\u628a\u8fb9\u754c\u8bf4\u6e05\u695a\u3002\u722c\u866b\u4e0d\u662f\u201c\u80fd\u6293\u5c31\u6293\u201d&#xff0c;\u800c\u662f\u5e94\u8be5\u5148\u5224\u65ad\u6570\u636e\u662f\u5426\u516c\u5f00\u3001\u4f7f\u7528\u65b9\u5f0f\u662f\u5426\u5408\u7406\u3001\u9891\u7387\u662f\u5426\u514b\u5236\u3002<\/p>\n<h4>3.1 robots.txt \u57fa\u672c\u8bf4\u660e<\/h4>\n<p>\u5f88\u591a\u7f51\u7ad9\u4f1a\u63d0\u4f9b robots.txt \u6587\u4ef6&#xff0c;\u7528\u6765\u8bf4\u660e\u641c\u7d22\u5f15\u64ce\u6216\u81ea\u52a8\u5316\u7a0b\u5e8f\u54ea\u4e9b\u8def\u5f84\u53ef\u4ee5\u8bbf\u95ee&#xff0c;\u54ea\u4e9b\u8def\u5f84\u4e0d\u5e0c\u671b\u88ab\u8bbf\u95ee\u3002\u5b83\u4e00\u822c\u4f4d\u4e8e\u7f51\u7ad9\u6839\u8def\u5f84&#xff1a;<\/p>\n<p>https:\/\/example.com\/robots.txt<\/p>\n<p>\u5728\u6b63\u5f0f\u91c7\u96c6\u524d&#xff0c;\u5efa\u8bae\u5148\u68c0\u67e5\u76ee\u6807\u7ad9\u70b9\u7684 robots \u89c4\u5219&#xff0c;\u5c24\u5176\u5173\u6ce8&#xff1a;<\/p>\n<p>User-agent: *<br \/>\nDisallow: \/private\/<br \/>\nDisallow: \/user\/<br \/>\nDisallow: \/api\/order\/<br \/>\nAllow: \/course\/<\/p>\n<p>\u5982\u679c\u89c4\u5219\u660e\u786e\u4e0d\u5141\u8bb8\u8bbf\u95ee\u67d0\u4e9b\u8def\u5f84&#xff0c;\u5c31\u4e0d\u8981\u91c7\u96c6\u8fd9\u4e9b\u8def\u5f84\u3002\u5373\u4fbf\u67d0\u4e9b\u63a5\u53e3\u80fd\u76f4\u63a5\u8bbf\u95ee&#xff0c;\u4e5f\u4e0d\u4ee3\u8868\u9002\u5408\u88ab\u6279\u91cf\u6293\u53d6\u3002<\/p>\n<h4>3.2 \u9891\u7387\u63a7\u5236<\/h4>\n<p>\u6280\u672f\u4e0a\u53ef\u4ee5\u5f00\u51e0\u5341\u4e2a\u7ebf\u7a0b\u3001\u51e0\u767e\u4e2a\u534f\u7a0b&#xff0c;\u4f46\u8fd9\u5e76\u4e0d\u610f\u5473\u7740\u5e94\u8be5\u8fd9\u4e48\u505a\u3002\u5bf9\u516c\u5f00\u8bfe\u7a0b\u76ee\u5f55\u8fd9\u79cd\u4f4e\u9891\u53d8\u5316\u7684\u6570\u636e&#xff0c;\u5b8c\u5168\u6ca1\u5fc5\u8981\u9ad8\u5e76\u53d1\u3002<\/p>\n<p>\u5efa\u8bae\u7b56\u7565&#xff1a;<\/p>\n<ul>\n<li>\u5355\u7ad9\u70b9\u8bf7\u6c42\u95f4\u9694\u8bbe\u7f6e\u4e3a 1\u20133 \u79d2\u3002<\/li>\n<li>\u5bf9\u5931\u8d25\u8bf7\u6c42\u4f7f\u7528\u6307\u6570\u9000\u907f\u3002<\/li>\n<li>\u5bf9 429\u3001503 \u7b49\u72b6\u6001\u7801\u4e3b\u52a8\u964d\u4f4e\u9891\u7387\u3002<\/li>\n<li>\u4e0d\u505a\u653b\u51fb\u5f0f\u5e76\u53d1\u3002<\/li>\n<li>\u4e0d\u5728\u77ed\u65f6\u95f4\u5185\u91cd\u590d\u8bf7\u6c42\u540c\u4e00 URL\u3002<\/li>\n<\/ul>\n<p>\u672c\u6587\u793a\u4f8b\u9879\u76ee\u9ed8\u8ba4\u662f\u4e32\u884c\u8bf7\u6c42\u3002\u540e\u9762\u8fdb\u9636\u90e8\u5206\u4f1a\u8bb2\u5e76\u53d1&#xff0c;\u4f46\u4e5f\u4f1a\u5f3a\u8c03\u901f\u7387\u9650\u5236\u3002<\/p>\n<h4>3.3 \u4e0d\u91c7\u96c6\u654f\u611f\u4fe1\u606f<\/h4>\n<p>\u672c\u6587\u53ea\u91c7\u96c6\u516c\u5f00\u8bfe\u7a0b\u76ee\u5f55\u5b57\u6bb5&#xff0c;\u4f8b\u5982\u8bfe\u7a0b\u540d\u79f0\u3001\u7ae0\u8282\u6807\u9898\u3001\u8bd5\u770b\u72b6\u6001\u3001\u65f6\u957f\u3001\u8bb2\u5e08\u3001\u6807\u7b7e\u3002\u4e0d\u8981\u91c7\u96c6&#xff1a;<\/p>\n<ul>\n<li>\u7528\u6237\u4e2a\u4eba\u4fe1\u606f<\/li>\n<li>\u5b66\u5458\u8bc4\u8bba\u4e2d\u7684\u654f\u611f\u5185\u5bb9<\/li>\n<li>\u8ba2\u5355\u4fe1\u606f<\/li>\n<li>\u8d2d\u4e70\u8bb0\u5f55<\/li>\n<li>\u767b\u5f55\u540e\u624d\u53ef\u89c1\u7684\u6570\u636e<\/li>\n<li>\u4ed8\u8d39\u89c6\u9891\u771f\u5b9e\u64ad\u653e\u5730\u5740<\/li>\n<li>\u9700\u8981\u7ed5\u8fc7\u6743\u9650\u624d\u80fd\u83b7\u53d6\u7684\u5185\u5bb9<\/li>\n<\/ul>\n<p>\u5bf9\u4e8e\u9700\u8981\u767b\u5f55\u3001\u4ed8\u8d39\u6216\u6388\u6743\u7684\u6570\u636e&#xff0c;\u5e94\u4f7f\u7528\u5b98\u65b9 API\u3001\u5f00\u653e\u5e73\u53f0\u6216\u7ecf\u8fc7\u6388\u6743\u7684\u6570\u636e\u5bfc\u51fa\u65b9\u5f0f\u3002<\/p>\n<h4>3.4 \u4e0d\u7ed5\u8fc7\u9650\u5236<\/h4>\n<p>\u672c\u6587\u4e0d\u4f1a\u6f14\u793a\u7ed5\u8fc7\u767b\u5f55\u3001\u7834\u89e3\u7b7e\u540d\u3001\u89c4\u907f\u98ce\u63a7\u3001\u6279\u91cf\u8d26\u53f7\u8bf7\u6c42\u3001\u8bbf\u95ee\u4ed8\u8d39\u8d44\u6e90\u7b49\u505a\u6cd5\u3002\u5373\u4f7f\u67d0\u4e9b\u6570\u636e\u5728\u6d4f\u89c8\u5668\u7f51\u7edc\u9762\u677f\u4e2d\u80fd\u770b\u5230&#xff0c;\u4e5f\u8981\u5224\u65ad\u5b83\u662f\u5426\u5c5e\u4e8e\u516c\u5f00\u76ee\u5f55\u4fe1\u606f\u3002\u6280\u672f\u5206\u4eab\u5e94\u8be5\u4fdd\u6301\u8fb9\u754c\u611f&#xff0c;\u8fd9\u4e00\u70b9\u6bd4\u4ee3\u7801\u672c\u8eab\u66f4\u91cd\u8981\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\u4e0e API \u7684\u533a\u522b<\/h4>\n<p>\u722c\u53d6\u7f51\u9875\u524d&#xff0c;\u6211\u4e60\u60ef\u5148\u628a\u76ee\u6807\u9875\u9762\u5206\u6210\u4e09\u7c7b\u3002<\/p>\n<p>\u7b2c\u4e00\u7c7b\u662f\u9759\u6001 HTML\u3002\u9875\u9762\u6e90\u4ee3\u7801\u91cc\u5df2\u7ecf\u6709\u5b8c\u6574\u6570\u636e&#xff0c;\u76f4\u63a5\u4f7f\u7528 requests &#043; BeautifulSoup\/lxml \u5c31\u80fd\u89e3\u6790\u3002<\/p>\n<p>\u7b2c\u4e8c\u7c7b\u662f\u52a8\u6001\u6e32\u67d3\u3002\u9875\u9762\u6e90\u4ee3\u7801\u91cc\u6ca1\u6709\u76ee\u6807\u6570\u636e&#xff0c;\u6570\u636e\u7531 JavaScript \u52a0\u8f7d\u540e\u6e32\u67d3\u3002\u8bfe\u7a0b\u76ee\u5f55\u6811\u7ecf\u5e38\u5c5e\u4e8e\u8fd9\u4e00\u7c7b\u3002<\/p>\n<p>\u7b2c\u4e09\u7c7b\u662f\u63a5\u53e3\u9a71\u52a8\u3002\u52a8\u6001\u6e32\u67d3\u80cc\u540e\u901a\u5e38\u6709 JSON \u63a5\u53e3\u3002\u4e0e\u5176\u7528\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u53bb\u70b9\u9875\u9762&#xff0c;\u4e0d\u5982\u76f4\u63a5\u8bf7\u6c42\u516c\u5f00\u63a5\u53e3&#xff0c;\u7136\u540e\u89e3\u6790 JSON\u3002<\/p>\n<p>\u672c\u6587\u5c5e\u4e8e\u7b2c\u4e09\u7c7b&#xff1a;\u52a8\u6001\u9875\u9762\u80cc\u540e\u7684\u516c\u5f00 JSON \u76ee\u5f55\u6811\u89e3\u6790\u3002<\/p>\n<h4>4.2 \u6574\u4f53\u6d41\u7a0b<\/h4>\n<p>\u6d41\u7a0b\u53ef\u4ee5\u6982\u62ec\u4e3a&#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>  #mermaid-svg-7o1JWeouvoDh4JBV{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:16px;fill:#333;}@keyframes edge-animation-frame{from{stroke-dashoffset:0;}}@keyframes dash{to{stroke-dashoffset:0;}}#mermaid-svg-7o1JWeouvoDh4JBV .edge-animation-slow{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 50s linear infinite;stroke-linecap:round;}#mermaid-svg-7o1JWeouvoDh4JBV .edge-animation-fast{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 20s linear infinite;stroke-linecap:round;}#mermaid-svg-7o1JWeouvoDh4JBV .error-icon{fill:#552222;}#mermaid-svg-7o1JWeouvoDh4JBV .error-text{fill:#552222;stroke:#552222;}#mermaid-svg-7o1JWeouvoDh4JBV .edge-thickness-normal{stroke-width:1px;}#mermaid-svg-7o1JWeouvoDh4JBV .edge-thickness-thick{stroke-width:3.5px;}#mermaid-svg-7o1JWeouvoDh4JBV .edge-pattern-solid{stroke-dasharray:0;}#mermaid-svg-7o1JWeouvoDh4JBV .edge-thickness-invisible{stroke-width:0;fill:none;}#mermaid-svg-7o1JWeouvoDh4JBV .edge-pattern-dashed{stroke-dasharray:3;}#mermaid-svg-7o1JWeouvoDh4JBV .edge-pattern-dotted{stroke-dasharray:2;}#mermaid-svg-7o1JWeouvoDh4JBV .marker{fill:#333333;stroke:#333333;}#mermaid-svg-7o1JWeouvoDh4JBV .marker.cross{stroke:#333333;}#mermaid-svg-7o1JWeouvoDh4JBV svg{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:16px;}#mermaid-svg-7o1JWeouvoDh4JBV p{margin:0;}#mermaid-svg-7o1JWeouvoDh4JBV .label{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;color:#333;}#mermaid-svg-7o1JWeouvoDh4JBV .cluster-label text{fill:#333;}#mermaid-svg-7o1JWeouvoDh4JBV .cluster-label span{color:#333;}#mermaid-svg-7o1JWeouvoDh4JBV .cluster-label span p{background-color:transparent;}#mermaid-svg-7o1JWeouvoDh4JBV .label text,#mermaid-svg-7o1JWeouvoDh4JBV span{fill:#333;color:#333;}#mermaid-svg-7o1JWeouvoDh4JBV .node rect,#mermaid-svg-7o1JWeouvoDh4JBV .node circle,#mermaid-svg-7o1JWeouvoDh4JBV .node ellipse,#mermaid-svg-7o1JWeouvoDh4JBV .node polygon,#mermaid-svg-7o1JWeouvoDh4JBV .node path{fill:#ECECFF;stroke:#9370DB;stroke-width:1px;}#mermaid-svg-7o1JWeouvoDh4JBV .rough-node .label text,#mermaid-svg-7o1JWeouvoDh4JBV .node .label text,#mermaid-svg-7o1JWeouvoDh4JBV .image-shape .label,#mermaid-svg-7o1JWeouvoDh4JBV .icon-shape .label{text-anchor:middle;}#mermaid-svg-7o1JWeouvoDh4JBV .node .katex path{fill:#000;stroke:#000;stroke-width:1px;}#mermaid-svg-7o1JWeouvoDh4JBV .rough-node .label,#mermaid-svg-7o1JWeouvoDh4JBV .node .label,#mermaid-svg-7o1JWeouvoDh4JBV .image-shape .label,#mermaid-svg-7o1JWeouvoDh4JBV .icon-shape .label{text-align:center;}#mermaid-svg-7o1JWeouvoDh4JBV .node.clickable{cursor:pointer;}#mermaid-svg-7o1JWeouvoDh4JBV .root .anchor path{fill:#333333!important;stroke-width:0;stroke:#333333;}#mermaid-svg-7o1JWeouvoDh4JBV .arrowheadPath{fill:#333333;}#mermaid-svg-7o1JWeouvoDh4JBV .edgePath .path{stroke:#333333;stroke-width:2.0px;}#mermaid-svg-7o1JWeouvoDh4JBV .flowchart-link{stroke:#333333;fill:none;}#mermaid-svg-7o1JWeouvoDh4JBV .edgeLabel{background-color:rgba(232,232,232, 0.8);text-align:center;}#mermaid-svg-7o1JWeouvoDh4JBV .edgeLabel p{background-color:rgba(232,232,232, 0.8);}#mermaid-svg-7o1JWeouvoDh4JBV .edgeLabel rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#mermaid-svg-7o1JWeouvoDh4JBV .labelBkg{background-color:rgba(232, 232, 232, 0.5);}#mermaid-svg-7o1JWeouvoDh4JBV .cluster rect{fill:#ffffde;stroke:#aaaa33;stroke-width:1px;}#mermaid-svg-7o1JWeouvoDh4JBV .cluster text{fill:#333;}#mermaid-svg-7o1JWeouvoDh4JBV .cluster span{color:#333;}#mermaid-svg-7o1JWeouvoDh4JBV div.mermaidTooltip{position:absolute;text-align:center;max-width:200px;padding:2px;font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:12px;background:hsl(80, 100%, 96.2745098039%);border:1px solid #aaaa33;border-radius:2px;pointer-events:none;z-index:100;}#mermaid-svg-7o1JWeouvoDh4JBV .flowchartTitleText{text-anchor:middle;font-size:18px;fill:#333;}#mermaid-svg-7o1JWeouvoDh4JBV rect.text{fill:none;stroke-width:0;}#mermaid-svg-7o1JWeouvoDh4JBV .icon-shape,#mermaid-svg-7o1JWeouvoDh4JBV .image-shape{background-color:rgba(232,232,232, 0.8);text-align:center;}#mermaid-svg-7o1JWeouvoDh4JBV .icon-shape p,#mermaid-svg-7o1JWeouvoDh4JBV .image-shape p{background-color:rgba(232,232,232, 0.8);padding:2px;}#mermaid-svg-7o1JWeouvoDh4JBV .icon-shape .label rect,#mermaid-svg-7o1JWeouvoDh4JBV .image-shape .label rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#mermaid-svg-7o1JWeouvoDh4JBV .label-icon{display:inline-block;height:1em;overflow:visible;vertical-align:-0.125em;}#mermaid-svg-7o1JWeouvoDh4JBV .node .label-icon path{fill:currentColor;stroke:revert;stroke-width:revert;}#mermaid-svg-7o1JWeouvoDh4JBV :root{&#8211;mermaid-font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;}<\/p>\n<p>         <span class=\"edgeLabel\"><\/span><\/p>\n<p>         <span class=\"edgeLabel\"><\/span><\/p>\n<p>         <span class=\"edgeLabel\"><\/span><\/p>\n<p>         <span class=\"edgeLabel\"><\/p>\n<p>\u5426<\/p>\n<p><\/span><\/p>\n<p>         <span class=\"edgeLabel\"><\/span><\/p>\n<p>         <span class=\"edgeLabel\"><\/p>\n<p>\u662f<\/p>\n<p><\/span><\/p>\n<p>         <span class=\"edgeLabel\"><\/span><\/p>\n<p>         <span class=\"edgeLabel\"><\/span><\/p>\n<p>         <span class=\"edgeLabel\"><\/span><\/p>\n<p>         <span class=\"edgeLabel\"><\/span><\/p>\n<p>         <span class=\"edgeLabel\"><\/span><\/p>\n<p>         <span class=\"edgeLabel\"><\/span><\/p>\n<p>         <span class=\"nodeLabel\"><\/p>\n<p>\u8bfb\u53d6\u914d\u7f6e<\/p>\n<p><\/span><\/p>\n<p>         <span class=\"nodeLabel\"><\/p>\n<p>\u6784\u9020\u8bf7\u6c42<\/p>\n<p><\/span><\/p>\n<p>         <span class=\"nodeLabel\"><\/p>\n<p>Fetcher \u8bf7\u6c42\u516c\u5f00 JSON<\/p>\n<p><\/span><\/p>\n<p>         <span class=\"nodeLabel\"><\/p>\n<p>\u8bf7\u6c42\u662f\u5426\u6210\u529f<\/p>\n<p><\/span><\/p>\n<p>         <span class=\"nodeLabel\"><\/p>\n<p>\u91cd\u8bd5\u4e0e\u9000\u907f<\/p>\n<p><\/span><\/p>\n<p>         <span class=\"nodeLabel\"><\/p>\n<p>Parser \u89e3\u6790\u8bfe\u7a0b\u4fe1\u606f<\/p>\n<p><\/span><\/p>\n<p>         <span class=\"nodeLabel\"><\/p>\n<p>\u9012\u5f52\u89e3\u6790 children \u76ee\u5f55\u6811<\/p>\n<p><\/span><\/p>\n<p>         <span class=\"nodeLabel\"><\/p>\n<p>\u5b57\u6bb5\u6e05\u6d17\u4e0e\u89c4\u8303\u5316<\/p>\n<p><\/span><\/p>\n<p>         <span class=\"nodeLabel\"><\/p>\n<p>\u53bb\u91cd<\/p>\n<p><\/span><\/p>\n<p>         <span class=\"nodeLabel\"><\/p>\n<p>\u5bfc\u51fa CSV<\/p>\n<p><\/span><\/p>\n<p>         <span class=\"nodeLabel\"><\/p>\n<p>\u5bfc\u51fa JSON<\/p>\n<p><\/span><\/p>\n<p>         <span class=\"nodeLabel\"><\/p>\n<p>\u5199\u5165 SQLite<\/p>\n<p><\/span><\/p>\n<h4>4.3 \u4e3a\u4ec0\u4e48\u9009\u62e9 requests<\/h4>\n<p>\u672c\u6587\u9009\u62e9 requests \u7684\u539f\u56e0\u5f88\u76f4\u63a5&#xff1a;<\/p>\n<li>\u76ee\u6807\u6570\u636e\u6765\u81ea\u516c\u5f00 JSON \u63a5\u53e3&#xff0c;\u4e0d\u9700\u8981\u6d4f\u89c8\u5668\u771f\u5b9e\u6e32\u67d3\u3002<\/li>\n<li>\u8bfe\u7a0b\u76ee\u5f55\u6570\u636e\u7ed3\u6784\u7a33\u5b9a&#xff0c;\u91cd\u70b9\u5728\u9012\u5f52\u89e3\u6790\u800c\u4e0d\u662f\u9875\u9762\u4ea4\u4e92\u3002<\/li>\n<li>requests \u9879\u76ee\u8f7b\u91cf&#xff0c;\u90e8\u7f72\u7b80\u5355&#xff0c;\u4fbf\u4e8e\u5b9a\u65f6\u4efb\u52a1\u8fd0\u884c\u3002<\/li>\n<li>\u5bf9\u521d\u5b66\u8005\u548c\u5de5\u7a0b\u5316\u6539\u9020\u90fd\u6bd4\u8f83\u53cb\u597d\u3002<\/li>\n<h4>4.4 \u4ec0\u4e48\u65f6\u5019\u7528 Playwright<\/h4>\n<p>\u5982\u679c\u4f60\u627e\u4e0d\u5230\u516c\u5f00 JSON \u63a5\u53e3&#xff0c;\u6216\u8005\u9875\u9762\u5fc5\u987b\u6267\u884c JavaScript \u624d\u80fd\u62ff\u5230\u6570\u636e&#xff0c;\u53ef\u4ee5\u8003\u8651 Playwright\u3002\u4f46 Playwright \u4e0d\u5e94\u8be5\u6210\u4e3a\u7b2c\u4e00\u9009\u62e9&#xff0c;\u56e0\u4e3a\u5b83\u66f4\u91cd&#xff0c;\u8fd0\u884c\u6210\u672c\u66f4\u9ad8\u3002<\/p>\n<p>\u5408\u7406\u505a\u6cd5\u662f&#xff1a;<\/p>\n<li>\u5148\u6253\u5f00\u6d4f\u89c8\u5668\u5f00\u53d1\u8005\u5de5\u5177\u3002<\/li>\n<li>\u67e5\u770b Network \u9762\u677f\u3002<\/li>\n<li>\u7b5b\u9009 Fetch\/XHR \u8bf7\u6c42\u3002<\/li>\n<li>\u627e\u5230\u8fd4\u56de\u8bfe\u7a0b\u76ee\u5f55 JSON \u7684\u516c\u5f00\u63a5\u53e3\u3002<\/li>\n<li>\u518d\u7528 requests \u590d\u73b0\u8fd9\u4e2a\u63a5\u53e3\u8bf7\u6c42\u3002<\/li>\n<p>\u53ea\u6709\u5728\u6570\u636e\u786e\u5b9e\u4f9d\u8d56\u6d4f\u89c8\u5668\u8fd0\u884c\u72b6\u6001\u65f6&#xff0c;\u518d\u4f7f\u7528 Playwright\u3002<\/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>\u672c\u6587\u4ee3\u7801\u5728 Python 3.10\u30013.11\u30013.12 \u8bed\u6cd5\u8303\u56f4\u5185\u90fd\u53ef\u4ee5\u8fd0\u884c\u3002<\/p>\n<h4>5.2 \u5b89\u88c5\u4f9d\u8d56<\/h4>\n<p>\u521b\u5efa\u9879\u76ee\u76ee\u5f55&#xff1a;<\/p>\n<p><span class=\"token function\">mkdir<\/span> course_tree_spider<br \/>\n<span class=\"token builtin class-name\">cd<\/span> course_tree_spider<br \/>\npython <span class=\"token parameter variable\">-m<\/span> venv .venv<\/p>\n<p>\u6fc0\u6d3b\u865a\u62df\u73af\u5883\u3002<\/p>\n<p>macOS \/ Linux&#xff1a;<\/p>\n<p><span class=\"token builtin class-name\">source<\/span> .venv\/bin\/activate<\/p>\n<p>Windows PowerShell&#xff1a;<\/p>\n<p><span class=\"token punctuation\">.<\/span>venv\\\\Scripts\\\\Activate<span class=\"token punctuation\">.<\/span>ps1<\/p>\n<p>\u5b89\u88c5\u4f9d\u8d56&#xff1a;<\/p>\n<p>pip <span class=\"token function\">install<\/span> requests pyyaml tenacity pydantic rich<\/p>\n<p>\u751f\u6210 requirements.txt&#xff1a;<\/p>\n<p>requests&gt;&#061;2.31.0<br \/>\nPyYAML&gt;&#061;6.0.1<br \/>\ntenacity&gt;&#061;8.2.3<br \/>\npydantic&gt;&#061;2.6.0<br \/>\nrich&gt;&#061;13.7.0<\/p>\n<p>\u5982\u679c\u4f60\u5e0c\u671b\u540e\u7eed\u6269\u5c55\u5230 HTML \u89e3\u6790&#xff0c;\u53ef\u4ee5\u989d\u5916\u5b89\u88c5&#xff1a;<\/p>\n<p>pip <span class=\"token function\">install<\/span> beautifulsoup4 lxml<\/p>\n<p>\u672c\u6587\u4e3b\u7ebf\u4f7f\u7528 JSON \u89e3\u6790&#xff0c;\u6240\u4ee5 bs4\/lxml \u4e0d\u662f\u5fc5\u987b\u4f9d\u8d56\u3002<\/p>\n<h4>5.3 \u63a8\u8350\u9879\u76ee\u7ed3\u6784<\/h4>\n<p>course_tree_spider\/<br \/>\n\u251c\u2500\u2500 configs\/<br \/>\n\u2502   \u2514\u2500\u2500 settings.yaml<br \/>\n\u251c\u2500\u2500 crawler\/<br \/>\n\u2502   \u251c\u2500\u2500 __init__.py<br \/>\n\u2502   \u251c\u2500\u2500 config.py<br \/>\n\u2502   \u251c\u2500\u2500 fetcher.py<br \/>\n\u2502   \u251c\u2500\u2500 parser.py<br \/>\n\u2502   \u251c\u2500\u2500 storage.py<br \/>\n\u2502   \u2514\u2500\u2500 utils.py<br \/>\n\u251c\u2500\u2500 examples\/<br \/>\n\u2502   \u2514\u2500\u2500 course_tree_sample.json<br \/>\n\u251c\u2500\u2500 data\/<br \/>\n\u2502   \u251c\u2500\u2500 output.csv<br \/>\n\u2502   \u251c\u2500\u2500 output.json<br \/>\n\u2502   \u2514\u2500\u2500 courses.db<br \/>\n\u251c\u2500\u2500 logs\/<br \/>\n\u2502   \u2514\u2500\u2500 spider.log<br \/>\n\u251c\u2500\u2500 tests\/<br \/>\n\u2502   \u2514\u2500\u2500 test_parser.py<br \/>\n\u251c\u2500\u2500 main.py<br \/>\n\u2514\u2500\u2500 requirements.txt<\/p>\n<p>\u4e3a\u4e86\u8ba9\u4ee3\u7801\u53ef\u4ee5\u771f\u5b9e\u8fd0\u884c&#xff0c;\u672c\u6587\u4f1a\u63d0\u4f9b\u4e00\u4e2a\u672c\u5730\u793a\u4f8b JSON\u3002\u4f60\u53ef\u4ee5\u5148\u7528\u672c\u5730\u6587\u4ef6\u8dd1\u901a\u6d41\u7a0b&#xff0c;\u518d\u628a\u914d\u7f6e\u5207\u6362\u6210\u516c\u5f00\u63a5\u53e3 URL\u3002<\/p>\n<hr \/>\n<h3>6\ufe0f\u20e3 \u6838\u5fc3\u5b9e\u73b0&#xff1a;\u8bf7\u6c42\u5c42&#xff08;Fetcher&#xff09;<\/h3>\n<p>Fetcher \u8d1f\u8d23\u8bf7\u6c42\u6570\u636e\u3002\u4e00\u4e2a\u6210\u719f\u7684\u8bf7\u6c42\u5c42\u81f3\u5c11\u5e94\u8be5\u8003\u8651&#xff1a;<\/p>\n<ul>\n<li>headers<\/li>\n<li>timeout<\/li>\n<li>session<\/li>\n<li>cookie<\/li>\n<li>retry<\/li>\n<li>backoff<\/li>\n<li>\u72b6\u6001\u7801\u5904\u7406<\/li>\n<li>JSON \u89e3\u6790\u5f02\u5e38<\/li>\n<li>\u672c\u5730\u793a\u4f8b\u6587\u4ef6\u8bfb\u53d6<\/li>\n<\/ul>\n<h4>6.1 \u914d\u7f6e\u6587\u4ef6<\/h4>\n<p>\u5148\u5199 configs\/settings.yaml&#xff1a;<\/p>\n<p><span class=\"token key atrule\">spider<\/span><span class=\"token punctuation\">:<\/span><br \/>\n  <span class=\"token key atrule\">mode<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;file&#034;<\/span>  <span class=\"token comment\"># file or api<\/span><br \/>\n  <span class=\"token key atrule\">api_url<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;https:\/\/example.com\/api\/course\/catalog?course_id&#061;python-1001&#034;<\/span><br \/>\n  <span class=\"token key atrule\">sample_file<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;examples\/course_tree_sample.json&#034;<\/span><br \/>\n  <span class=\"token key atrule\">source_url<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;https:\/\/example.com\/course\/python-1001&#034;<\/span><br \/>\n  <span class=\"token key atrule\">request_interval<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token number\">1.5<\/span><br \/>\n  <span class=\"token key atrule\">timeout<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token number\">10<\/span><br \/>\n  <span class=\"token key atrule\">max_retries<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token number\">3<\/span><\/p>\n<p><span class=\"token key atrule\">headers<\/span><span class=\"token punctuation\">:<\/span><br \/>\n  <span class=\"token key atrule\">User-Agent<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 Chrome\/124.0 Safari\/537.36&#034;<\/span><br \/>\n  <span class=\"token key atrule\">Referer<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;https:\/\/example.com\/course\/python-1001&#034;<\/span><br \/>\n  <span class=\"token key atrule\">Accept<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;application\/json, text\/plain, *\/*&#034;<\/span><br \/>\n  <span class=\"token key atrule\">Accept-Language<\/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><\/p>\n<p><span class=\"token key atrule\">storage<\/span><span class=\"token punctuation\">:<\/span><br \/>\n  <span class=\"token key atrule\">csv_path<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;data\/output.csv&#034;<\/span><br \/>\n  <span class=\"token key atrule\">json_path<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;data\/output.json&#034;<\/span><br \/>\n  <span class=\"token key atrule\">sqlite_path<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;data\/courses.db&#034;<\/span><br \/>\n  <span class=\"token key atrule\">sqlite_table<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;course_chapters&#034;<\/span><\/p>\n<p>\u8fd9\u91cc\u7684 mode \u6709\u4e24\u4e2a\u503c&#xff1a;<\/p>\n<ul>\n<li>file&#xff1a;\u8bfb\u53d6\u672c\u5730\u793a\u4f8b JSON&#xff0c;\u9002\u5408\u5148\u9a8c\u8bc1\u89e3\u6790\u903b\u8f91\u3002<\/li>\n<li>api&#xff1a;\u8bf7\u6c42\u516c\u5f00 API&#xff0c;\u9002\u5408\u66ff\u6362\u6210\u771f\u5b9e\u516c\u5f00\u76ee\u5f55\u63a5\u53e3\u3002<\/li>\n<\/ul>\n<h4>6.2 \u793a\u4f8b JSON<\/h4>\n<p>\u521b\u5efa examples\/course_tree_sample.json&#xff1a;<\/p>\n<p><span class=\"token punctuation\">{<\/span><br \/>\n  <span class=\"token string-property property\">&#034;code&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">0<\/span><span class=\"token punctuation\">,<\/span><br \/>\n  <span class=\"token string-property property\">&#034;message&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;ok&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n  <span class=\"token string-property property\">&#034;data&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n    <span class=\"token string-property property\">&#034;course&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n      <span class=\"token string-property property\">&#034;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;python-1001&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n      <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;Python \u7f51\u7edc\u722c\u866b\u5b9e\u6218\u5165\u95e8&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n      <span class=\"token string-property property\">&#034;teacher&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n        <span class=\"token string-property property\">&#034;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;t-7788&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;name&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;\u6797\u5ddd&#034;<\/span><br \/>\n      <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">,<\/span><br \/>\n      <span class=\"token string-property property\">&#034;tags&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;Python&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;\u722c\u866b&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;\u6570\u636e\u91c7\u96c6&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;\u5b9e\u6218&#034;<\/span><span class=\"token punctuation\">]<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string-property property\">&#034;catalog&#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;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;c1&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;\u7b2c 1 \u7ae0 \u8bfe\u7a0b\u4ecb\u7ecd\u4e0e\u73af\u5883\u51c6\u5907&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;duration&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">1800<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;preview&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token boolean\">true<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;children&#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;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;c1-1&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;1.1 \u8bfe\u7a0b\u9002\u5408\u8c01\u5b66\u4e60&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;duration&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">420<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;preview&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token boolean\">true<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;children&#034;<\/span><span class=\"token operator\">:<\/span> <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 punctuation\">{<\/span><br \/>\n            <span class=\"token string-property property\">&#034;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;c1-2&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;1.2 Python \u73af\u5883\u5b89\u88c5&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;duration&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">780<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;preview&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token boolean\">true<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;children&#034;<\/span><span class=\"token operator\">:<\/span> <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 punctuation\">{<\/span><br \/>\n            <span class=\"token string-property property\">&#034;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;c1-3&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;1.3 \u9879\u76ee\u76ee\u5f55\u89c4\u5212&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;duration&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">600<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;preview&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token boolean\">false<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;children&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n          <span class=\"token punctuation\">}<\/span><br \/>\n        <span class=\"token punctuation\">]<\/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;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;c2&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;\u7b2c 2 \u7ae0 HTTP \u8bf7\u6c42\u57fa\u7840&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;duration&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">3600<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;preview&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token boolean\">false<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;children&#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;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;c2-1&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;2.1 GET \u4e0e POST \u7684\u533a\u522b&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;duration&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">900<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;preview&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token boolean\">false<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;children&#034;<\/span><span class=\"token operator\">:<\/span> <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 punctuation\">{<\/span><br \/>\n            <span class=\"token string-property property\">&#034;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;c2-2&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;2.2 headers \u4e0e referer&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;duration&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">960<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;preview&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token boolean\">false<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;children&#034;<\/span><span class=\"token operator\">:<\/span> <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 punctuation\">{<\/span><br \/>\n            <span class=\"token string-property property\">&#034;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;c2-3&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;2.3 timeout \u4e0e\u91cd\u8bd5&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;duration&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">1020<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;preview&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token boolean\">true<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;children&#034;<\/span><span class=\"token operator\">:<\/span> <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 punctuation\">{<\/span><br \/>\n            <span class=\"token string-property property\">&#034;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;c2-4&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;2.4 \u9891\u7387\u63a7\u5236\u4e0e\u5408\u89c4\u91c7\u96c6&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;duration&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">720<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;preview&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token boolean\">false<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;children&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n          <span class=\"token punctuation\">}<\/span><br \/>\n        <span class=\"token punctuation\">]<\/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;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;c3&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;\u7b2c 3 \u7ae0 \u52a8\u6001\u76ee\u5f55\u6811\u89e3\u6790&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;duration&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">5400<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;preview&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token boolean\">false<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;children&#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;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;c3-1&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;3.1 \u8bc6\u522b\u52a8\u6001\u6e32\u67d3\u9875\u9762&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;duration&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">1200<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;preview&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token boolean\">false<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;children&#034;<\/span><span class=\"token operator\">:<\/span> <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 punctuation\">{<\/span><br \/>\n            <span class=\"token string-property property\">&#034;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;c3-2&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;3.2 Network \u9762\u677f\u5b9a\u4f4d\u516c\u5f00 JSON&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;duration&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">1500<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;preview&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token boolean\">false<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;children&#034;<\/span><span class=\"token operator\">:<\/span> <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 punctuation\">{<\/span><br \/>\n            <span class=\"token string-property property\">&#034;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;c3-3&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;3.3 \u9012\u5f52\u89e3\u6790 children&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;duration&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">1800<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;preview&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token boolean\">true<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;children&#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;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;c3-3-1&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;3.3.1 \u9012\u5f52\u51fd\u6570\u8bbe\u8ba1&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string-property property\">&#034;duration&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">600<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string-property property\">&#034;preview&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token boolean\">true<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string-property property\">&#034;children&#034;<\/span><span class=\"token operator\">:<\/span> <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 punctuation\">{<\/span><br \/>\n                <span class=\"token string-property property\">&#034;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;c3-3-2&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;3.3.2 \u5c42\u7ea7\u4e0e sort_path \u7ef4\u62a4&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string-property property\">&#034;duration&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">720<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string-property property\">&#034;preview&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token boolean\">false<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string-property property\">&#034;children&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n              <span class=\"token punctuation\">}<\/span><br \/>\n            <span class=\"token punctuation\">]<\/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;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;c3-4&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;3.4 \u89e3\u6790\u5f02\u5e38\u4e0e\u5bb9\u9519&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;duration&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">900<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;preview&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token boolean\">false<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string-property property\">&#034;children&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n          <span class=\"token punctuation\">}<\/span><br \/>\n        <span class=\"token punctuation\">]<\/span><br \/>\n      <span class=\"token punctuation\">}<\/span><br \/>\n    <span class=\"token punctuation\">]<\/span><br \/>\n  <span class=\"token punctuation\">}<\/span><br \/>\n<span class=\"token punctuation\">}<\/span><\/p>\n<h4>6.3 \u914d\u7f6e\u8bfb\u53d6<\/h4>\n<p>\u521b\u5efa crawler\/config.py&#xff1a;<\/p>\n<p><span class=\"token keyword\">from<\/span> __future__ <span class=\"token keyword\">import<\/span> annotations<\/p>\n<p><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> Any<\/p>\n<p><span class=\"token keyword\">import<\/span> yaml<br \/>\n<span class=\"token keyword\">from<\/span> pydantic <span class=\"token keyword\">import<\/span> BaseModel<span class=\"token punctuation\">,<\/span> Field<\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">SpiderSettings<\/span><span class=\"token punctuation\">(<\/span>BaseModel<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    mode<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> Field<span class=\"token punctuation\">(<\/span>default<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;file&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    api_url<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> Field<span class=\"token punctuation\">(<\/span>default<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    sample_file<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> Field<span class=\"token punctuation\">(<\/span>default<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;examples\/course_tree_sample.json&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    source_url<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> Field<span class=\"token punctuation\">(<\/span>default<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    request_interval<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">float<\/span> <span class=\"token operator\">&#061;<\/span> Field<span class=\"token punctuation\">(<\/span>default<span class=\"token operator\">&#061;<\/span><span class=\"token number\">1.0<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    timeout<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">int<\/span> <span class=\"token operator\">&#061;<\/span> Field<span class=\"token punctuation\">(<\/span>default<span class=\"token operator\">&#061;<\/span><span class=\"token number\">10<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    max_retries<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">int<\/span> <span class=\"token operator\">&#061;<\/span> Field<span class=\"token punctuation\">(<\/span>default<span class=\"token operator\">&#061;<\/span><span class=\"token number\">3<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">StorageSettings<\/span><span class=\"token punctuation\">(<\/span>BaseModel<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    csv_path<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> Field<span class=\"token punctuation\">(<\/span>default<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;data\/output.csv&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    json_path<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> Field<span class=\"token punctuation\">(<\/span>default<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;data\/output.json&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    sqlite_path<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> Field<span class=\"token punctuation\">(<\/span>default<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;data\/courses.db&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    sqlite_table<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> Field<span class=\"token punctuation\">(<\/span>default<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;course_chapters&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">AppSettings<\/span><span class=\"token punctuation\">(<\/span>BaseModel<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    spider<span class=\"token punctuation\">:<\/span> SpiderSettings<br \/>\n    headers<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">dict<\/span><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 operator\">&#061;<\/span> Field<span class=\"token punctuation\">(<\/span>default_factory<span class=\"token operator\">&#061;<\/span><span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    storage<span class=\"token punctuation\">:<\/span> StorageSettings<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">load_settings<\/span><span class=\"token punctuation\">(<\/span>path<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;configs\/settings.yaml&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> AppSettings<span class=\"token punctuation\">:<\/span><br \/>\n    config_path <span class=\"token operator\">&#061;<\/span> Path<span class=\"token punctuation\">(<\/span>path<span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> config_path<span class=\"token punctuation\">.<\/span>exists<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">raise<\/span> FileNotFoundError<span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\u914d\u7f6e\u6587\u4ef6\u4e0d\u5b58\u5728: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>config_path<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">with<\/span> config_path<span class=\"token punctuation\">.<\/span><span class=\"token builtin\">open<\/span><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&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">as<\/span> f<span class=\"token punctuation\">:<\/span><br \/>\n        raw<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> yaml<span class=\"token punctuation\">.<\/span>safe_load<span class=\"token punctuation\">(<\/span>f<span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">return<\/span> AppSettings<span class=\"token punctuation\">(<\/span><span class=\"token operator\">**<\/span>raw<span class=\"token punctuation\">)<\/span><\/p>\n<h4>6.4 \u5de5\u5177\u51fd\u6570<\/h4>\n<p>\u521b\u5efa crawler\/utils.py&#xff1a;<\/p>\n<p><span class=\"token keyword\">from<\/span> __future__ <span class=\"token keyword\">import<\/span> annotations<\/p>\n<p><span class=\"token keyword\">import<\/span> hashlib<br \/>\n<span class=\"token keyword\">import<\/span> json<br \/>\n<span class=\"token keyword\">import<\/span> logging<br \/>\n<span class=\"token keyword\">from<\/span> datetime <span class=\"token keyword\">import<\/span> datetime<span class=\"token punctuation\">,<\/span> timezone<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> Any<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">ensure_parent_dir<\/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 boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    target <span class=\"token operator\">&#061;<\/span> Path<span class=\"token punctuation\">(<\/span>path<span class=\"token punctuation\">)<\/span><br \/>\n    target<span class=\"token punctuation\">.<\/span>parent<span class=\"token punctuation\">.<\/span>mkdir<span class=\"token punctuation\">(<\/span>parents<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><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\">now_iso<\/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\">return<\/span> datetime<span class=\"token punctuation\">.<\/span>now<span class=\"token punctuation\">(<\/span>timezone<span class=\"token punctuation\">.<\/span>utc<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>astimezone<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>isoformat<span class=\"token punctuation\">(<\/span>timespec<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;seconds&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">content_hash<\/span><span class=\"token punctuation\">(<\/span>value<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<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    raw <span class=\"token operator\">&#061;<\/span> json<span class=\"token punctuation\">.<\/span>dumps<span class=\"token punctuation\">(<\/span>value<span class=\"token punctuation\">,<\/span> ensure_ascii<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">False<\/span><span class=\"token punctuation\">,<\/span> sort_keys<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">return<\/span> hashlib<span class=\"token punctuation\">.<\/span>sha256<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\">format_duration<\/span><span class=\"token punctuation\">(<\/span>seconds<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">int<\/span> <span class=\"token operator\">|<\/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> seconds <span class=\"token keyword\">is<\/span> <span class=\"token boolean\">None<\/span><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\">try<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        total <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">(<\/span>seconds<span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">except<\/span> <span class=\"token punctuation\">(<\/span>TypeError<span class=\"token punctuation\">,<\/span> ValueError<span class=\"token punctuation\">)<\/span><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> total <span class=\"token operator\">&lt;<\/span> <span class=\"token number\">0<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;&#034;<\/span><\/p>\n<p>    hours <span class=\"token operator\">&#061;<\/span> total <span class=\"token operator\">\/\/<\/span> <span class=\"token number\">3600<\/span><br \/>\n    minutes <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">(<\/span>total <span class=\"token operator\">%<\/span> <span class=\"token number\">3600<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">\/\/<\/span> <span class=\"token number\">60<\/span><br \/>\n    secs <span class=\"token operator\">&#061;<\/span> total <span class=\"token operator\">%<\/span> <span class=\"token number\">60<\/span><\/p>\n<p>    <span class=\"token keyword\">if<\/span> hours<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>hours<span class=\"token punctuation\">:<\/span><span class=\"token format-spec\">02d<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">:<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>minutes<span class=\"token punctuation\">:<\/span><span class=\"token format-spec\">02d<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">:<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>secs<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>    <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>minutes<span class=\"token punctuation\">:<\/span><span class=\"token format-spec\">02d<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">:<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>secs<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><span class=\"token keyword\">def<\/span> <span class=\"token function\">setup_logger<\/span><span class=\"token punctuation\">(<\/span>log_path<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;logs\/spider.log&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> logging<span class=\"token punctuation\">.<\/span>Logger<span class=\"token punctuation\">:<\/span><br \/>\n    Path<span class=\"token punctuation\">(<\/span>log_path<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>parent<span class=\"token punctuation\">.<\/span>mkdir<span class=\"token punctuation\">(<\/span>parents<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><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>    logger <span class=\"token operator\">&#061;<\/span> logging<span class=\"token punctuation\">.<\/span>getLogger<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;course_tree_spider&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    logger<span class=\"token punctuation\">.<\/span>setLevel<span class=\"token punctuation\">(<\/span>logging<span class=\"token punctuation\">.<\/span>INFO<span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">if<\/span> logger<span class=\"token punctuation\">.<\/span>handlers<span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> logger<\/p>\n<p>    formatter <span class=\"token operator\">&#061;<\/span> logging<span class=\"token punctuation\">.<\/span>Formatter<span class=\"token punctuation\">(<\/span><br \/>\n        fmt<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;%(asctime)s | %(levelname)s | %(name)s | %(message)s&#034;<\/span><br \/>\n    <span class=\"token punctuation\">)<\/span><\/p>\n<p>    file_handler <span class=\"token operator\">&#061;<\/span> logging<span class=\"token punctuation\">.<\/span>FileHandler<span class=\"token punctuation\">(<\/span>log_path<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><br \/>\n    file_handler<span class=\"token punctuation\">.<\/span>setFormatter<span class=\"token punctuation\">(<\/span>formatter<span class=\"token punctuation\">)<\/span><\/p>\n<p>    console_handler <span class=\"token operator\">&#061;<\/span> logging<span class=\"token punctuation\">.<\/span>StreamHandler<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    console_handler<span class=\"token punctuation\">.<\/span>setFormatter<span class=\"token punctuation\">(<\/span>formatter<span class=\"token punctuation\">)<\/span><\/p>\n<p>    logger<span class=\"token punctuation\">.<\/span>addHandler<span class=\"token punctuation\">(<\/span>file_handler<span class=\"token punctuation\">)<\/span><br \/>\n    logger<span class=\"token punctuation\">.<\/span>addHandler<span class=\"token punctuation\">(<\/span>console_handler<span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">return<\/span> logger<\/p>\n<h4>6.5 Fetcher \u5b9e\u73b0<\/h4>\n<p>\u521b\u5efa crawler\/fetcher.py&#xff1a;<\/p>\n<p><span class=\"token keyword\">from<\/span> __future__ <span class=\"token keyword\">import<\/span> annotations<\/p>\n<p><span class=\"token keyword\">import<\/span> json<br \/>\n<span class=\"token keyword\">import<\/span> time<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> Any<\/p>\n<p><span class=\"token keyword\">import<\/span> requests<br \/>\n<span class=\"token keyword\">from<\/span> requests <span class=\"token keyword\">import<\/span> Response<span class=\"token punctuation\">,<\/span> Session<br \/>\n<span class=\"token keyword\">from<\/span> tenacity <span class=\"token keyword\">import<\/span> <span class=\"token punctuation\">(<\/span><br \/>\n    retry<span class=\"token punctuation\">,<\/span><br \/>\n    retry_if_exception_type<span class=\"token punctuation\">,<\/span><br \/>\n    stop_after_attempt<span class=\"token punctuation\">,<\/span><br \/>\n    wait_exponential<span class=\"token punctuation\">,<\/span><br \/>\n<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">from<\/span> crawler<span class=\"token punctuation\">.<\/span>config <span class=\"token keyword\">import<\/span> SpiderSettings<br \/>\n<span class=\"token keyword\">from<\/span> crawler<span class=\"token punctuation\">.<\/span>utils <span class=\"token keyword\">import<\/span> setup_logger<\/p>\n<p>logger <span class=\"token operator\">&#061;<\/span> setup_logger<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">FetchError<\/span><span class=\"token punctuation\">(<\/span>RuntimeError<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">pass<\/span><\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">CourseCatalogFetcher<\/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> settings<span class=\"token punctuation\">:<\/span> SpiderSettings<span class=\"token punctuation\">,<\/span> headers<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">dict<\/span><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 punctuation\">:<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>settings <span class=\"token operator\">&#061;<\/span> settings<br \/>\n        self<span class=\"token punctuation\">.<\/span>headers <span class=\"token operator\">&#061;<\/span> headers<br \/>\n        self<span class=\"token punctuation\">.<\/span>session<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>headers<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> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        mode <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>settings<span class=\"token punctuation\">.<\/span>mode<span class=\"token punctuation\">.<\/span>lower<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<p>        <span class=\"token keyword\">if<\/span> mode <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token string\">&#034;file&#034;<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> self<span class=\"token punctuation\">.<\/span>fetch_from_file<span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">.<\/span>settings<span class=\"token punctuation\">.<\/span>sample_file<span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">if<\/span> mode <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token string\">&#034;api&#034;<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> self<span class=\"token punctuation\">.<\/span>fetch_from_api<span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">.<\/span>settings<span class=\"token punctuation\">.<\/span>api_url<span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">raise<\/span> ValueError<span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\u672a\u77e5 mode: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>self<span class=\"token punctuation\">.<\/span>settings<span class=\"token punctuation\">.<\/span>mode<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#xff0c;\u53ea\u652f\u6301 file \u6216 api&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">fetch_from_file<\/span><span class=\"token punctuation\">(<\/span>self<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\">dict<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        file_path <span class=\"token operator\">&#061;<\/span> Path<span class=\"token punctuation\">(<\/span>path<span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> file_path<span class=\"token punctuation\">.<\/span>exists<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">raise<\/span> FileNotFoundError<span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\u793a\u4f8b JSON \u6587\u4ef6\u4e0d\u5b58\u5728: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>file_path<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        logger<span class=\"token punctuation\">.<\/span>info<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u8bfb\u53d6\u672c\u5730\u793a\u4f8b\u6570\u636e: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> file_path<span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">with<\/span> file_path<span class=\"token punctuation\">.<\/span><span class=\"token builtin\">open<\/span><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&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">as<\/span> f<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> json<span class=\"token punctuation\">.<\/span>load<span class=\"token punctuation\">(<\/span>f<span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token decorator annotation punctuation\">&#064;retry<\/span><span class=\"token punctuation\">(<\/span><br \/>\n        retry<span class=\"token operator\">&#061;<\/span>retry_if_exception_type<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">(<\/span>requests<span class=\"token punctuation\">.<\/span>RequestException<span class=\"token punctuation\">,<\/span> FetchError<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        stop<span class=\"token operator\">&#061;<\/span>stop_after_attempt<span class=\"token punctuation\">(<\/span><span class=\"token number\">3<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        wait<span class=\"token operator\">&#061;<\/span>wait_exponential<span class=\"token punctuation\">(<\/span>multiplier<span class=\"token operator\">&#061;<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">min<\/span><span class=\"token operator\">&#061;<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">max<\/span><span class=\"token operator\">&#061;<\/span><span class=\"token number\">10<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        reraise<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">fetch_from_api<\/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\">dict<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/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\">raise<\/span> ValueError<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;api_url \u4e0d\u80fd\u4e3a\u7a7a&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        logger<span class=\"token punctuation\">.<\/span>info<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u8bf7\u6c42\u516c\u5f00\u8bfe\u7a0b\u76ee\u5f55\u63a5\u53e3: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">)<\/span><\/p>\n<p>        time<span class=\"token punctuation\">.<\/span>sleep<span class=\"token punctuation\">(<\/span><span class=\"token builtin\">max<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">.<\/span>settings<span class=\"token punctuation\">.<\/span>request_interval<span class=\"token punctuation\">,<\/span> <span class=\"token number\">0<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        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            timeout<span class=\"token operator\">&#061;<\/span>self<span class=\"token punctuation\">.<\/span>settings<span class=\"token punctuation\">.<\/span>timeout<span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">)<\/span><\/p>\n<p>        self<span class=\"token punctuation\">.<\/span>_check_response<span class=\"token punctuation\">(<\/span>response<span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">try<\/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><br \/>\n        <span class=\"token keyword\">except<\/span> ValueError <span class=\"token keyword\">as<\/span> exc<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">raise<\/span> FetchError<span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\u54cd\u5e94\u4e0d\u662f\u5408\u6cd5 JSON: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>exc<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">from<\/span> exc<\/p>\n<p>    <span class=\"token decorator annotation punctuation\">&#064;staticmethod<\/span><br \/>\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">_check_response<\/span><span class=\"token punctuation\">(<\/span>response<span class=\"token punctuation\">:<\/span> Response<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        status <span class=\"token operator\">&#061;<\/span> response<span class=\"token punctuation\">.<\/span>status_code<\/p>\n<p>        <span class=\"token keyword\">if<\/span> status <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token number\">200<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span><\/p>\n<p>        <span class=\"token keyword\">if<\/span> status <span class=\"token keyword\">in<\/span> <span class=\"token punctuation\">{<\/span><span class=\"token number\">403<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">401<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">raise<\/span> FetchError<span class=\"token punctuation\">(<\/span><br \/>\n                <span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\u8bf7\u6c42\u88ab\u62d2\u7edd&#xff0c;\u72b6\u6001\u7801 <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>status<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">\u3002\u8bf7\u786e\u8ba4\u6570\u636e\u662f\u5426\u516c\u5f00&#xff0c;&#034;<\/span><\/span><br \/>\n                <span class=\"token string\">&#034;\u4e0d\u8981\u5c1d\u8bd5\u7ed5\u8fc7\u767b\u5f55\u3001\u6743\u9650\u6216\u4ed8\u8d39\u9650\u5236\u3002&#034;<\/span><br \/>\n            <span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">if<\/span> status <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token number\">429<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">raise<\/span> FetchError<span class=\"token punctuation\">(<\/span><br \/>\n                <span class=\"token string\">&#034;\u8bf7\u6c42\u8fc7\u4e8e\u9891\u7e41&#xff0c;\u72b6\u6001\u7801 429\u3002\u8bf7\u964d\u4f4e\u9891\u7387&#xff0c;\u589e\u52a0\u8bf7\u6c42\u95f4\u9694\u3002&#034;<\/span><br \/>\n            <span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">if<\/span> <span class=\"token number\">500<\/span> <span class=\"token operator\">&lt;&#061;<\/span> status <span class=\"token operator\">&lt;<\/span> <span class=\"token number\">600<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">raise<\/span> FetchError<span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\u670d\u52a1\u7aef\u9519\u8bef&#xff0c;\u72b6\u6001\u7801 <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>status<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#xff0c;\u7a0d\u540e\u53ef\u91cd\u8bd5\u3002&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">raise<\/span> FetchError<span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\u8bf7\u6c42\u5931\u8d25&#xff0c;\u72b6\u6001\u7801 <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>status<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#xff0c;\u54cd\u5e94\u7247\u6bb5: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>response<span class=\"token punctuation\">.<\/span>text<span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">:<\/span><span class=\"token format-spec\">200]<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u8fd9\u91cc\u7684\u8bf7\u6c42\u5c42\u6709\u51e0\u4e2a\u7ec6\u8282\u3002<\/p>\n<p>\u7b2c\u4e00&#xff0c;\u4f7f\u7528 requests.Session()\u3002\u5b83\u53ef\u4ee5\u590d\u7528\u8fde\u63a5&#xff0c;\u4e5f\u65b9\u4fbf\u7edf\u4e00\u8bbe\u7f6e headers\u3002<\/p>\n<p>\u7b2c\u4e8c&#xff0c;\u8bbe\u7f6e timeout\u3002\u6ca1\u6709 timeout \u7684\u8bf7\u6c42\u5728\u7f51\u7edc\u4e0d\u7a33\u5b9a\u65f6\u53ef\u80fd\u4e00\u76f4\u5361\u4f4f&#xff0c;\u8fd9\u5728\u5b9a\u65f6\u4efb\u52a1\u91cc\u5f88\u9ebb\u70e6\u3002<\/p>\n<p>\u7b2c\u4e09&#xff0c;\u52a0\u5165\u91cd\u8bd5\u548c\u6307\u6570\u9000\u907f\u3002\u7f51\u7edc\u6296\u52a8\u3001\u77ed\u6682 5xx \u9519\u8bef\u90fd\u53ef\u80fd\u51fa\u73b0&#xff0c;\u76f4\u63a5\u5931\u8d25\u5e76\u4e0d\u4f18\u96c5\u3002<\/p>\n<p>\u7b2c\u56db&#xff0c;\u5bf9 401\u3001403\u3001429 \u505a\u5355\u72ec\u63d0\u793a\u3002403 \u4e0d\u5e94\u8be5\u7b2c\u4e00\u53cd\u5e94\u5c31\u662f\u201c\u600e\u4e48\u7ed5\u8fc7\u201d&#xff0c;\u66f4\u5e94\u8be5\u5148\u786e\u8ba4\u6570\u636e\u662f\u5426\u516c\u5f00\u3001\u8bf7\u6c42\u662f\u5426\u8fc7\u5feb\u3001headers \u662f\u5426\u7f3a\u5931\u3001\u76ee\u6807\u7ad9\u70b9\u662f\u5426\u5141\u8bb8\u81ea\u52a8\u5316\u8bbf\u95ee\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\u662f\u672c\u6587\u91cd\u70b9\u3002\u8bfe\u7a0b\u76ee\u5f55\u6811\u6700\u5e38\u89c1\u7684\u95ee\u9898\u662f&#xff1a;\u53ea\u89e3\u6790\u5230\u7b2c\u4e00\u5c42\u7ae0\u8282&#xff0c;\u6f0f\u6389 children \u91cc\u7684\u5b50\u7ae0\u8282\u3002<\/p>\n<h4>7.1 \u539f\u59cb JSON \u7ed3\u6784\u5206\u6790<\/h4>\n<p>\u793a\u4f8b\u6570\u636e\u7684\u6838\u5fc3\u7ed3\u6784\u5982\u4e0b&#xff1a;<\/p>\n<p><span class=\"token punctuation\">{<\/span><br \/>\n  <span class=\"token string-property property\">&#034;data&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n    <span class=\"token string-property property\">&#034;course&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n      <span class=\"token string-property property\">&#034;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;python-1001&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n      <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;Python \u7f51\u7edc\u722c\u866b\u5b9e\u6218\u5165\u95e8&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n      <span class=\"token string-property property\">&#034;teacher&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n        <span class=\"token string-property property\">&#034;name&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;\u6797\u5ddd&#034;<\/span><br \/>\n      <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">,<\/span><br \/>\n      <span class=\"token string-property property\">&#034;tags&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;Python&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;\u722c\u866b&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;\u6570\u636e\u91c7\u96c6&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;\u5b9e\u6218&#034;<\/span><span class=\"token punctuation\">]<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string-property property\">&#034;catalog&#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;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;c1&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;\u7b2c 1 \u7ae0 \u8bfe\u7a0b\u4ecb\u7ecd\u4e0e\u73af\u5883\u51c6\u5907&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;duration&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">1800<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;preview&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token boolean\">true<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;children&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n      <span class=\"token punctuation\">}<\/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>\u76ee\u5f55\u8282\u70b9\u53ef\u80fd\u6709\u5f88\u591a\u53d8\u4f53&#xff0c;\u6bd4\u5982&#xff1a;<\/p>\n<p><span class=\"token punctuation\">{<\/span><br \/>\n  <span class=\"token string-property property\">&#034;chapterId&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;xxx&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n  <span class=\"token string-property property\">&#034;chapterName&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;xxx&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n  <span class=\"token string-property property\">&#034;trial&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span><br \/>\n  <span class=\"token string-property property\">&#034;length&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;12:30&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n  <span class=\"token string-property property\">&#034;childList&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n<span class=\"token punctuation\">}<\/span><\/p>\n<p>\u6240\u4ee5\u89e3\u6790\u5668\u4e0d\u80fd\u5199\u5f97\u592a\u6b7b\u3002\u6211\u7684\u4e60\u60ef\u662f\u5199\u51e0\u4e2a\u5c0f\u5de5\u5177\u51fd\u6570&#xff0c;\u517c\u5bb9\u4e0d\u540c\u5b57\u6bb5\u540d&#xff1a;<\/p>\n<ul>\n<li>pick_str<\/li>\n<li>pick_bool<\/li>\n<li>pick_int<\/li>\n<li>normalize_tags<\/li>\n<li>parse_duration_to_seconds<\/li>\n<\/ul>\n<h4>7.2 \u6570\u636e\u6a21\u578b<\/h4>\n<p>\u521b\u5efa crawler\/parser.py&#xff1a;<\/p>\n<p><span class=\"token keyword\">from<\/span> __future__ <span class=\"token keyword\">import<\/span> annotations<\/p>\n<p><span class=\"token keyword\">from<\/span> dataclasses <span class=\"token keyword\">import<\/span> asdict<span class=\"token punctuation\">,<\/span> dataclass<br \/>\n<span class=\"token keyword\">from<\/span> typing <span class=\"token keyword\">import<\/span> Any<span class=\"token punctuation\">,<\/span> Iterable<\/p>\n<p><span class=\"token keyword\">from<\/span> crawler<span class=\"token punctuation\">.<\/span>utils <span class=\"token keyword\">import<\/span> content_hash<span class=\"token punctuation\">,<\/span> format_duration<span class=\"token punctuation\">,<\/span> now_iso<\/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\">ChapterRecord<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    course_id<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><br \/>\n    course_title<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><br \/>\n    teacher<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><br \/>\n    tags<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><br \/>\n    chapter_id<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><br \/>\n    chapter_title<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><br \/>\n    parent_id<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><br \/>\n    level<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">int<\/span><br \/>\n    is_preview<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">bool<\/span><br \/>\n    duration_seconds<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">int<\/span> <span class=\"token operator\">|<\/span> <span class=\"token boolean\">None<\/span><br \/>\n    duration_text<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><br \/>\n    sort_path<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><br \/>\n    source_url<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><br \/>\n    crawled_at<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><br \/>\n    row_hash<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">to_dict<\/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 builtin\">dict<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> asdict<span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">pick_value<\/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 builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> keys<span class=\"token punctuation\">:<\/span> Iterable<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> default<span class=\"token punctuation\">:<\/span> Any <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> Any<span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">for<\/span> key <span class=\"token keyword\">in<\/span> keys<span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> key <span class=\"token keyword\">in<\/span> data <span class=\"token keyword\">and<\/span> data<span class=\"token punctuation\">[<\/span>key<span class=\"token punctuation\">]<\/span> <span class=\"token keyword\">not<\/span> <span class=\"token keyword\">in<\/span> <span class=\"token punctuation\">(<\/span><span class=\"token boolean\">None<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> data<span class=\"token punctuation\">[<\/span>key<span class=\"token punctuation\">]<\/span><br \/>\n    <span class=\"token keyword\">return<\/span> default<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">pick_str<\/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 builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> keys<span class=\"token punctuation\">:<\/span> Iterable<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> default<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;&#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    value <span class=\"token operator\">&#061;<\/span> pick_value<span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">,<\/span> keys<span class=\"token punctuation\">,<\/span> default<span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">if<\/span> value <span class=\"token keyword\">is<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> default<br \/>\n    <span class=\"token keyword\">return<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">(<\/span>value<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\">def<\/span> <span class=\"token function\">pick_bool<\/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 builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> keys<span class=\"token punctuation\">:<\/span> Iterable<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> default<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">bool<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token boolean\">False<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">bool<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    value <span class=\"token operator\">&#061;<\/span> pick_value<span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">,<\/span> keys<span class=\"token punctuation\">,<\/span> default<span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">if<\/span> <span class=\"token builtin\">isinstance<\/span><span class=\"token punctuation\">(<\/span>value<span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">bool<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> value<\/p>\n<p>    <span class=\"token keyword\">if<\/span> <span class=\"token builtin\">isinstance<\/span><span class=\"token punctuation\">(<\/span>value<span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> value <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token number\">1<\/span><\/p>\n<p>    <span class=\"token keyword\">if<\/span> <span class=\"token builtin\">isinstance<\/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 punctuation\">:<\/span><br \/>\n        normalized <span class=\"token operator\">&#061;<\/span> value<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>lower<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> normalized <span class=\"token keyword\">in<\/span> <span class=\"token punctuation\">{<\/span><span class=\"token string\">&#034;1&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;true&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;yes&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;y&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;\u8bd5\u770b&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;free&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;preview&#034;<\/span><span class=\"token punctuation\">}<\/span><\/p>\n<p>    <span class=\"token keyword\">return<\/span> default<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">parse_duration_to_seconds<\/span><span class=\"token punctuation\">(<\/span>value<span class=\"token punctuation\">:<\/span> Any<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 operator\">|<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">if<\/span> value <span class=\"token keyword\">is<\/span> <span class=\"token boolean\">None<\/span> <span class=\"token keyword\">or<\/span> value <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> <span class=\"token boolean\">None<\/span><\/p>\n<p>    <span class=\"token keyword\">if<\/span> <span class=\"token builtin\">isinstance<\/span><span class=\"token punctuation\">(<\/span>value<span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> value <span class=\"token keyword\">if<\/span> value <span class=\"token operator\">&gt;&#061;<\/span> <span class=\"token number\">0<\/span> <span class=\"token keyword\">else<\/span> <span class=\"token boolean\">None<\/span><\/p>\n<p>    <span class=\"token keyword\">if<\/span> <span class=\"token builtin\">isinstance<\/span><span class=\"token punctuation\">(<\/span>value<span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">float<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">(<\/span>value<span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">if<\/span> value <span class=\"token operator\">&gt;&#061;<\/span> <span class=\"token number\">0<\/span> <span class=\"token keyword\">else<\/span> <span class=\"token boolean\">None<\/span><\/p>\n<p>    <span class=\"token keyword\">if<\/span> <span class=\"token builtin\">isinstance<\/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 punctuation\">:<\/span><br \/>\n        text <span class=\"token operator\">&#061;<\/span> value<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> text<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> <span class=\"token boolean\">None<\/span><\/p>\n<p>        <span class=\"token keyword\">if<\/span> text<span class=\"token punctuation\">.<\/span>isdigit<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\">int<\/span><span class=\"token punctuation\">(<\/span>text<span class=\"token punctuation\">)<\/span><\/p>\n<p>        parts <span class=\"token operator\">&#061;<\/span> text<span class=\"token punctuation\">.<\/span>split<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 builtin\">all<\/span><span class=\"token punctuation\">(<\/span>part<span class=\"token punctuation\">.<\/span>isdigit<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">for<\/span> part <span class=\"token keyword\">in<\/span> parts<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>parts<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token number\">2<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                minutes<span class=\"token punctuation\">,<\/span> seconds <span class=\"token operator\">&#061;<\/span> parts<br \/>\n                <span class=\"token keyword\">return<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">(<\/span>minutes<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">*<\/span> <span class=\"token number\">60<\/span> <span class=\"token operator\">&#043;<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">(<\/span>seconds<span class=\"token punctuation\">)<\/span><\/p>\n<p>            <span class=\"token keyword\">if<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>parts<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token number\">3<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                hours<span class=\"token punctuation\">,<\/span> minutes<span class=\"token punctuation\">,<\/span> seconds <span class=\"token operator\">&#061;<\/span> parts<br \/>\n                <span class=\"token keyword\">return<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">(<\/span>hours<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">*<\/span> <span class=\"token number\">3600<\/span> <span class=\"token operator\">&#043;<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">(<\/span>minutes<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">*<\/span> <span class=\"token number\">60<\/span> <span class=\"token operator\">&#043;<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">(<\/span>seconds<span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">return<\/span> <span class=\"token boolean\">None<\/span><\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">normalize_tags<\/span><span class=\"token punctuation\">(<\/span>value<span class=\"token punctuation\">:<\/span> Any<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> value <span class=\"token keyword\">is<\/span> <span class=\"token boolean\">None<\/span><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> <span class=\"token builtin\">isinstance<\/span><span class=\"token punctuation\">(<\/span>value<span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;,&#034;<\/span><span class=\"token punctuation\">.<\/span>join<span class=\"token punctuation\">(<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">(<\/span>item<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">for<\/span> item <span class=\"token keyword\">in<\/span> value <span class=\"token keyword\">if<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">(<\/span>item<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\">if<\/span> <span class=\"token builtin\">isinstance<\/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 punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> value<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">return<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">(<\/span>value<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\">def<\/span> <span class=\"token function\">find_first_list<\/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 builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> keys<span class=\"token punctuation\">:<\/span> Iterable<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\">list<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">for<\/span> key <span class=\"token keyword\">in<\/span> keys<span class=\"token punctuation\">:<\/span><br \/>\n        value <span class=\"token operator\">&#061;<\/span> data<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> <span class=\"token builtin\">isinstance<\/span><span class=\"token punctuation\">(<\/span>value<span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> <span class=\"token punctuation\">[<\/span>item <span class=\"token keyword\">for<\/span> item <span class=\"token keyword\">in<\/span> value <span class=\"token keyword\">if<\/span> <span class=\"token builtin\">isinstance<\/span><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    <span class=\"token keyword\">return<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">CourseCatalogParser<\/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> source_url<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>source_url <span class=\"token operator\">&#061;<\/span> source_url<\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">parse<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> payload<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<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\">list<\/span><span class=\"token punctuation\">[<\/span>ChapterRecord<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        data <span class=\"token operator\">&#061;<\/span> payload<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;data&#034;<\/span><span class=\"token punctuation\">,<\/span> payload<span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> <span class=\"token builtin\">isinstance<\/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 punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">raise<\/span> ValueError<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;payload.data \u4e0d\u662f\u5bf9\u8c61\u7ed3\u6784&#xff0c;\u65e0\u6cd5\u89e3\u6790&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        course <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>_extract_course<span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">)<\/span><br \/>\n        catalog <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>_extract_catalog<span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> catalog<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>        records<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">[<\/span>ChapterRecord<span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>_walk_nodes<span class=\"token punctuation\">(<\/span><br \/>\n            nodes<span class=\"token operator\">&#061;<\/span>catalog<span class=\"token punctuation\">,<\/span><br \/>\n            course<span class=\"token operator\">&#061;<\/span>course<span class=\"token punctuation\">,<\/span><br \/>\n            records<span class=\"token operator\">&#061;<\/span>records<span class=\"token punctuation\">,<\/span><br \/>\n            parent_id<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            level<span class=\"token operator\">&#061;<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            prefix<span class=\"token operator\">&#061;<\/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        <span class=\"token keyword\">return<\/span> records<\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">_extract_course<\/span><span class=\"token punctuation\">(<\/span>self<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 builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<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\">dict<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        course <span class=\"token operator\">&#061;<\/span> data<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;course&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> data<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;courseInfo&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> data<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;detail&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> data<\/p>\n<p>        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> <span class=\"token builtin\">isinstance<\/span><span class=\"token punctuation\">(<\/span>course<span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            course <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><span class=\"token punctuation\">}<\/span><\/p>\n<p>        teacher_value <span class=\"token operator\">&#061;<\/span> pick_value<span class=\"token punctuation\">(<\/span>course<span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;teacher&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;lecturer&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;instructor&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">if<\/span> <span class=\"token builtin\">isinstance<\/span><span class=\"token punctuation\">(<\/span>teacher_value<span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            teacher <span class=\"token operator\">&#061;<\/span> pick_str<span class=\"token punctuation\">(<\/span>teacher_value<span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;name&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;nickname&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;title&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">else<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            teacher <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">(<\/span>teacher_value<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">if<\/span> teacher_value <span class=\"token keyword\">else<\/span> <span class=\"token string\">&#034;&#034;<\/span><\/p>\n<p>        <span class=\"token keyword\">return<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n            <span class=\"token string\">&#034;course_id&#034;<\/span><span class=\"token punctuation\">:<\/span> pick_str<span class=\"token punctuation\">(<\/span>course<span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;id&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;course_id&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;courseId&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;course_title&#034;<\/span><span class=\"token punctuation\">:<\/span> pick_str<span class=\"token punctuation\">(<\/span>course<span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;title&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;name&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;course_title&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;courseName&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;teacher&#034;<\/span><span class=\"token punctuation\">:<\/span> teacher<span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;tags&#034;<\/span><span class=\"token punctuation\">:<\/span> normalize_tags<span class=\"token punctuation\">(<\/span>pick_value<span class=\"token punctuation\">(<\/span>course<span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;tags&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;tagList&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;labels&#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><span class=\"token punctuation\">)<\/span><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\">_extract_catalog<\/span><span class=\"token punctuation\">(<\/span>self<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 builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<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\">list<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        catalog <span class=\"token operator\">&#061;<\/span> find_first_list<span class=\"token punctuation\">(<\/span><br \/>\n            data<span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token punctuation\">[<\/span><br \/>\n                <span class=\"token string\">&#034;catalog&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;chapters&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;chapterList&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;lessons&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;items&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;tree&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;children&#034;<\/span><span class=\"token punctuation\">,<\/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 keyword\">return<\/span> catalog<\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">_walk_nodes<\/span><span class=\"token punctuation\">(<\/span><br \/>\n        self<span class=\"token punctuation\">,<\/span><br \/>\n        nodes<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        course<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        records<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">[<\/span>ChapterRecord<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        parent_id<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        level<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        prefix<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">int<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <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 keyword\">for<\/span> index<span class=\"token punctuation\">,<\/span> node <span class=\"token keyword\">in<\/span> <span class=\"token builtin\">enumerate<\/span><span class=\"token punctuation\">(<\/span>nodes<span class=\"token punctuation\">,<\/span> start<span class=\"token operator\">&#061;<\/span><span class=\"token number\">1<\/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> <span class=\"token builtin\">isinstance<\/span><span class=\"token punctuation\">(<\/span>node<span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                <span class=\"token keyword\">continue<\/span><\/p>\n<p>            sort_path_parts <span class=\"token operator\">&#061;<\/span> prefix <span class=\"token operator\">&#043;<\/span> <span class=\"token punctuation\">[<\/span>index<span class=\"token punctuation\">]<\/span><br \/>\n            sort_path <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 builtin\">str<\/span><span class=\"token punctuation\">(<\/span>part<span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">for<\/span> part <span class=\"token keyword\">in<\/span> sort_path_parts<span class=\"token punctuation\">)<\/span><\/p>\n<p>            chapter_id <span class=\"token operator\">&#061;<\/span> pick_str<span class=\"token punctuation\">(<\/span><br \/>\n                node<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;id&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;chapter_id&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;chapterId&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;lesson_id&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;lessonId&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;nodeId&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                default<span class=\"token operator\">&#061;<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;auto-<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>sort_path<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token punctuation\">)<\/span><\/p>\n<p>            title <span class=\"token operator\">&#061;<\/span> pick_str<span class=\"token punctuation\">(<\/span><br \/>\n                node<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;title&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;name&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;chapter_title&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;chapterName&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;lessonName&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                default<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token punctuation\">)<\/span><\/p>\n<p>            duration_seconds <span class=\"token operator\">&#061;<\/span> parse_duration_to_seconds<span class=\"token punctuation\">(<\/span><br \/>\n                pick_value<span class=\"token punctuation\">(<\/span><br \/>\n                    node<span class=\"token punctuation\">,<\/span><br \/>\n                    <span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;duration&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;duration_seconds&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;durationSeconds&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;length&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;time&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                    <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token punctuation\">)<\/span><\/p>\n<p>            is_preview <span class=\"token operator\">&#061;<\/span> pick_bool<span class=\"token punctuation\">(<\/span><br \/>\n                node<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;preview&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;is_preview&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;isPreview&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;trial&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;free&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                default<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">False<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token punctuation\">)<\/span><\/p>\n<p>            base <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n                <span class=\"token string\">&#034;course_id&#034;<\/span><span class=\"token punctuation\">:<\/span> course<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;course_id&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;course_title&#034;<\/span><span class=\"token punctuation\">:<\/span> course<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;course_title&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;teacher&#034;<\/span><span class=\"token punctuation\">:<\/span> course<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;teacher&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;tags&#034;<\/span><span class=\"token punctuation\">:<\/span> course<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;tags&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;chapter_id&#034;<\/span><span class=\"token punctuation\">:<\/span> chapter_id<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;chapter_title&#034;<\/span><span class=\"token punctuation\">:<\/span> title<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;parent_id&#034;<\/span><span class=\"token punctuation\">:<\/span> parent_id<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;level&#034;<\/span><span class=\"token punctuation\">:<\/span> level<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;is_preview&#034;<\/span><span class=\"token punctuation\">:<\/span> is_preview<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;duration_seconds&#034;<\/span><span class=\"token punctuation\">:<\/span> duration_seconds<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;duration_text&#034;<\/span><span class=\"token punctuation\">:<\/span> format_duration<span class=\"token punctuation\">(<\/span>duration_seconds<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;sort_path&#034;<\/span><span class=\"token punctuation\">:<\/span> sort_path<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;source_url&#034;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>source_url<span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token punctuation\">}<\/span><\/p>\n<p>            row_hash <span class=\"token operator\">&#061;<\/span> content_hash<span class=\"token punctuation\">(<\/span>base<span class=\"token punctuation\">)<\/span><\/p>\n<p>            record <span class=\"token operator\">&#061;<\/span> ChapterRecord<span class=\"token punctuation\">(<\/span><br \/>\n                <span class=\"token operator\">**<\/span>base<span class=\"token punctuation\">,<\/span><br \/>\n                crawled_at<span class=\"token operator\">&#061;<\/span>now_iso<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                row_hash<span class=\"token operator\">&#061;<\/span>row_hash<span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token punctuation\">)<\/span><br \/>\n            records<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span>record<span class=\"token punctuation\">)<\/span><\/p>\n<p>            children <span class=\"token operator\">&#061;<\/span> find_first_list<span class=\"token punctuation\">(<\/span><br \/>\n                node<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;children&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;childList&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;subChapters&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;sections&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;lessons&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token punctuation\">)<\/span><\/p>\n<p>            <span class=\"token keyword\">if<\/span> children<span class=\"token punctuation\">:<\/span><br \/>\n                self<span class=\"token punctuation\">.<\/span>_walk_nodes<span class=\"token punctuation\">(<\/span><br \/>\n                    nodes<span class=\"token operator\">&#061;<\/span>children<span class=\"token punctuation\">,<\/span><br \/>\n                    course<span class=\"token operator\">&#061;<\/span>course<span class=\"token punctuation\">,<\/span><br \/>\n                    records<span class=\"token operator\">&#061;<\/span>records<span class=\"token punctuation\">,<\/span><br \/>\n                    parent_id<span class=\"token operator\">&#061;<\/span>chapter_id<span class=\"token punctuation\">,<\/span><br \/>\n                    level<span class=\"token operator\">&#061;<\/span>level <span class=\"token operator\">&#043;<\/span> <span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                    prefix<span class=\"token operator\">&#061;<\/span>sort_path_parts<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token punctuation\">)<\/span><\/p>\n<h4>7.3 \u89e3\u6790\u65b9\u5f0f\u8bf4\u660e<\/h4>\n<p>\u672c\u6587\u4e3b\u7ebf\u4f7f\u7528 JSON \u89e3\u6790\u3002\u539f\u56e0\u662f\u76ee\u6807\u6570\u636e\u672c\u8eab\u5c31\u662f\u52a8\u6001\u9875\u9762\u80cc\u540e\u7684 JSON \u6570\u636e&#xff0c;\u4e0d\u9700\u8981\u5148\u628a\u5b83\u6e32\u67d3\u6210 HTML \u518d\u89e3\u6790\u3002<\/p>\n<p>\u5982\u679c\u76ee\u6807\u7ad9\u70b9\u662f\u9759\u6001 HTML&#xff0c;\u53ef\u4ee5\u4f7f\u7528&#xff1a;<\/p>\n<ul>\n<li>BeautifulSoup<\/li>\n<li>XPath<\/li>\n<li>CSS Selector<\/li>\n<li>lxml<\/li>\n<\/ul>\n<p>\u5982\u679c\u76ee\u6807\u7ad9\u70b9\u662f\u52a8\u6001\u9875\u9762&#xff0c;\u5efa\u8bae\u5148\u5b9a\u4f4d\u63a5\u53e3\u3002\u5b9e\u5728\u65e0\u6cd5\u5b9a\u4f4d\u65f6&#xff0c;\u518d\u7528 Playwright\u3002<\/p>\n<h4>7.4 \u5217\u8868\u9875\u5982\u4f55\u62ff\u8be6\u60c5\u94fe\u63a5<\/h4>\n<p>\u6709\u4e9b\u5e73\u53f0\u4e0d\u662f\u76f4\u63a5\u7ed9\u4e00\u4e2a\u8bfe\u7a0b\u63a5\u53e3&#xff0c;\u800c\u662f\u5148\u6709\u8bfe\u7a0b\u5217\u8868\u9875\u3002\u5178\u578b\u6d41\u7a0b\u5982\u4e0b&#xff1a;<\/p>\n<p>\u8bfe\u7a0b\u5217\u8868\u63a5\u53e3 \u2192 \u83b7\u53d6 course_id \/ detail_url \u2192 \u9010\u4e2a\u8bf7\u6c42\u8bfe\u7a0b\u76ee\u5f55\u63a5\u53e3<\/p>\n<p>\u793a\u4f8b\u7ed3\u6784\u53ef\u80fd\u662f&#xff1a;<\/p>\n<p><span class=\"token punctuation\">{<\/span><br \/>\n  <span class=\"token string-property property\">&#034;data&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n    <span class=\"token string-property property\">&#034;list&#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;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;python-1001&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;Python \u7f51\u7edc\u722c\u866b\u5b9e\u6218\u5165\u95e8&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;detailUrl&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;https:\/\/example.com\/course\/python-1001&#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;id&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;data-2001&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;\u6570\u636e\u5206\u6790\u57fa\u7840&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string-property property\">&#034;detailUrl&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;https:\/\/example.com\/course\/data-2001&#034;<\/span><br \/>\n      <span class=\"token punctuation\">}<\/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>\u8fd9\u79cd\u60c5\u51b5\u4e0b\u53ef\u4ee5\u52a0\u4e00\u4e2a\u5217\u8868\u89e3\u6790\u5668&#xff1a;<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">parse_course_list<\/span><span class=\"token punctuation\">(<\/span>payload<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> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    data <span class=\"token operator\">&#061;<\/span> payload<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;data&#034;<\/span><span class=\"token punctuation\">,<\/span> payload<span class=\"token punctuation\">)<\/span><br \/>\n    items <span class=\"token operator\">&#061;<\/span> data<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;list&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> data<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 keyword\">or<\/span> data<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;courses&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><\/p>\n<p>    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> item <span class=\"token keyword\">in<\/span> items<span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> <span class=\"token builtin\">isinstance<\/span><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            <span class=\"token keyword\">continue<\/span><\/p>\n<p>        course_id <span class=\"token operator\">&#061;<\/span> item<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;id&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> item<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;courseId&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> item<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;course_id&#034;<\/span><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;detailUrl&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/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 keyword\">or<\/span> item<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;link&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        title <span class=\"token operator\">&#061;<\/span> item<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;title&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> item<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;name&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#034;&#034;<\/span><\/p>\n<p>        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> course_id <span class=\"token keyword\">and<\/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>        result<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span><br \/>\n            <span class=\"token punctuation\">{<\/span><br \/>\n                <span class=\"token string\">&#034;course_id&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">(<\/span>course_id <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><span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;title&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">(<\/span>title<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><br \/>\n                <span class=\"token string\">&#034;detail_url&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">(<\/span>detail_url <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><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token punctuation\">}<\/span><br \/>\n        <span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">return<\/span> result<\/p>\n<p>\u5982\u679c\u76ee\u5f55\u63a5\u53e3\u9700\u8981 course_id&#xff0c;\u5c31\u628a\u5b83\u62fc\u8fdb URL&#xff1a;<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">build_catalog_url<\/span><span class=\"token punctuation\">(<\/span>template<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> course_id<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> template<span class=\"token punctuation\">.<\/span><span class=\"token builtin\">format<\/span><span class=\"token punctuation\">(<\/span>course_id<span class=\"token operator\">&#061;<\/span>course_id<span class=\"token punctuation\">)<\/span><\/p>\n<p>\u4f8b\u5982&#xff1a;<\/p>\n<p>url <span class=\"token operator\">&#061;<\/span> build_catalog_url<span class=\"token punctuation\">(<\/span><br \/>\n    <span class=\"token string\">&#034;https:\/\/example.com\/api\/course\/catalog?course_id&#061;{course_id}&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;python-1001&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n<span class=\"token punctuation\">)<\/span><\/p>\n<h4>7.5 \u8be6\u60c5\u9875\u5982\u4f55\u62bd\u5b57\u6bb5<\/h4>\n<p>\u8be6\u60c5\u9875\u5b57\u6bb5\u901a\u5e38\u5206\u4e24\u90e8\u5206\u3002<\/p>\n<p>\u7b2c\u4e00\u90e8\u5206\u662f\u8bfe\u7a0b\u7ea7\u5b57\u6bb5&#xff1a;<\/p>\n<ul>\n<li>\u8bfe\u7a0b ID<\/li>\n<li>\u8bfe\u7a0b\u540d\u79f0<\/li>\n<li>\u8bb2\u5e08<\/li>\n<li>\u6807\u7b7e<\/li>\n<\/ul>\n<p>\u7b2c\u4e8c\u90e8\u5206\u662f\u7ae0\u8282\u7ea7\u5b57\u6bb5&#xff1a;<\/p>\n<ul>\n<li>\u7ae0\u8282 ID<\/li>\n<li>\u7ae0\u8282\u6807\u9898<\/li>\n<li>\u662f\u5426\u8bd5\u770b<\/li>\n<li>\u65f6\u957f<\/li>\n<li>\u7236\u7ae0\u8282<\/li>\n<li>\u5c42\u7ea7<\/li>\n<\/ul>\n<p>\u8bfe\u7a0b\u7ea7\u5b57\u6bb5\u53ea\u89e3\u6790\u4e00\u6b21&#xff0c;\u7ae0\u8282\u5b57\u6bb5\u9012\u5f52\u89e3\u6790\u591a\u6b21\u3002\u6bcf\u4e2a\u7ae0\u8282\u8bb0\u5f55\u90fd\u4f1a\u5e26\u4e0a\u8bfe\u7a0b\u5b57\u6bb5&#xff0c;\u8fd9\u6837\u5bfc\u51fa CSV \u540e\u66f4\u5bb9\u6613\u505a\u7edf\u8ba1\u3002<\/p>\n<h4>7.6 \u7f3a\u5931\u5b57\u6bb5\u600e\u4e48\u529e<\/h4>\n<p>\u5b9e\u9645\u9879\u76ee\u91cc&#xff0c;\u7f3a\u5b57\u6bb5\u975e\u5e38\u5e38\u89c1&#xff1a;<\/p>\n<ul>\n<li>\u67d0\u4e9b\u7ae0\u8282\u6ca1\u6709\u65f6\u957f\u3002<\/li>\n<li>\u67d0\u4e9b\u8bfe\u7a0b\u6ca1\u6709\u6807\u7b7e\u3002<\/li>\n<li>\u67d0\u4e9b\u7236\u8282\u70b9\u53ea\u662f\u5206\u7c7b&#xff0c;\u6ca1\u6709\u8bd5\u770b\u72b6\u6001\u3002<\/li>\n<li>\u67d0\u4e9b\u8282\u70b9\u6ca1\u6709 ID\u3002<\/li>\n<\/ul>\n<p>\u672c\u6587\u5904\u7406\u65b9\u5f0f\u5982\u4e0b&#xff1a;<\/p>\n<table>\n<tr>\u7f3a\u5931\u5b57\u6bb5\u5904\u7406\u65b9\u5f0f<\/tr>\n<tbody>\n<tr>\n<td>chapter_id \u7f3a\u5931<\/td>\n<td>\u4f7f\u7528 auto-{sort_path} \u751f\u6210\u4e34\u65f6 ID<\/td>\n<\/tr>\n<tr>\n<td>duration \u7f3a\u5931<\/td>\n<td>\u7f6e\u4e3a None<\/td>\n<\/tr>\n<tr>\n<td>preview \u7f3a\u5931<\/td>\n<td>\u9ed8\u8ba4 False<\/td>\n<\/tr>\n<tr>\n<td>tags \u7f3a\u5931<\/td>\n<td>\u7a7a\u5b57\u7b26\u4e32<\/td>\n<\/tr>\n<tr>\n<td>teacher \u7f3a\u5931<\/td>\n<td>\u7a7a\u5b57\u7b26\u4e32<\/td>\n<\/tr>\n<tr>\n<td>children \u7f3a\u5931<\/td>\n<td>\u5f53\u4f5c\u7a7a\u5217\u8868<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>\u8fd9\u79cd\u7b56\u7565\u7684\u597d\u5904\u662f\u4e0d\u4e2d\u65ad\u91c7\u96c6\u3002\u540e\u7eed\u5982\u679c\u9700\u8981\u66f4\u4e25\u683c\u7684\u6570\u636e\u8d28\u91cf\u6821\u9a8c&#xff0c;\u53ef\u4ee5\u5728\u6e05\u6d17\u5c42\u589e\u52a0\u89c4\u5219\u3002<\/p>\n<hr \/>\n<h3>8\ufe0f\u20e3 \u6570\u636e\u5b58\u50a8\u4e0e\u5bfc\u51fa&#xff08;Storage&#xff09;<\/h3>\n<p>\u672c\u6587\u540c\u65f6\u5b9e\u73b0 CSV\u3001JSON\u3001SQLite \u4e09\u79cd\u5b58\u50a8\u65b9\u5f0f\u3002\u8d77\u6b65\u9636\u6bb5 CSV \u6700\u65b9\u4fbf&#xff0c;\u8c03\u8bd5\u9636\u6bb5 JSON \u6700\u6e05\u6670&#xff0c;\u957f\u671f\u67e5\u8be2 SQLite \u66f4\u7a33\u3002<\/p>\n<h4>8.1 \u5b57\u6bb5\u6620\u5c04\u8868<\/h4>\n<table>\n<tr>\u5b57\u6bb5\u540d\u7c7b\u578b\u793a\u4f8b\u503c<\/tr>\n<tbody>\n<tr>\n<td>course_id<\/td>\n<td align=\"right\">str<\/td>\n<td>python-1001<\/td>\n<\/tr>\n<tr>\n<td>course_title<\/td>\n<td align=\"right\">str<\/td>\n<td>Python \u7f51\u7edc\u722c\u866b\u5b9e\u6218\u5165\u95e8<\/td>\n<\/tr>\n<tr>\n<td>teacher<\/td>\n<td align=\"right\">str<\/td>\n<td>\u6797\u5ddd<\/td>\n<\/tr>\n<tr>\n<td>tags<\/td>\n<td align=\"right\">str<\/td>\n<td>Python,\u722c\u866b,\u6570\u636e\u91c7\u96c6,\u5b9e\u6218<\/td>\n<\/tr>\n<tr>\n<td>chapter_id<\/td>\n<td align=\"right\">str<\/td>\n<td>c3-3-1<\/td>\n<\/tr>\n<tr>\n<td>chapter_title<\/td>\n<td align=\"right\">str<\/td>\n<td>3.3.1 \u9012\u5f52\u51fd\u6570\u8bbe\u8ba1<\/td>\n<\/tr>\n<tr>\n<td>parent_id<\/td>\n<td align=\"right\">str<\/td>\n<td>c3-3<\/td>\n<\/tr>\n<tr>\n<td>level<\/td>\n<td align=\"right\">int<\/td>\n<td>3<\/td>\n<\/tr>\n<tr>\n<td>is_preview<\/td>\n<td align=\"right\">bool<\/td>\n<td>true<\/td>\n<\/tr>\n<tr>\n<td>duration_seconds<\/td>\n<td align=\"right\">int<\/td>\n<td>600<\/td>\n<\/tr>\n<tr>\n<td>duration_text<\/td>\n<td align=\"right\">str<\/td>\n<td>10:00<\/td>\n<\/tr>\n<tr>\n<td>sort_path<\/td>\n<td align=\"right\">str<\/td>\n<td>3.3.1<\/td>\n<\/tr>\n<tr>\n<td>source_url<\/td>\n<td align=\"right\">str<\/td>\n<td>https:\/\/example.com\/course\/python-1001<\/td>\n<\/tr>\n<tr>\n<td>crawled_at<\/td>\n<td align=\"right\">str<\/td>\n<td>2026-06-12T10:30:00&#043;03:00<\/td>\n<\/tr>\n<tr>\n<td>row_hash<\/td>\n<td align=\"right\">str<\/td>\n<td>sha256 hash<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h4>8.2 Storage \u5b9e\u73b0<\/h4>\n<p>\u521b\u5efa crawler\/storage.py&#xff1a;<\/p>\n<p><span class=\"token keyword\">from<\/span> __future__ <span class=\"token keyword\">import<\/span> annotations<\/p>\n<p><span class=\"token keyword\">import<\/span> csv<br \/>\n<span class=\"token keyword\">import<\/span> json<br \/>\n<span class=\"token keyword\">import<\/span> sqlite3<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> Any<\/p>\n<p><span class=\"token keyword\">from<\/span> crawler<span class=\"token punctuation\">.<\/span>parser <span class=\"token keyword\">import<\/span> ChapterRecord<br \/>\n<span class=\"token keyword\">from<\/span> crawler<span class=\"token punctuation\">.<\/span>utils <span class=\"token keyword\">import<\/span> ensure_parent_dir<span class=\"token punctuation\">,<\/span> setup_logger<\/p>\n<p>logger <span class=\"token operator\">&#061;<\/span> setup_logger<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>FIELDNAMES <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><br \/>\n    <span class=\"token string\">&#034;course_id&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;course_title&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;teacher&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;tags&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;chapter_id&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;chapter_title&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;parent_id&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;level&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;is_preview&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;duration_seconds&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;duration_text&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;sort_path&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;source_url&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;crawled_at&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string\">&#034;row_hash&#034;<\/span><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\">deduplicate_records<\/span><span class=\"token punctuation\">(<\/span>records<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">[<\/span>ChapterRecord<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\">list<\/span><span class=\"token punctuation\">[<\/span>ChapterRecord<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    seen<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">set<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">tuple<\/span><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 builtin\">str<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">set<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    result<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">[<\/span>ChapterRecord<span class=\"token punctuation\">]<\/span> <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> record <span class=\"token keyword\">in<\/span> records<span class=\"token punctuation\">:<\/span><br \/>\n        key <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">(<\/span>record<span class=\"token punctuation\">.<\/span>course_id<span class=\"token punctuation\">,<\/span> record<span class=\"token punctuation\">.<\/span>chapter_id<span class=\"token punctuation\">,<\/span> record<span class=\"token punctuation\">.<\/span>sort_path<span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> key <span class=\"token keyword\">in<\/span> seen<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">continue<\/span><br \/>\n        seen<span class=\"token punctuation\">.<\/span>add<span class=\"token punctuation\">(<\/span>key<span class=\"token punctuation\">)<\/span><br \/>\n        result<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span>record<span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">return<\/span> result<\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">CourseStorage<\/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> csv_path<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> json_path<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> sqlite_path<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> table<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>csv_path <span class=\"token operator\">&#061;<\/span> csv_path<br \/>\n        self<span class=\"token punctuation\">.<\/span>json_path <span class=\"token operator\">&#061;<\/span> json_path<br \/>\n        self<span class=\"token punctuation\">.<\/span>sqlite_path <span class=\"token operator\">&#061;<\/span> sqlite_path<br \/>\n        self<span class=\"token punctuation\">.<\/span>table <span class=\"token operator\">&#061;<\/span> table<\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">save_all<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> records<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">[<\/span>ChapterRecord<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        clean_records <span class=\"token operator\">&#061;<\/span> deduplicate_records<span class=\"token punctuation\">(<\/span>records<span class=\"token punctuation\">)<\/span><\/p>\n<p>        logger<span class=\"token punctuation\">.<\/span>info<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u89e3\u6790\u8bb0\u5f55\u6570: %s&#xff0c;\u53bb\u91cd\u540e\u8bb0\u5f55\u6570: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>records<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>clean_records<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        self<span class=\"token punctuation\">.<\/span>save_csv<span class=\"token punctuation\">(<\/span>clean_records<span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>save_json<span class=\"token punctuation\">(<\/span>clean_records<span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>save_sqlite<span class=\"token punctuation\">(<\/span>clean_records<span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">save_csv<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> records<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">[<\/span>ChapterRecord<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_parent_dir<span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">.<\/span>csv_path<span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">with<\/span> <span class=\"token builtin\">open<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">.<\/span>csv_path<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;w&#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>DictWriter<span class=\"token punctuation\">(<\/span>f<span class=\"token punctuation\">,<\/span> fieldnames<span class=\"token operator\">&#061;<\/span>FIELDNAMES<span class=\"token punctuation\">)<\/span><br \/>\n            writer<span class=\"token punctuation\">.<\/span>writeheader<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>            <span class=\"token keyword\">for<\/span> record <span class=\"token keyword\">in<\/span> records<span class=\"token punctuation\">:<\/span><br \/>\n                writer<span class=\"token punctuation\">.<\/span>writerow<span class=\"token punctuation\">(<\/span>record<span class=\"token punctuation\">.<\/span>to_dict<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        logger<span class=\"token punctuation\">.<\/span>info<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;CSV \u5df2\u5bfc\u51fa: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> self<span class=\"token punctuation\">.<\/span>csv_path<span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">save_json<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> records<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">[<\/span>ChapterRecord<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_parent_dir<span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">.<\/span>json_path<span class=\"token punctuation\">)<\/span><\/p>\n<p>        data <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span>record<span class=\"token punctuation\">.<\/span>to_dict<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">for<\/span> record <span class=\"token keyword\">in<\/span> records<span class=\"token punctuation\">]<\/span><\/p>\n<p>        <span class=\"token keyword\">with<\/span> <span class=\"token builtin\">open<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">.<\/span>json_path<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;w&#034;<\/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> <span class=\"token keyword\">as<\/span> f<span class=\"token punctuation\">:<\/span><br \/>\n            json<span class=\"token punctuation\">.<\/span>dump<span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">,<\/span> f<span class=\"token punctuation\">,<\/span> ensure_ascii<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">False<\/span><span class=\"token punctuation\">,<\/span> indent<span class=\"token operator\">&#061;<\/span><span class=\"token number\">2<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        logger<span class=\"token punctuation\">.<\/span>info<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;JSON \u5df2\u5bfc\u51fa: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> self<span class=\"token punctuation\">.<\/span>json_path<span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">save_sqlite<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> records<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">[<\/span>ChapterRecord<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_parent_dir<span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">.<\/span>sqlite_path<span class=\"token punctuation\">)<\/span><\/p>\n<p>        conn <span class=\"token operator\">&#061;<\/span> sqlite3<span class=\"token punctuation\">.<\/span>connect<span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">.<\/span>sqlite_path<span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            self<span class=\"token punctuation\">.<\/span>_create_table<span class=\"token punctuation\">(<\/span>conn<span class=\"token punctuation\">)<\/span><\/p>\n<p>            sql <span class=\"token operator\">&#061;<\/span> <span class=\"token string-interpolation\"><span class=\"token string\">f&#034;&#034;&#034;<br \/>\n            INSERT OR REPLACE INTO <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>self<span class=\"token punctuation\">.<\/span>table<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> (<br \/>\n                course_id,<br \/>\n                course_title,<br \/>\n                teacher,<br \/>\n                tags,<br \/>\n                chapter_id,<br \/>\n                chapter_title,<br \/>\n                parent_id,<br \/>\n                level,<br \/>\n                is_preview,<br \/>\n                duration_seconds,<br \/>\n                duration_text,<br \/>\n                sort_path,<br \/>\n                source_url,<br \/>\n                crawled_at,<br \/>\n                row_hash<br \/>\n            ) VALUES (<br \/>\n                :course_id,<br \/>\n                :course_title,<br \/>\n                :teacher,<br \/>\n                :tags,<br \/>\n                :chapter_id,<br \/>\n                :chapter_title,<br \/>\n                :parent_id,<br \/>\n                :level,<br \/>\n                :is_preview,<br \/>\n                :duration_seconds,<br \/>\n                :duration_text,<br \/>\n                :sort_path,<br \/>\n                :source_url,<br \/>\n                :crawled_at,<br \/>\n                :row_hash<br \/>\n            )<br \/>\n            &#034;&#034;&#034;<\/span><\/span><\/p>\n<p>            payload<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n            <span class=\"token keyword\">for<\/span> record <span class=\"token keyword\">in<\/span> records<span class=\"token punctuation\">:<\/span><br \/>\n                item <span class=\"token operator\">&#061;<\/span> record<span class=\"token punctuation\">.<\/span>to_dict<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n                item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;is_preview&#034;<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">(<\/span>item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;is_preview&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><br \/>\n                payload<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span>item<span class=\"token punctuation\">)<\/span><\/p>\n<p>            conn<span class=\"token punctuation\">.<\/span>executemany<span class=\"token punctuation\">(<\/span>sql<span class=\"token punctuation\">,<\/span> payload<span class=\"token punctuation\">)<\/span><br \/>\n            conn<span class=\"token punctuation\">.<\/span>commit<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>            logger<span class=\"token punctuation\">.<\/span>info<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;SQLite \u5df2\u5199\u5165: %s&#xff0c;\u8868: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> self<span class=\"token punctuation\">.<\/span>sqlite_path<span class=\"token punctuation\">,<\/span> self<span class=\"token punctuation\">.<\/span>table<span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">finally<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            conn<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\">_create_table<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> conn<span class=\"token punctuation\">:<\/span> sqlite3<span class=\"token punctuation\">.<\/span>Connection<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 string-interpolation\"><span class=\"token string\">f&#034;&#034;&#034;<br \/>\n        CREATE TABLE IF NOT EXISTS <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>self<span class=\"token punctuation\">.<\/span>table<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> (<br \/>\n            course_id TEXT NOT NULL,<br \/>\n            course_title TEXT,<br \/>\n            teacher TEXT,<br \/>\n            tags TEXT,<br \/>\n            chapter_id TEXT NOT NULL,<br \/>\n            chapter_title TEXT,<br \/>\n            parent_id TEXT,<br \/>\n            level INTEGER,<br \/>\n            is_preview INTEGER,<br \/>\n            duration_seconds INTEGER,<br \/>\n            duration_text TEXT,<br \/>\n            sort_path TEXT NOT NULL,<br \/>\n            source_url TEXT,<br \/>\n            crawled_at TEXT,<br \/>\n            row_hash TEXT,<br \/>\n            PRIMARY KEY (course_id, chapter_id, sort_path)<br \/>\n        );<br \/>\n        &#034;&#034;&#034;<\/span><\/span><\/p>\n<p>        conn<span class=\"token punctuation\">.<\/span>execute<span class=\"token punctuation\">(<\/span>sql<span class=\"token punctuation\">)<\/span><\/p>\n<p>        index_sql <span class=\"token operator\">&#061;<\/span> <span class=\"token string-interpolation\"><span class=\"token string\">f&#034;&#034;&#034;<br \/>\n        CREATE INDEX IF NOT EXISTS idx_<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>self<span class=\"token punctuation\">.<\/span>table<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">_course<br \/>\n        ON <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>self<span class=\"token punctuation\">.<\/span>table<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> (course_id, level, sort_path);<br \/>\n        &#034;&#034;&#034;<\/span><\/span><\/p>\n<p>        conn<span class=\"token punctuation\">.<\/span>execute<span class=\"token punctuation\">(<\/span>index_sql<span class=\"token punctuation\">)<\/span><br \/>\n        conn<span class=\"token punctuation\">.<\/span>commit<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<h4>8.3 \u53bb\u91cd\u7b56\u7565<\/h4>\n<p>\u672c\u6587\u91c7\u7528\u7ec4\u5408\u952e\u53bb\u91cd&#xff1a;<\/p>\n<p>course_id &#043; chapter_id &#043; sort_path<\/p>\n<p>\u4e3a\u4ec0\u4e48\u4e0d\u53ea\u7528 chapter_id&#xff1f;<\/p>\n<p>\u56e0\u4e3a\u4e0d\u540c\u8bfe\u7a0b\u91cc\u53ef\u80fd\u5b58\u5728\u76f8\u540c\u7684\u7ae0\u8282 ID&#xff0c;\u5c24\u5176\u662f\u5e73\u53f0\u5185\u90e8\u5982\u679c\u7528\u77ed ID \u6216\u8fc1\u79fb\u6570\u636e\u65f6&#xff0c;\u5355\u72ec\u7528 chapter_id \u4e0d\u591f\u7a33\u3002<\/p>\n<p>\u4e3a\u4ec0\u4e48\u52a0 sort_path&#xff1f;<\/p>\n<p>\u56e0\u4e3a\u6709\u4e9b\u8282\u70b9\u6ca1\u6709\u771f\u5b9e ID&#xff0c;\u6211\u4eec\u4f1a\u751f\u6210 auto-1.2.3\u3002\u52a0\u5165 sort_path \u53ef\u4ee5\u907f\u514d\u540c\u540d\u8282\u70b9\u4e92\u76f8\u8986\u76d6\u3002<\/p>\n<p>\u5982\u679c\u4f60\u8981\u505a\u5185\u5bb9\u53d8\u5316\u76d1\u63a7&#xff0c;\u53ef\u4ee5\u4f7f\u7528 row_hash \u5224\u65ad\u8bb0\u5f55\u662f\u5426\u53d8\u5316\u3002\u6bd4\u5982\u540c\u4e00\u4e2a\u7ae0\u8282\u6807\u9898\u6216\u8bd5\u770b\u72b6\u6001\u53d8\u4e86&#xff0c;hash \u4f1a\u53d1\u751f\u53d8\u5316\u3002<\/p>\n<hr \/>\n<h3>9\ufe0f\u20e3 \u8fd0\u884c\u65b9\u5f0f\u4e0e\u7ed3\u679c\u5c55\u793a<\/h3>\n<h4>9.1 \u4e3b\u5165\u53e3\u6587\u4ef6<\/h4>\n<p>\u521b\u5efa main.py&#xff1a;<\/p>\n<p><span class=\"token keyword\">from<\/span> __future__ <span class=\"token keyword\">import<\/span> annotations<\/p>\n<p><span class=\"token keyword\">from<\/span> rich<span class=\"token punctuation\">.<\/span>console <span class=\"token keyword\">import<\/span> Console<br \/>\n<span class=\"token keyword\">from<\/span> rich<span class=\"token punctuation\">.<\/span>table <span class=\"token keyword\">import<\/span> Table<\/p>\n<p><span class=\"token keyword\">from<\/span> crawler<span class=\"token punctuation\">.<\/span>config <span class=\"token keyword\">import<\/span> load_settings<br \/>\n<span class=\"token keyword\">from<\/span> crawler<span class=\"token punctuation\">.<\/span>fetcher <span class=\"token keyword\">import<\/span> CourseCatalogFetcher<br \/>\n<span class=\"token keyword\">from<\/span> crawler<span class=\"token punctuation\">.<\/span>parser <span class=\"token keyword\">import<\/span> CourseCatalogParser<br \/>\n<span class=\"token keyword\">from<\/span> crawler<span class=\"token punctuation\">.<\/span>storage <span class=\"token keyword\">import<\/span> CourseStorage<br \/>\n<span class=\"token keyword\">from<\/span> crawler<span class=\"token punctuation\">.<\/span>utils <span class=\"token keyword\">import<\/span> setup_logger<\/p>\n<p>console <span class=\"token operator\">&#061;<\/span> Console<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\nlogger <span class=\"token operator\">&#061;<\/span> setup_logger<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">preview_records<\/span><span class=\"token punctuation\">(<\/span>records<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> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    table <span class=\"token operator\">&#061;<\/span> Table<span class=\"token punctuation\">(<\/span>title<span class=\"token operator\">&#061;<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;Course Catalog Preview Top <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>limit<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    table<span class=\"token punctuation\">.<\/span>add_column<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;course_title&#034;<\/span><span class=\"token punctuation\">,<\/span> overflow<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;fold&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    table<span class=\"token punctuation\">.<\/span>add_column<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;chapter_title&#034;<\/span><span class=\"token punctuation\">,<\/span> overflow<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;fold&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    table<span class=\"token punctuation\">.<\/span>add_column<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;level&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    table<span class=\"token punctuation\">.<\/span>add_column<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;preview&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    table<span class=\"token punctuation\">.<\/span>add_column<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;duration&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    table<span class=\"token punctuation\">.<\/span>add_column<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;teacher&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">for<\/span> record <span class=\"token keyword\">in<\/span> records<span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">:<\/span>limit<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        table<span class=\"token punctuation\">.<\/span>add_row<span class=\"token punctuation\">(<\/span><br \/>\n            record<span class=\"token punctuation\">.<\/span>course_title<span class=\"token punctuation\">,<\/span><br \/>\n            record<span class=\"token punctuation\">.<\/span>chapter_title<span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">(<\/span>record<span class=\"token punctuation\">.<\/span>level<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;yes&#034;<\/span> <span class=\"token keyword\">if<\/span> record<span class=\"token punctuation\">.<\/span>is_preview <span class=\"token keyword\">else<\/span> <span class=\"token string\">&#034;no&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            record<span class=\"token punctuation\">.<\/span>duration_text<span class=\"token punctuation\">,<\/span><br \/>\n            record<span class=\"token punctuation\">.<\/span>teacher<span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">)<\/span><\/p>\n<p>    console<span class=\"token punctuation\">.<\/span><span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span>table<span class=\"token punctuation\">)<\/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    settings <span class=\"token operator\">&#061;<\/span> load_settings<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    fetcher <span class=\"token operator\">&#061;<\/span> CourseCatalogFetcher<span class=\"token punctuation\">(<\/span><br \/>\n        settings<span class=\"token operator\">&#061;<\/span>settings<span class=\"token punctuation\">.<\/span>spider<span class=\"token punctuation\">,<\/span><br \/>\n        headers<span class=\"token operator\">&#061;<\/span>settings<span class=\"token punctuation\">.<\/span>headers<span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token punctuation\">)<\/span><\/p>\n<p>    payload <span class=\"token operator\">&#061;<\/span> fetcher<span class=\"token punctuation\">.<\/span>fetch<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    parser <span class=\"token operator\">&#061;<\/span> CourseCatalogParser<span class=\"token punctuation\">(<\/span><br \/>\n        source_url<span class=\"token operator\">&#061;<\/span>settings<span class=\"token punctuation\">.<\/span>spider<span class=\"token punctuation\">.<\/span>source_url <span class=\"token keyword\">or<\/span> settings<span class=\"token punctuation\">.<\/span>spider<span class=\"token punctuation\">.<\/span>api_url<span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token punctuation\">)<\/span><\/p>\n<p>    records <span class=\"token operator\">&#061;<\/span> parser<span class=\"token punctuation\">.<\/span>parse<span class=\"token punctuation\">(<\/span>payload<span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> records<span class=\"token punctuation\">:<\/span><br \/>\n        logger<span class=\"token punctuation\">.<\/span>warning<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u6ca1\u6709\u89e3\u6790\u5230\u4efb\u4f55\u8bfe\u7a0b\u7ae0\u8282\u8bb0\u5f55&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">return<\/span><\/p>\n<p>    storage <span class=\"token operator\">&#061;<\/span> CourseStorage<span class=\"token punctuation\">(<\/span><br \/>\n        csv_path<span class=\"token operator\">&#061;<\/span>settings<span class=\"token punctuation\">.<\/span>storage<span class=\"token punctuation\">.<\/span>csv_path<span class=\"token punctuation\">,<\/span><br \/>\n        json_path<span class=\"token operator\">&#061;<\/span>settings<span class=\"token punctuation\">.<\/span>storage<span class=\"token punctuation\">.<\/span>json_path<span class=\"token punctuation\">,<\/span><br \/>\n        sqlite_path<span class=\"token operator\">&#061;<\/span>settings<span class=\"token punctuation\">.<\/span>storage<span class=\"token punctuation\">.<\/span>sqlite_path<span class=\"token punctuation\">,<\/span><br \/>\n        table<span class=\"token operator\">&#061;<\/span>settings<span class=\"token punctuation\">.<\/span>storage<span class=\"token punctuation\">.<\/span>sqlite_table<span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token punctuation\">)<\/span><\/p>\n<p>    storage<span class=\"token punctuation\">.<\/span>save_all<span class=\"token punctuation\">(<\/span>records<span class=\"token punctuation\">)<\/span><\/p>\n<p>    preview_records<span class=\"token punctuation\">(<\/span>records<span class=\"token punctuation\">,<\/span> limit<span class=\"token operator\">&#061;<\/span><span class=\"token number\">5<\/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>9.2 \u542f\u52a8\u547d\u4ee4<\/h4>\n<p>\u5148\u786e\u4fdd\u76ee\u5f55\u5b8c\u6574&#xff1a;<\/p>\n<p><span class=\"token function\">mkdir<\/span> <span class=\"token parameter variable\">-p<\/span> configs crawler examples data logs tests<br \/>\n<span class=\"token function\">touch<\/span> crawler\/__init__.py<\/p>\n<p>\u8fd0\u884c&#xff1a;<\/p>\n<p>python main.py<\/p>\n<p>\u9ed8\u8ba4\u8bfb\u53d6\u672c\u5730\u793a\u4f8b\u6587\u4ef6&#xff1a;<\/p>\n<p><span class=\"token key atrule\">spider<\/span><span class=\"token punctuation\">:<\/span><br \/>\n  <span class=\"token key atrule\">mode<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;file&#034;<\/span><\/p>\n<p>\u5982\u679c\u8981\u8bf7\u6c42\u516c\u5f00\u63a5\u53e3&#xff0c;\u628a\u914d\u7f6e\u6539\u6210&#xff1a;<\/p>\n<p><span class=\"token key atrule\">spider<\/span><span class=\"token punctuation\">:<\/span><br \/>\n  <span class=\"token key atrule\">mode<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;api&#034;<\/span><br \/>\n  <span class=\"token key atrule\">api_url<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;https:\/\/example.com\/api\/course\/catalog?course_id&#061;python-1001&#034;<\/span><\/p>\n<p>\u7136\u540e\u518d\u6b21\u8fd0\u884c&#xff1a;<\/p>\n<p>python main.py<\/p>\n<h4>9.3 \u8f93\u51fa\u4f4d\u7f6e<\/h4>\n<p>\u8fd0\u884c\u540e\u4f1a\u751f\u6210&#xff1a;<\/p>\n<p>data\/output.csv<br \/>\ndata\/output.json<br \/>\ndata\/courses.db<\/p>\n<p>SQLite \u67e5\u8be2\u793a\u4f8b&#xff1a;<\/p>\n<p>sqlite3 data\/courses.db<\/p>\n<p>\u8fdb\u5165 SQLite \u540e\u6267\u884c&#xff1a;<\/p>\n<p><span class=\"token keyword\">SELECT<\/span><br \/>\n    course_title<span class=\"token punctuation\">,<\/span><br \/>\n    chapter_title<span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token keyword\">level<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    is_preview<span class=\"token punctuation\">,<\/span><br \/>\n    duration_text<span class=\"token punctuation\">,<\/span><br \/>\n    teacher<br \/>\n<span class=\"token keyword\">FROM<\/span> course_chapters<br \/>\n<span class=\"token keyword\">ORDER<\/span> <span class=\"token keyword\">BY<\/span> course_id<span class=\"token punctuation\">,<\/span> sort_path<br \/>\n<span class=\"token keyword\">LIMIT<\/span> <span class=\"token number\">5<\/span><span class=\"token punctuation\">;<\/span><\/p>\n<h4>9.4 \u793a\u4f8b\u7ed3\u679c<\/h4>\n<p>\u793a\u4f8b\u8f93\u51fa\u7c7b\u4f3c&#xff1a;<\/p>\n<table>\n<tr>course_titlechapter_titlelevelis_previewduration_textteacher<\/tr>\n<tbody>\n<tr>\n<td>Python \u7f51\u7edc\u722c\u866b\u5b9e\u6218\u5165\u95e8<\/td>\n<td>\u7b2c 1 \u7ae0 \u8bfe\u7a0b\u4ecb\u7ecd\u4e0e\u73af\u5883\u51c6\u5907<\/td>\n<td align=\"right\">1<\/td>\n<td align=\"right\">1<\/td>\n<td>30:00<\/td>\n<td>\u6797\u5ddd<\/td>\n<\/tr>\n<tr>\n<td>Python \u7f51\u7edc\u722c\u866b\u5b9e\u6218\u5165\u95e8<\/td>\n<td>1.1 \u8bfe\u7a0b\u9002\u5408\u8c01\u5b66\u4e60<\/td>\n<td align=\"right\">2<\/td>\n<td align=\"right\">1<\/td>\n<td>07:00<\/td>\n<td>\u6797\u5ddd<\/td>\n<\/tr>\n<tr>\n<td>Python \u7f51\u7edc\u722c\u866b\u5b9e\u6218\u5165\u95e8<\/td>\n<td>1.2 Python \u73af\u5883\u5b89\u88c5<\/td>\n<td align=\"right\">2<\/td>\n<td align=\"right\">1<\/td>\n<td>13:00<\/td>\n<td>\u6797\u5ddd<\/td>\n<\/tr>\n<tr>\n<td>Python \u7f51\u7edc\u722c\u866b\u5b9e\u6218\u5165\u95e8<\/td>\n<td>1.3 \u9879\u76ee\u76ee\u5f55\u89c4\u5212<\/td>\n<td align=\"right\">2<\/td>\n<td align=\"right\">0<\/td>\n<td>10:00<\/td>\n<td>\u6797\u5ddd<\/td>\n<\/tr>\n<tr>\n<td>Python \u7f51\u7edc\u722c\u866b\u5b9e\u6218\u5165\u95e8<\/td>\n<td>\u7b2c 2 \u7ae0 HTTP \u8bf7\u6c42\u57fa\u7840<\/td>\n<td align=\"right\">1<\/td>\n<td align=\"right\">0<\/td>\n<td>01:00:00<\/td>\n<td>\u6797\u5ddd<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>\u4f60\u4f1a\u53d1\u73b0&#xff0c;\u7236\u7ae0\u8282\u548c\u5b50\u7ae0\u8282\u90fd\u88ab\u5c55\u5f00\u5230\u4e86\u540c\u4e00\u5f20\u8868\u91cc\u3002\u540e\u7eed\u8981\u7edf\u8ba1\u6bcf\u95e8\u8bfe\u6709\u591a\u5c11\u5c0f\u8282\u3001\u8bd5\u770b\u5c0f\u8282\u6bd4\u4f8b\u3001\u603b\u8bfe\u65f6&#xff0c;\u90fd\u5f88\u65b9\u4fbf\u3002<\/p>\n<hr \/>\n<h3>&#x1f51f; \u5e38\u89c1\u95ee\u9898\u4e0e\u6392\u9519<\/h3>\n<h4>10.1 \u9047\u5230 403 \u600e\u4e48\u529e&#xff1f;<\/h4>\n<p>403 \u8868\u793a\u8bf7\u6c42\u88ab\u62d2\u7edd\u3002\u5e38\u89c1\u539f\u56e0\u6709&#xff1a;<\/p>\n<ul>\n<li>\u76ee\u6807\u6570\u636e\u5e76\u975e\u516c\u5f00\u6570\u636e\u3002<\/li>\n<li>\u8bf7\u6c42\u7f3a\u5c11\u5408\u7406 headers\u3002<\/li>\n<li>Referer \u4e0d\u7b26\u5408\u7ad9\u70b9\u9884\u671f\u3002<\/li>\n<li>\u8bf7\u6c42\u9891\u7387\u8fc7\u9ad8\u3002<\/li>\n<li>\u63a5\u53e3\u9700\u8981\u767b\u5f55\u6216\u6388\u6743\u3002<\/li>\n<\/ul>\n<p>\u5efa\u8bae\u5904\u7406\u65b9\u5f0f&#xff1a;<\/p>\n<li>\u5148\u786e\u8ba4\u6570\u636e\u662f\u5426\u516c\u5f00\u3002<\/li>\n<li>\u68c0\u67e5 robots.txt\u3002<\/li>\n<li>\u964d\u4f4e\u8bf7\u6c42\u9891\u7387\u3002<\/li>\n<li>\u8865\u5145\u5e38\u89c4 headers&#xff0c;\u4f8b\u5982 User-Agent\u3001Accept\u3001Referer\u3002<\/li>\n<li>\u4e0d\u8981\u5c1d\u8bd5\u7ed5\u8fc7\u767b\u5f55\u3001\u4ed8\u8d39\u6216\u6743\u9650\u9650\u5236\u3002<\/li>\n<p>\u672c\u6587 Fetcher \u5bf9 403 \u7684\u5904\u7406\u662f\u76f4\u63a5\u63d0\u793a\u5e76\u505c\u6b62&#xff0c;\u4e0d\u4f1a\u7ee7\u7eed\u9ad8\u9891\u91cd\u8bd5\u3002<\/p>\n<h4>10.2 \u9047\u5230 429 \u600e\u4e48\u529e&#xff1f;<\/h4>\n<p>429 \u901a\u5e38\u8868\u793a\u8bf7\u6c42\u8fc7\u591a\u3002\u89e3\u51b3\u65b9\u5f0f\u4e0d\u662f\u7ee7\u7eed\u52a0\u4ee3\u7406\u731b\u6253&#xff0c;\u800c\u662f\u964d\u4f4e\u9891\u7387\u3002<\/p>\n<p>\u5efa\u8bae&#xff1a;<\/p>\n<ul>\n<li>\u589e\u52a0 request_interval\u3002<\/li>\n<li>\u5f00\u542f\u6307\u6570\u9000\u907f\u3002<\/li>\n<li>\u51cf\u5c11\u5e76\u53d1\u3002<\/li>\n<li>\u505a\u672c\u5730\u7f13\u5b58\u3002<\/li>\n<li>\u4e0d\u91cd\u590d\u8bf7\u6c42\u540c\u4e00\u8bfe\u7a0b\u3002<\/li>\n<li>\u5bf9\u7a33\u5b9a\u76ee\u5f55\u6570\u636e\u8bbe\u7f6e\u8f83\u957f\u66f4\u65b0\u5468\u671f\u3002<\/li>\n<\/ul>\n<p>\u8bfe\u7a0b\u76ee\u5f55\u4e0d\u662f\u79d2\u7ea7\u53d8\u5316\u7684\u6570\u636e&#xff0c;\u5f88\u591a\u573a\u666f\u6bcf\u5929\u91c7\u4e00\u6b21\u5df2\u7ecf\u8db3\u591f\u3002<\/p>\n<h4>10.3 HTML \u6293\u5230\u7a7a\u58f3\u600e\u4e48\u529e&#xff1f;<\/h4>\n<p>\u5982\u679c\u4f60\u7528&#xff1a;<\/p>\n<p>html <span class=\"token operator\">&#061;<\/span> requests<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>text<br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">)<\/span><\/p>\n<p>\u53d1\u73b0\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>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>\/static\/js\/app.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>\u8bf4\u660e\u9875\u9762\u5927\u6982\u7387\u662f\u524d\u7aef\u52a8\u6001\u6e32\u67d3\u3002\u5904\u7406\u6b65\u9aa4&#xff1a;<\/p>\n<li>\u6253\u5f00\u6d4f\u89c8\u5668\u5f00\u53d1\u8005\u5de5\u5177\u3002<\/li>\n<li>\u5207\u5230 Network\u3002<\/li>\n<li>\u9009\u62e9 Fetch\/XHR\u3002<\/li>\n<li>\u5237\u65b0\u9875\u9762\u3002<\/li>\n<li>\u627e\u8fd4\u56de JSON \u7684\u8bf7\u6c42\u3002<\/li>\n<li>\u68c0\u67e5\u662f\u5426\u662f\u516c\u5f00\u8bfe\u7a0b\u76ee\u5f55\u63a5\u53e3\u3002<\/li>\n<li>\u7528 requests \u590d\u73b0\u63a5\u53e3\u8bf7\u6c42\u3002<\/li>\n<p>\u4e0d\u8981\u6025\u7740\u4e0a Playwright\u3002\u5f88\u591a\u65f6\u5019\u771f\u6b63\u9700\u8981\u7684\u53ea\u662f\u4e00\u4e2a\u516c\u5f00 JSON \u63a5\u53e3\u3002<\/p>\n<h4>10.4 \u89e3\u6790\u62a5\u9519\u600e\u4e48\u529e&#xff1f;<\/h4>\n<p>\u89e3\u6790\u62a5\u9519\u5e38\u89c1\u539f\u56e0&#xff1a;<\/p>\n<ul>\n<li>\u5b57\u6bb5\u540d\u53d8\u5316\u3002<\/li>\n<li>children \u6539\u6210\u4e86 childList\u3002<\/li>\n<li>duration \u4ece\u6574\u6570\u53d8\u6210\u4e86 &#034;12:30&#034;\u3002<\/li>\n<li>teacher \u4ece\u5b57\u7b26\u4e32\u53d8\u6210\u4e86\u5bf9\u8c61\u3002<\/li>\n<li>\u67d0\u4e9b\u8282\u70b9\u7f3a\u5c11 ID\u3002<\/li>\n<li>\u63a5\u53e3\u8fd4\u56de\u9519\u8bef\u4fe1\u606f\u800c\u4e0d\u662f\u8bfe\u7a0b\u6570\u636e\u3002<\/li>\n<\/ul>\n<p>\u672c\u6587\u89e3\u6790\u5668\u901a\u8fc7 pick_value\u3001find_first_list \u548c parse_duration_to_seconds \u505a\u4e86\u4e00\u5c42\u517c\u5bb9\u3002\u4f46\u771f\u5b9e\u9879\u76ee\u4e2d\u4ecd\u7136\u5efa\u8bae\u628a\u5f02\u5e38\u6837\u672c\u4fdd\u5b58\u4e0b\u6765\u3002<\/p>\n<p>\u53ef\u4ee5\u5728 main.py \u4e2d\u52a0\u4e00\u6bb5\u8c03\u8bd5\u8f93\u51fa&#xff1a;<\/p>\n<p><span class=\"token keyword\">import<\/span> json<\/p>\n<p><span class=\"token keyword\">with<\/span> <span class=\"token builtin\">open<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;data\/debug_payload.json&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;w&#034;<\/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> <span class=\"token keyword\">as<\/span> f<span class=\"token punctuation\">:<\/span><br \/>\n    json<span class=\"token punctuation\">.<\/span>dump<span class=\"token punctuation\">(<\/span>payload<span class=\"token punctuation\">,<\/span> f<span class=\"token punctuation\">,<\/span> ensure_ascii<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">False<\/span><span class=\"token punctuation\">,<\/span> indent<span class=\"token operator\">&#061;<\/span><span class=\"token number\">2<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u5f53\u89e3\u6790\u5931\u8d25\u65f6&#xff0c;\u5148\u770b\u539f\u59cb JSON&#xff0c;\u4e0d\u8981\u53ea\u76ef\u7740\u4ee3\u7801\u731c\u3002<\/p>\n<h4>10.5 \u7f16\u7801\u4e71\u7801\u600e\u4e48\u529e&#xff1f;<\/h4>\n<p>CSV \u4e71\u7801\u901a\u5e38\u662f Excel \u6253\u5f00\u65b9\u5f0f\u5bfc\u81f4\u7684\u3002\u672c\u6587\u5199 CSV \u65f6\u4f7f\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\u5728 Windows Excel \u4e2d\u6253\u5f00\u4e2d\u6587\u66f4\u7a33\u3002<\/p>\n<p>JSON \u5efa\u8bae\u4f7f\u7528&#xff1a;<\/p>\n<p>json<span class=\"token punctuation\">.<\/span>dump<span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">,<\/span> f<span class=\"token punctuation\">,<\/span> ensure_ascii<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">False<\/span><span class=\"token punctuation\">,<\/span> indent<span class=\"token operator\">&#061;<\/span><span class=\"token number\">2<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u8fd9\u6837\u4e2d\u6587\u4e0d\u4f1a\u88ab\u8f6c\u4e49\u6210 \\\\u4e2d\\\\u6587\u3002<\/p>\n<h4>10.6 \u6570\u636e\u91cd\u590d\u600e\u4e48\u529e&#xff1f;<\/h4>\n<p>\u5148\u786e\u8ba4\u91cd\u590d\u7c7b\u578b\u3002<\/p>\n<p>\u5982\u679c\u662f\u5b8c\u5168\u91cd\u590d&#xff0c;\u591a\u534a\u662f\u7ffb\u9875\u6216\u4efb\u52a1\u8c03\u5ea6\u91cd\u590d\u8bf7\u6c42\u5bfc\u81f4\u7684\u3002<\/p>\n<p>\u5982\u679c\u662f\u540c\u540d\u7ae0\u8282\u91cd\u590d&#xff0c;\u53ef\u80fd\u662f\u8bfe\u7a0b\u786e\u5b9e\u6709\u591a\u4e2a\u540c\u540d\u5c0f\u8282\u3002<\/p>\n<p>\u5982\u679c\u662f\u7236\u7ae0\u8282\u548c\u5b50\u7ae0\u8282\u770b\u8d77\u6765\u91cd\u590d&#xff0c;\u8981\u68c0\u67e5 level \u548c parent_id\u3002<\/p>\n<p>\u672c\u6587\u4f7f\u7528&#xff1a;<\/p>\n<p>course_id &#043; chapter_id &#043; sort_path<\/p>\n<p>\u4f5c\u4e3a\u53bb\u91cd\u4e3b\u952e&#xff0c;\u9002\u5408\u8bfe\u7a0b\u76ee\u5f55\u6811\u573a\u666f\u3002<\/p>\n<h4>10.7 \u8bd5\u770b\u5b57\u6bb5\u4e0d\u51c6\u600e\u4e48\u529e&#xff1f;<\/h4>\n<p>\u8bd5\u770b\u5b57\u6bb5\u5728\u4e0d\u540c\u5e73\u53f0\u53ef\u80fd\u53eb&#xff1a;<\/p>\n<p>preview<br \/>\nisPreview<br \/>\ntrial<br \/>\nfree<br \/>\ncanTry<\/p>\n<p>\u6709\u7684\u5e73\u53f0\u8fd8\u4f1a\u7528\u6570\u5b57&#xff1a;<\/p>\n<p>1 \u8868\u793a\u8bd5\u770b<br \/>\n0 \u8868\u793a\u4e0d\u53ef\u8bd5\u770b<\/p>\n<p>\u4e5f\u53ef\u80fd\u7528\u5b57\u7b26\u4e32&#xff1a;<\/p>\n<p>&#034;free&#034;<br \/>\n&#034;trial&#034;<br \/>\n&#034;\u8bd5\u770b&#034;<\/p>\n<p>\u6240\u4ee5\u89e3\u6790\u65f6\u4e0d\u8981\u53ea\u5199&#xff1a;<\/p>\n<p>is_preview <span class=\"token operator\">&#061;<\/span> node<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;preview&#034;<\/span><span class=\"token punctuation\">]<\/span><\/p>\n<p>\u800c\u5e94\u8be5\u5199\u517c\u5bb9\u903b\u8f91\u3002\u672c\u6587 pick_bool \u5c31\u662f\u4e3a\u8fd9\u4e2a\u573a\u666f\u51c6\u5907\u7684\u3002<\/p>\n<hr \/>\n<h3>1\ufe0f\u20e31\ufe0f\u20e3 \u8fdb\u9636\u4f18\u5316<\/h3>\n<h4>11.1 \u5e76\u53d1\u91c7\u96c6<\/h4>\n<p>\u5982\u679c\u4f60\u8981\u91c7\u96c6\u5f88\u591a\u8bfe\u7a0b&#xff0c;\u53ef\u4ee5\u5f15\u5165\u5e76\u53d1\u3002\u4f46\u8bfe\u7a0b\u76ee\u5f55\u63a5\u53e3\u4e0d\u9002\u5408\u76f2\u76ee\u9ad8\u5e76\u53d1\u3002\u5efa\u8bae\u5148\u505a\u4f4e\u5e76\u53d1&#xff0c;\u4f8b\u5982 3\u20135 \u4e2a worker\u3002<\/p>\n<p>\u7ebf\u7a0b\u6c60\u793a\u4f8b&#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<br \/>\n<span class=\"token keyword\">from<\/span> typing <span class=\"token keyword\">import<\/span> Callable<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">run_with_threads<\/span><span class=\"token punctuation\">(<\/span><br \/>\n    course_ids<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><br \/>\n    worker<span class=\"token punctuation\">:<\/span> Callable<span class=\"token punctuation\">[<\/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 builtin\">list<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    max_workers<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><br \/>\n<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\">dict<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    results<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><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>max_workers<span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">as<\/span> executor<span class=\"token punctuation\">:<\/span><br \/>\n        future_map <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n            executor<span class=\"token punctuation\">.<\/span>submit<span class=\"token punctuation\">(<\/span>worker<span class=\"token punctuation\">,<\/span> course_id<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span> course_id<br \/>\n            <span class=\"token keyword\">for<\/span> course_id <span class=\"token keyword\">in<\/span> course_ids<br \/>\n        <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>future_map<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            course_id <span class=\"token operator\">&#061;<\/span> future_map<span class=\"token punctuation\">[<\/span>future<span class=\"token punctuation\">]<\/span><\/p>\n<p>            <span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                rows <span class=\"token operator\">&#061;<\/span> future<span class=\"token punctuation\">.<\/span>result<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n                results<span class=\"token punctuation\">.<\/span>extend<span class=\"token punctuation\">(<\/span>rows<span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">except<\/span> Exception <span class=\"token keyword\">as<\/span> exc<span class=\"token punctuation\">:<\/span><br \/>\n                <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;course_id&#061;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>course_id<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> \u91c7\u96c6\u5931\u8d25: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>exc<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">return<\/span> results<\/p>\n<p>\u8fd9\u4e2a\u4f8b\u5b50\u53ea\u662f\u8bf4\u660e\u7ed3\u6784&#xff0c;\u4e0d\u5efa\u8bae\u76f4\u63a5\u628a\u5e76\u53d1\u5f00\u5927\u3002\u5e76\u53d1\u4e0d\u662f\u8d8a\u9ad8\u8d8a\u4e13\u4e1a&#xff0c;\u7a33\u5b9a\u3001\u514b\u5236\u3001\u53ef\u6062\u590d\u624d\u66f4\u91cd\u8981\u3002<\/p>\n<h4>11.2 \u65ad\u70b9\u7eed\u8dd1<\/h4>\n<p>\u8bfe\u7a0b\u91c7\u96c6\u4efb\u52a1\u53ef\u80fd\u4e2d\u9014\u5931\u8d25&#xff0c;\u6bd4\u5982\u7f51\u7edc\u4e2d\u65ad\u3001\u63a5\u53e3\u4e34\u65f6\u9519\u8bef\u3001\u673a\u5668\u91cd\u542f\u3002\u65ad\u70b9\u7eed\u8dd1\u53ef\u4ee5\u907f\u514d\u4ece\u5934\u5f00\u59cb\u3002<\/p>\n<p>\u7b80\u5355\u505a\u6cd5\u662f\u7ef4\u62a4\u4e00\u4e2a\u5df2\u5b8c\u6210\u96c6\u5408&#xff1a;<\/p>\n<p><span class=\"token keyword\">import<\/span> json<br \/>\n<span class=\"token keyword\">from<\/span> pathlib <span class=\"token keyword\">import<\/span> Path<\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">Checkpoint<\/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> path<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;data\/checkpoint.json&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>path <span class=\"token operator\">&#061;<\/span> Path<span class=\"token punctuation\">(<\/span>path<span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>done<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">set<\/span><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 builtin\">set<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>load<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">load<\/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        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> self<span class=\"token punctuation\">.<\/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            self<span class=\"token punctuation\">.<\/span>done <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">set<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">return<\/span><\/p>\n<p>        <span class=\"token keyword\">with<\/span> self<span class=\"token punctuation\">.<\/span>path<span class=\"token punctuation\">.<\/span><span class=\"token builtin\">open<\/span><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&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">as<\/span> f<span class=\"token punctuation\">:<\/span><br \/>\n            data <span class=\"token operator\">&#061;<\/span> json<span class=\"token punctuation\">.<\/span>load<span class=\"token punctuation\">(<\/span>f<span class=\"token punctuation\">)<\/span><\/p>\n<p>        self<span class=\"token punctuation\">.<\/span>done <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">set<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;done&#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><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">save<\/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>path<span class=\"token punctuation\">.<\/span>parent<span class=\"token punctuation\">.<\/span>mkdir<span class=\"token punctuation\">(<\/span>parents<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><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\">with<\/span> self<span class=\"token punctuation\">.<\/span>path<span class=\"token punctuation\">.<\/span><span class=\"token builtin\">open<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;w&#034;<\/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> <span class=\"token keyword\">as<\/span> f<span class=\"token punctuation\">:<\/span><br \/>\n            json<span class=\"token punctuation\">.<\/span>dump<span class=\"token punctuation\">(<\/span><br \/>\n                <span class=\"token punctuation\">{<\/span><span class=\"token string\">&#034;done&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">sorted<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">.<\/span>done<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                f<span class=\"token punctuation\">,<\/span><br \/>\n                ensure_ascii<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">False<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                indent<span class=\"token operator\">&#061;<\/span><span class=\"token number\">2<\/span><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\">is_done<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> course_id<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\">bool<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> course_id <span class=\"token keyword\">in<\/span> self<span class=\"token punctuation\">.<\/span>done<\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">mark_done<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> course_id<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 boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>done<span class=\"token punctuation\">.<\/span>add<span class=\"token punctuation\">(<\/span>course_id<span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>save<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u4f7f\u7528\u65b9\u5f0f&#xff1a;<\/p>\n<p>checkpoint <span class=\"token operator\">&#061;<\/span> Checkpoint<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">for<\/span> course_id <span class=\"token keyword\">in<\/span> course_ids<span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">if<\/span> checkpoint<span class=\"token punctuation\">.<\/span>is_done<span class=\"token punctuation\">(<\/span>course_id<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">continue<\/span><\/p>\n<p>    <span class=\"token comment\"># fetch and parse course<\/span><br \/>\n    <span class=\"token comment\"># save records<\/span><\/p>\n<p>    checkpoint<span class=\"token punctuation\">.<\/span>mark_done<span class=\"token punctuation\">(<\/span>course_id<span class=\"token punctuation\">)<\/span><\/p>\n<h4>11.3 \u65e5\u5fd7\u4e0e\u76d1\u63a7<\/h4>\n<p>\u6b63\u5f0f\u4efb\u52a1\u4e0d\u5efa\u8bae\u53ea\u7528 print\u3002\u65e5\u5fd7\u81f3\u5c11\u8981\u8bb0\u5f55&#xff1a;<\/p>\n<ul>\n<li>\u8bf7\u6c42 URL<\/li>\n<li>\u72b6\u6001\u7801<\/li>\n<li>\u89e3\u6790\u8bb0\u5f55\u6570<\/li>\n<li>\u6210\u529f\u8bfe\u7a0b\u6570<\/li>\n<li>\u5931\u8d25\u8bfe\u7a0b\u6570<\/li>\n<li>\u5931\u8d25\u539f\u56e0<\/li>\n<li>\u5bfc\u51fa\u8def\u5f84<\/li>\n<\/ul>\n<p>\u540e\u7eed\u53ef\u4ee5\u7edf\u8ba1\u6210\u529f\u7387&#xff1a;<\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">SpiderStats<\/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 punctuation\">:<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>total <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">0<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>success <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">0<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>failed <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">0<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>records <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">0<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">mark_success<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> count<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 boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>total <span class=\"token operator\">&#043;&#061;<\/span> <span class=\"token number\">1<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>success <span class=\"token operator\">&#043;&#061;<\/span> <span class=\"token number\">1<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>records <span class=\"token operator\">&#043;&#061;<\/span> count<\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">mark_failed<\/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>total <span class=\"token operator\">&#043;&#061;<\/span> <span class=\"token number\">1<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>failed <span class=\"token operator\">&#043;&#061;<\/span> <span class=\"token number\">1<\/span><\/p>\n<p>    <span class=\"token decorator annotation punctuation\">&#064;property<\/span><br \/>\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">success_rate<\/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 builtin\">float<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> self<span class=\"token punctuation\">.<\/span>total <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token number\">0<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> <span class=\"token number\">0.0<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> self<span class=\"token punctuation\">.<\/span>success <span class=\"token operator\">\/<\/span> self<span class=\"token punctuation\">.<\/span>total<\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">summary<\/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 builtin\">dict<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n            <span class=\"token string\">&#034;total&#034;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>total<span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;success&#034;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>success<span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;failed&#034;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>failed<span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;records&#034;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>records<span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;success_rate&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">round<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">.<\/span>success_rate<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><\/p>\n<h4>11.4 \u5b9a\u65f6\u4efb\u52a1<\/h4>\n<p>Linux \u4e0a\u53ef\u4ee5\u7528 cron\u3002\u6bd4\u5982\u6bcf\u5929\u51cc\u6668 2 \u70b9\u6267\u884c&#xff1a;<\/p>\n<p><span class=\"token number\">0<\/span> <span class=\"token number\">2<\/span> * * * <span class=\"token builtin class-name\">cd<\/span> \/opt\/course_tree_spider <span class=\"token operator\">&amp;&amp;<\/span> \/opt\/course_tree_spider\/.venv\/bin\/python main.py <span class=\"token operator\">&gt;&gt;<\/span> logs\/cron.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>\u5982\u679c\u4efb\u52a1\u590d\u6742&#xff0c;\u53ef\u4ee5\u7528 Airflow\u3001Prefect \u6216\u5176\u4ed6\u8c03\u5ea6\u7cfb\u7edf\u3002\u5c0f\u9879\u76ee\u7528 cron \u5c31\u591f\u4e86&#xff0c;\u5927\u9879\u76ee\u518d\u8c08\u5de5\u4f5c\u6d41\u5e73\u53f0\u3002<\/p>\n<h4>11.5 \u7f13\u5b58\u539f\u59cb\u54cd\u5e94<\/h4>\n<p>\u539f\u59cb\u54cd\u5e94\u5f88\u6709\u4ef7\u503c\u3002\u89e3\u6790\u89c4\u5219\u53d8\u4e86\u4ee5\u540e&#xff0c;\u53ef\u4ee5\u76f4\u63a5\u7528\u5386\u53f2 JSON \u91cd\u65b0\u89e3\u6790&#xff0c;\u800c\u4e0d\u7528\u91cd\u65b0\u8bf7\u6c42\u76ee\u6807\u7ad9\u70b9\u3002<\/p>\n<p>\u793a\u4f8b&#xff1a;<\/p>\n<p><span class=\"token keyword\">import<\/span> json<br \/>\n<span class=\"token keyword\">from<\/span> pathlib <span class=\"token keyword\">import<\/span> Path<br \/>\n<span class=\"token keyword\">from<\/span> datetime <span class=\"token keyword\">import<\/span> datetime<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">save_raw_payload<\/span><span class=\"token punctuation\">(<\/span>course_id<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> payload<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">,<\/span> root<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;data\/raw&#034;<\/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    today <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&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    directory <span class=\"token operator\">&#061;<\/span> Path<span class=\"token punctuation\">(<\/span>root<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">\/<\/span> today<br \/>\n    directory<span class=\"token punctuation\">.<\/span>mkdir<span class=\"token punctuation\">(<\/span>parents<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><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>    path <span class=\"token operator\">&#061;<\/span> directory <span class=\"token operator\">\/<\/span> <span class=\"token string-interpolation\"><span class=\"token string\">f&#034;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>course_id<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">.json&#034;<\/span><\/span><\/p>\n<p>    <span class=\"token keyword\">with<\/span> path<span class=\"token punctuation\">.<\/span><span class=\"token builtin\">open<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;w&#034;<\/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> <span class=\"token keyword\">as<\/span> f<span class=\"token punctuation\">:<\/span><br \/>\n        json<span class=\"token punctuation\">.<\/span>dump<span class=\"token punctuation\">(<\/span>payload<span class=\"token punctuation\">,<\/span> f<span class=\"token punctuation\">,<\/span> ensure_ascii<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">False<\/span><span class=\"token punctuation\">,<\/span> indent<span class=\"token operator\">&#061;<\/span><span class=\"token number\">2<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u8fd9\u79cd\u7f13\u5b58\u5bf9\u6392\u9519\u975e\u5e38\u6709\u5e2e\u52a9\u3002\u5f88\u591a\u65f6\u5019&#xff0c;\u7ebf\u4e0a\u5931\u8d25\u4e0d\u662f\u4ee3\u7801\u7a81\u7136\u574f\u4e86&#xff0c;\u800c\u662f\u63a5\u53e3\u7ed3\u6784\u53d8\u4e86\u3002\u4fdd\u7559\u539f\u59cb JSON&#xff0c;\u6392\u67e5\u4f1a\u8f7b\u677e\u5f88\u591a\u3002<\/p>\n<h4>11.6 \u6570\u636e\u8d28\u91cf\u68c0\u67e5<\/h4>\n<p>\u53ef\u4ee5\u52a0\u4e00\u4e2a\u7b80\u5355\u7684\u6570\u636e\u8d28\u91cf\u51fd\u6570&#xff1a;<\/p>\n<p><span class=\"token keyword\">from<\/span> crawler<span class=\"token punctuation\">.<\/span>parser <span class=\"token keyword\">import<\/span> ChapterRecord<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">validate_records<\/span><span class=\"token punctuation\">(<\/span>records<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">[<\/span>ChapterRecord<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\">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    errors<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 operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><\/p>\n<p>    <span class=\"token keyword\">for<\/span> index<span class=\"token punctuation\">,<\/span> record <span class=\"token keyword\">in<\/span> <span class=\"token builtin\">enumerate<\/span><span class=\"token punctuation\">(<\/span>records<span class=\"token punctuation\">,<\/span> start<span class=\"token operator\">&#061;<\/span><span class=\"token number\">1<\/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> record<span class=\"token punctuation\">.<\/span>course_id<span class=\"token punctuation\">:<\/span><br \/>\n            errors<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\u7b2c <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>index<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> \u884c\u7f3a\u5c11 course_id&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> record<span class=\"token punctuation\">.<\/span>chapter_title<span class=\"token punctuation\">:<\/span><br \/>\n            errors<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\u7b2c <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>index<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> \u884c\u7f3a\u5c11 chapter_title&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">if<\/span> record<span class=\"token punctuation\">.<\/span>level <span class=\"token operator\">&lt;&#061;<\/span> <span class=\"token number\">0<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            errors<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\u7b2c <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>index<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> \u884c level \u975e\u6cd5: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>record<span class=\"token punctuation\">.<\/span>level<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">if<\/span> record<span class=\"token punctuation\">.<\/span>duration_seconds <span class=\"token keyword\">is<\/span> <span class=\"token keyword\">not<\/span> <span class=\"token boolean\">None<\/span> <span class=\"token keyword\">and<\/span> record<span class=\"token punctuation\">.<\/span>duration_seconds <span class=\"token operator\">&lt;<\/span> <span class=\"token number\">0<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            errors<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\u7b2c <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>index<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> \u884c duration_seconds \u975e\u6cd5&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">return<\/span> errors<\/p>\n<p>\u5728 main.py \u4e2d\u4f7f\u7528&#xff1a;<\/p>\n<p>errors <span class=\"token operator\">&#061;<\/span> validate_records<span class=\"token punctuation\">(<\/span>records<span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">if<\/span> errors<span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">for<\/span> error <span class=\"token keyword\">in<\/span> errors<span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">:<\/span><span class=\"token number\">20<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        logger<span class=\"token punctuation\">.<\/span>warning<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u6570\u636e\u8d28\u91cf\u95ee\u9898: %s&#034;<\/span><span class=\"token punctuation\">,<\/span> error<span class=\"token punctuation\">)<\/span><\/p>\n<p>\u6570\u636e\u8d28\u91cf\u68c0\u67e5\u4e0d\u4e00\u5b9a\u8981\u963b\u65ad\u6d41\u7a0b&#xff0c;\u4f46\u81f3\u5c11\u8981\u8ba9\u4f60\u77e5\u9053\u54ea\u91cc\u4e0d\u5bf9\u3002<\/p>\n<h4>11.7 \u6269\u5c55\u5230 Scrapy<\/h4>\n<p>\u5f53\u76ee\u6807\u53d8\u6210\u5927\u91cf\u8bfe\u7a0b\u3001\u591a\u5165\u53e3\u3001\u591a\u5217\u8868\u3001\u591a\u8be6\u60c5\u9875\u65f6&#xff0c;\u53ef\u4ee5\u8003\u8651 Scrapy\u3002Scrapy \u7684\u4f18\u52bf\u662f&#xff1a;<\/p>\n<ul>\n<li>\u8c03\u5ea6\u5668\u6210\u719f<\/li>\n<li>\u4e0b\u8f7d\u4e2d\u95f4\u4ef6\u5b8c\u5584<\/li>\n<li>\u53bb\u91cd\u673a\u5236\u5185\u7f6e<\/li>\n<li>\u65e5\u5fd7\u6e05\u6670<\/li>\n<li>item pipeline \u9002\u5408\u5b58\u50a8<\/li>\n<li>\u66f4\u9002\u5408\u5927\u89c4\u6a21\u4efb\u52a1<\/li>\n<\/ul>\n<p>\u4f46\u5bf9\u4e8e\u672c\u6587\u8fd9\u4e2a\u5355\u63a5\u53e3\u8bfe\u7a0b\u76ee\u5f55\u6811\u9879\u76ee&#xff0c;\u76f4\u63a5\u4e0a Scrapy \u4f1a\u7565\u663e\u91cd\u3002\u6280\u672f\u9009\u578b\u6ca1\u6709\u7edd\u5bf9\u9ad8\u7ea7&#xff0c;\u53ea\u6709\u9002\u4e0d\u9002\u5408\u3002<\/p>\n<h4>11.8 \u6269\u5c55\u5230 Playwright<\/h4>\n<p>\u5982\u679c\u63a5\u53e3\u9700\u8981\u9875\u9762\u8fd0\u884c\u540e\u624d\u80fd\u5f97\u5230&#xff0c;Playwright \u53ef\u4ee5\u7528\u4e8e&#xff1a;<\/p>\n<ul>\n<li>\u7b49\u5f85\u9875\u9762\u6e32\u67d3<\/li>\n<li>\u76d1\u542c\u63a5\u53e3\u54cd\u5e94<\/li>\n<li>\u63d0\u53d6\u9875\u9762\u4e2d\u7684\u521d\u59cb\u5316 JSON<\/li>\n<li>\u5904\u7406\u5fc5\u8981\u7684\u524d\u7aef\u72b6\u6001<\/li>\n<\/ul>\n<p>\u4e00\u4e2a\u4e2d\u6027\u3001\u5b89\u5168\u7684 Playwright \u601d\u8def\u5982\u4e0b&#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\">capture_public_json<\/span><span class=\"token punctuation\">(<\/span>page_url<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> keyword<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;catalog&#034;<\/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\">dict<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    matched<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">dict<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><\/p>\n<p>    <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><span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">def<\/span> <span class=\"token function\">handle_response<\/span><span class=\"token punctuation\">(<\/span>response<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            url <span class=\"token operator\">&#061;<\/span> response<span class=\"token punctuation\">.<\/span>url<br \/>\n            <span class=\"token keyword\">if<\/span> keyword <span class=\"token keyword\">not<\/span> <span class=\"token keyword\">in<\/span> url<span class=\"token punctuation\">:<\/span><br \/>\n                <span class=\"token keyword\">return<\/span><\/p>\n<p>            content_type <span class=\"token operator\">&#061;<\/span> response<span class=\"token punctuation\">.<\/span>headers<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;content-type&#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 string\">&#034;application\/json&#034;<\/span> <span class=\"token keyword\">not<\/span> <span class=\"token keyword\">in<\/span> content_type<span class=\"token punctuation\">:<\/span><br \/>\n                <span class=\"token keyword\">return<\/span><\/p>\n<p>            <span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                matched<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span><br \/>\n                    <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 string\">&#034;json&#034;<\/span><span class=\"token punctuation\">:<\/span> response<span class=\"token punctuation\">.<\/span>json<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                    <span class=\"token punctuation\">}<\/span><br \/>\n                <span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">except<\/span> Exception<span class=\"token punctuation\">:<\/span><br \/>\n                <span class=\"token keyword\">pass<\/span><\/p>\n<p>        page<span class=\"token punctuation\">.<\/span>on<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;response&#034;<\/span><span class=\"token punctuation\">,<\/span> handle_response<span class=\"token punctuation\">)<\/span><br \/>\n        page<span class=\"token punctuation\">.<\/span>goto<span class=\"token punctuation\">(<\/span>page_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><\/p>\n<p>        browser<span class=\"token punctuation\">.<\/span>close<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">return<\/span> matched<\/p>\n<p>\u8fd9\u6bb5\u4ee3\u7801\u53ea\u7528\u4e8e\u5b9a\u4f4d\u516c\u5f00 JSON \u54cd\u5e94&#xff0c;\u4e0d\u7528\u4e8e\u7ed5\u8fc7\u767b\u5f55\u3001\u6743\u9650\u6216\u4ed8\u8d39\u9650\u5236\u3002<\/p>\n<hr \/>\n<h3>1\ufe0f\u20e32\ufe0f\u20e3 \u603b\u7ed3\u4e0e\u5ef6\u4f38\u9605\u8bfb<\/h3>\n<p>\u672c\u6587\u5b8c\u6210\u4e86\u4e00\u4e2a\u5728\u7ebf\u6559\u80b2\u5e73\u53f0\u516c\u5f00\u76ee\u5f55\u6811\u91c7\u96c6\u9879\u76ee&#xff0c;\u4ece\u914d\u7f6e\u3001\u8bf7\u6c42\u3001\u89e3\u6790\u3001\u6e05\u6d17\u3001\u5b58\u50a8\u5230\u8fd0\u884c\u5c55\u793a\u90fd\u8d70\u4e86\u4e00\u904d\u3002<\/p>\n<p>\u6211\u4eec\u505a\u4e86\u51e0\u4ef6\u5173\u952e\u4e8b\u60c5&#xff1a;<\/p>\n<li>\u660e\u786e\u4e86\u76ee\u6807\u5b57\u6bb5&#xff1a;\u8bfe\u7a0b\u3001\u7ae0\u8282\u3001\u8bd5\u770b\u3001\u65f6\u957f\u3001\u8bb2\u5e08\u3001\u6807\u7b7e\u3002<\/li>\n<li>\u5224\u65ad\u4e86\u9875\u9762\u7c7b\u578b&#xff1a;\u52a8\u6001\u9875\u9762\u80cc\u540e\u7684\u516c\u5f00 JSON \u6570\u636e\u3002<\/li>\n<li>\u7f16\u5199\u4e86\u8bf7\u6c42\u5c42&#xff1a;headers\u3001timeout\u3001session\u3001\u5931\u8d25\u5904\u7406\u3001\u91cd\u8bd5\u9000\u907f\u3002<\/li>\n<li>\u7f16\u5199\u4e86\u89e3\u6790\u5c42&#xff1a;\u517c\u5bb9\u5b57\u6bb5\u540d&#xff0c;\u9012\u5f52\u89e3\u6790 children&#xff0c;\u4fdd\u7559\u5c42\u7ea7\u5173\u7cfb\u3002<\/li>\n<li>\u7f16\u5199\u4e86\u5b58\u50a8\u5c42&#xff1a;CSV\u3001JSON\u3001SQLite \u4e09\u79cd\u5bfc\u51fa\u65b9\u5f0f\u3002<\/li>\n<li>\u5904\u7406\u4e86\u5e38\u89c1\u95ee\u9898&#xff1a;403\u3001429\u3001\u7a7a\u58f3 HTML\u3001\u89e3\u6790\u5f02\u5e38\u3001\u4e71\u7801\u3001\u53bb\u91cd\u3002<\/li>\n<li>\u7ed9\u51fa\u4e86\u8fdb\u9636\u65b9\u5411&#xff1a;\u5e76\u53d1\u3001\u65ad\u70b9\u7eed\u8dd1\u3001\u65e5\u5fd7\u76d1\u63a7\u3001\u5b9a\u65f6\u4efb\u52a1\u3001Scrapy\u3001Playwright\u3002<\/li>\n<p>\u6211\u4e2a\u4eba\u5199\u8fd9\u7c7b\u91c7\u96c6\u4efb\u52a1\u65f6&#xff0c;\u6700\u770b\u91cd\u7684\u4e0d\u662f\u201c\u8dd1\u5f97\u591a\u5feb\u201d&#xff0c;\u800c\u662f\u201c\u4e0b\u4e2a\u6708\u8fd8\u80fd\u4e0d\u80fd\u770b\u61c2&#xff0c;\u51fa\u4e86\u95ee\u9898\u80fd\u4e0d\u80fd\u5b9a\u4f4d&#xff0c;\u76ee\u6807\u7ad9\u70b9\u80fd\u4e0d\u80fd\u627f\u53d7\u201d\u3002\u8bfe\u7a0b\u76ee\u5f55\u8fd9\u7c7b\u6570\u636e\u672c\u8eab\u4e0d\u9700\u8981\u9ad8\u9891\u6293\u53d6&#xff0c;\u7a33\u5b9a\u6027\u3001\u53ef\u7ef4\u62a4\u6027\u548c\u5408\u89c4\u8fb9\u754c\u8981\u6bd4\u5e76\u53d1\u6570\u66f4\u91cd\u8981\u3002<\/p>\n<p>\u4e0b\u4e00\u6b65\u4f60\u53ef\u4ee5\u7ee7\u7eed\u6269\u5c55&#xff1a;<\/p>\n<ul>\n<li>\u63a5\u5165\u8bfe\u7a0b\u5217\u8868\u9875&#xff0c;\u6279\u91cf\u91c7\u96c6\u591a\u4e2a\u8bfe\u7a0b\u3002<\/li>\n<li>\u589e\u52a0\u8bfe\u7a0b\u53d8\u66f4\u76d1\u63a7&#xff0c;\u6bd4\u8f83\u4eca\u5929\u548c\u6628\u5929\u7684\u76ee\u5f55\u5dee\u5f02\u3002<\/li>\n<li>\u628a SQLite \u6362\u6210 MySQL \u6216 PostgreSQL\u3002<\/li>\n<li>\u7528 Scrapy \u7ba1\u7406\u5927\u89c4\u6a21\u8bfe\u7a0b\u4efb\u52a1\u3002<\/li>\n<li>\u7528 Playwright \u8f85\u52a9\u5b9a\u4f4d\u52a8\u6001\u9875\u9762\u516c\u5f00\u63a5\u53e3\u3002<\/li>\n<li>\u589e\u52a0\u53ef\u89c6\u5316\u5206\u6790&#xff0c;\u6bd4\u5982\u8bd5\u770b\u6bd4\u4f8b\u3001\u603b\u8bfe\u65f6\u3001\u7ae0\u8282\u5c42\u7ea7\u5206\u5e03\u3002<\/li>\n<\/ul>\n<p>\u6700\u540e\u518d\u5f3a\u8c03\u4e00\u6b21&#xff1a;\u722c\u866b\u6280\u672f\u672c\u8eab\u6ca1\u6709\u95ee\u9898&#xff0c;\u5173\u952e\u5728\u4f7f\u7528\u65b9\u5f0f\u3002\u53ea\u91c7\u96c6\u516c\u5f00\u6570\u636e&#xff0c;\u63a7\u5236\u9891\u7387&#xff0c;\u5c0a\u91cd\u89c4\u5219&#xff0c;\u4e0d\u89e6\u78b0\u6743\u9650\u8fb9\u754c&#xff0c;\u8fd9\u6837\u5199\u51fa\u6765\u7684\u7a0b\u5e8f\u624d\u503c\u5f97\u957f\u671f\u7ef4\u62a4\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\/08\/20260830134203-6a94332b3bcd4.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\/08\/20260830134203-6a94332b53e9a.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":97983,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[11230,11229,11228,81,677],"topic":[],"class_list":["post-97986","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-server","tag-11230","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>\u5728\u7ebf\u6559\u80b2\u5e73\u53f0\u516c\u5f00\u76ee\u5f55\u6811\u91c7\u96c6\u5b9e\u6218\uff1a\u52a8\u6001\u8bfe\u7a0b\u7ae0\u8282\u3001\u8bd5\u770b\u72b6\u6001\u3001\u65f6\u957f\u3001\u8bb2\u5e08\u4e0e\u6807\u7b7e\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\/97986.html\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u5728\u7ebf\u6559\u80b2\u5e73\u53f0\u516c\u5f00\u76ee\u5f55\u6811\u91c7\u96c6\u5b9e\u6218\uff1a\u52a8\u6001\u8bfe\u7a0b\u7ae0\u8282\u3001\u8bd5\u770b\u72b6\u6001\u3001\u65f6\u957f\u3001\u8bb2\u5e08\u4e0e\u6807\u7b7e\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\/97986.html\" \/>\n<meta property=\"og:site_name\" content=\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"article:published_time\" content=\"2026-08-30T13:42:08+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/08\/20260830134202-6a94332a89e5c.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=\"26 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/97986.html\",\"url\":\"https:\/\/www.wsisp.com\/helps\/97986.html\",\"name\":\"\u5728\u7ebf\u6559\u80b2\u5e73\u53f0\u516c\u5f00\u76ee\u5f55\u6811\u91c7\u96c6\u5b9e\u6218\uff1a\u52a8\u6001\u8bfe\u7a0b\u7ae0\u8282\u3001\u8bd5\u770b\u72b6\u6001\u3001\u65f6\u957f\u3001\u8bb2\u5e08\u4e0e\u6807\u7b7e\u89e3\u6790 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"isPartOf\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\"},\"datePublished\":\"2026-08-30T13:42:08+00:00\",\"dateModified\":\"2026-08-30T13:42:08+00:00\",\"author\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/97986.html#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.wsisp.com\/helps\/97986.html\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/97986.html#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.wsisp.com\/helps\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u5728\u7ebf\u6559\u80b2\u5e73\u53f0\u516c\u5f00\u76ee\u5f55\u6811\u91c7\u96c6\u5b9e\u6218\uff1a\u52a8\u6001\u8bfe\u7a0b\u7ae0\u8282\u3001\u8bd5\u770b\u72b6\u6001\u3001\u65f6\u957f\u3001\u8bb2\u5e08\u4e0e\u6807\u7b7e\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":"\u5728\u7ebf\u6559\u80b2\u5e73\u53f0\u516c\u5f00\u76ee\u5f55\u6811\u91c7\u96c6\u5b9e\u6218\uff1a\u52a8\u6001\u8bfe\u7a0b\u7ae0\u8282\u3001\u8bd5\u770b\u72b6\u6001\u3001\u65f6\u957f\u3001\u8bb2\u5e08\u4e0e\u6807\u7b7e\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\/97986.html","og_locale":"zh_CN","og_type":"article","og_title":"\u5728\u7ebf\u6559\u80b2\u5e73\u53f0\u516c\u5f00\u76ee\u5f55\u6811\u91c7\u96c6\u5b9e\u6218\uff1a\u52a8\u6001\u8bfe\u7a0b\u7ae0\u8282\u3001\u8bd5\u770b\u72b6\u6001\u3001\u65f6\u957f\u3001\u8bb2\u5e08\u4e0e\u6807\u7b7e\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\/97986.html","og_site_name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","article_published_time":"2026-08-30T13:42:08+00:00","og_image":[{"url":"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/08\/20260830134202-6a94332a89e5c.png"}],"author":"admin","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"admin","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"26 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wsisp.com\/helps\/97986.html","url":"https:\/\/www.wsisp.com\/helps\/97986.html","name":"\u5728\u7ebf\u6559\u80b2\u5e73\u53f0\u516c\u5f00\u76ee\u5f55\u6811\u91c7\u96c6\u5b9e\u6218\uff1a\u52a8\u6001\u8bfe\u7a0b\u7ae0\u8282\u3001\u8bd5\u770b\u72b6\u6001\u3001\u65f6\u957f\u3001\u8bb2\u5e08\u4e0e\u6807\u7b7e\u89e3\u6790 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","isPartOf":{"@id":"https:\/\/www.wsisp.com\/helps\/#website"},"datePublished":"2026-08-30T13:42:08+00:00","dateModified":"2026-08-30T13:42:08+00:00","author":{"@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41"},"breadcrumb":{"@id":"https:\/\/www.wsisp.com\/helps\/97986.html#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wsisp.com\/helps\/97986.html"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wsisp.com\/helps\/97986.html#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.wsisp.com\/helps"},{"@type":"ListItem","position":2,"name":"\u5728\u7ebf\u6559\u80b2\u5e73\u53f0\u516c\u5f00\u76ee\u5f55\u6811\u91c7\u96c6\u5b9e\u6218\uff1a\u52a8\u6001\u8bfe\u7a0b\u7ae0\u8282\u3001\u8bd5\u770b\u72b6\u6001\u3001\u65f6\u957f\u3001\u8bb2\u5e08\u4e0e\u6807\u7b7e\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\/97986","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=97986"}],"version-history":[{"count":0,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/97986\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media\/97983"}],"wp:attachment":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media?parent=97986"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/categories?post=97986"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/tags?post=97986"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/topic?post=97986"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}