{"id":69211,"date":"2026-01-31T08:05:56","date_gmt":"2026-01-31T00:05:56","guid":{"rendered":"https:\/\/www.wsisp.com\/helps\/69211.html"},"modified":"2026-01-31T08:05:56","modified_gmt":"2026-01-31T00:05:56","slug":"python%e7%88%ac%e8%99%ab%e5%85%a5%e9%97%a8%e5%ae%9e%e6%88%98%ef%bc%9a%e4%bb%8e%e9%9b%b6%e5%bc%80%e5%a7%8b%e6%8a%93%e5%8f%96%e7%bd%91%e9%a1%b5%e6%95%b0%e6%8d%ae","status":"publish","type":"post","link":"https:\/\/www.wsisp.com\/helps\/69211.html","title":{"rendered":"Python\u722c\u866b\u5165\u95e8\u5b9e\u6218\uff1a\u4ece\u96f6\u5f00\u59cb\u6293\u53d6\u7f51\u9875\u6570\u636e"},"content":{"rendered":"<h3>\u524d\u8a00&#xff1a;\u4e3a\u4ec0\u4e48\u5b66\u4e60\u722c\u866b&#xff1f;<\/h3>\n<p>\u5728\u5f53\u4eca\u5927\u6570\u636e\u65f6\u4ee3&#xff0c;\u7f51\u7edc\u6570\u636e\u91c7\u96c6&#xff08;\u722c\u866b&#xff09;\u5df2\u6210\u4e3a\u6570\u636e\u5206\u6790\u548c\u4eba\u5de5\u667a\u80fd\u9886\u57df\u7684\u91cd\u8981\u6280\u80fd\u3002\u65e0\u8bba\u662f\u5e02\u573a\u8c03\u7814\u3001\u7ade\u54c1\u5206\u6790&#xff0c;\u8fd8\u662f\u5b66\u672f\u7814\u7a76&#xff0c;\u722c\u866b\u6280\u672f\u90fd\u80fd\u5e2e\u52a9\u6211\u4eec\u9ad8\u6548\u83b7\u53d6\u6240\u9700\u4fe1\u606f\u3002\u672c\u6587\u5c06\u5e26\u9886Python\u521d\u5b66\u8005\u4e00\u6b65\u6b65\u638c\u63e1\u722c\u866b\u6838\u5fc3\u6280\u672f\u3002<\/p>\n<h3>\u4e00\u3001\u722c\u866b\u57fa\u7840\u51c6\u5907<\/h3>\n<h4>1.1 \u73af\u5883\u642d\u5efa<\/h4>\n<p><span class=\"token comment\"># \u521b\u5efa\u865a\u62df\u73af\u5883&#xff08;\u63a8\u8350&#xff09;<\/span><br \/>\npython <span class=\"token operator\">&#8211;<\/span>m venv spider_env<br \/>\nsource spider_env<span class=\"token operator\">\/<\/span><span class=\"token builtin\">bin<\/span><span class=\"token operator\">\/<\/span>activate  <span class=\"token comment\"># Linux\/Mac<\/span><br \/>\nspider_env\\\\Scripts\\\\activate     <span class=\"token comment\"># Windows<\/span><\/p>\n<p><span class=\"token comment\"># \u5b89\u88c5\u5fc5\u8981\u5e93<\/span><br \/>\npip install requests beautifulsoup4 lxml pandas<br \/>\n<span class=\"token comment\"># \u53ef\u9009&#xff1a;\u5b89\u88c5\u66f4\u5f3a\u5927\u7684\u89e3\u6790\u5e93<\/span><br \/>\npip install parsel selenium playwright<\/p>\n<h4>1.2 \u722c\u866b\u6838\u5fc3\u5e93\u4ecb\u7ecd<\/h4>\n<ul>\n<li>requests&#xff1a;\u53d1\u9001HTTP\u8bf7\u6c42<\/li>\n<li>BeautifulSoup&#xff1a;\u89e3\u6790HTML\/XML<\/li>\n<li>lxml&#xff1a;\u9ad8\u6548\u89e3\u6790\u5e93<\/li>\n<li>pandas&#xff1a;\u6570\u636e\u5904\u7406\u548c\u5b58\u50a8<\/li>\n<\/ul>\n<h3>\u4e8c\u3001\u7b2c\u4e00\u4e2a\u722c\u866b&#xff1a;\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/h3>\n<h4>2.1 \u7b80\u5355\u7684GET\u8bf7\u6c42<\/h4>\n<p><span class=\"token keyword\">import<\/span> requests<br \/>\n<span class=\"token keyword\">from<\/span> bs4 <span class=\"token keyword\">import<\/span> BeautifulSoup<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">get_webpage<\/span><span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u83b7\u53d6\u7f51\u9875\u5185\u5bb9&#034;&#034;&#034;<\/span><br \/>\n    headers <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n        <span class=\"token string\">&#039;User-Agent&#039;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#039;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36&#039;<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><\/p>\n<p>    <span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        response <span class=\"token operator\">&#061;<\/span> requests<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">,<\/span> headers<span class=\"token operator\">&#061;<\/span>headers<span class=\"token punctuation\">,<\/span> timeout<span class=\"token operator\">&#061;<\/span><span class=\"token number\">10<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        response<span class=\"token punctuation\">.<\/span>raise_for_status<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>  <span class=\"token comment\"># \u68c0\u67e5\u8bf7\u6c42\u662f\u5426\u6210\u529f<\/span><br \/>\n        response<span class=\"token punctuation\">.<\/span>encoding <span class=\"token operator\">&#061;<\/span> response<span class=\"token punctuation\">.<\/span>apparent_encoding<br \/>\n        <span class=\"token keyword\">return<\/span> response<span class=\"token punctuation\">.<\/span>text<br \/>\n    <span class=\"token keyword\">except<\/span> requests<span class=\"token punctuation\">.<\/span>RequestException <span class=\"token keyword\">as<\/span> e<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;\u8bf7\u6c42\u5931\u8d25: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>e<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/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 comment\"># \u6d4b\u8bd5\u722c\u53d6\u8c46\u74e3\u7535\u5f71TOP250<\/span><br \/>\nurl <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;https:\/\/movie.douban.com\/top250&#034;<\/span><br \/>\nhtml <span class=\"token operator\">&#061;<\/span> get_webpage<span class=\"token punctuation\">(<\/span>url<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;\u83b7\u53d6\u5230 <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span><span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> \u4e2a\u5b57\u7b26&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<h4>2.2 \u89e3\u6790HTML\u5185\u5bb9<\/h4>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">parse_movie_info<\/span><span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u89e3\u6790\u7535\u5f71\u4fe1\u606f&#034;&#034;&#034;<\/span><br \/>\n    <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> html<span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><\/p>\n<p>    soup <span class=\"token operator\">&#061;<\/span> BeautifulSoup<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#039;lxml&#039;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    movies <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><\/p>\n<p>    <span class=\"token comment\"># \u67e5\u627e\u6240\u6709\u7535\u5f71\u9879\u76ee<\/span><br \/>\n    items <span class=\"token operator\">&#061;<\/span> soup<span class=\"token punctuation\">.<\/span>find_all<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;div&#039;<\/span><span class=\"token punctuation\">,<\/span> class_<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#039;item&#039;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">for<\/span> item <span class=\"token keyword\">in<\/span> items<span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">:<\/span><span class=\"token number\">5<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span>  <span class=\"token comment\"># \u53ea\u53d6\u524d5\u90e8\u7535\u5f71<\/span><br \/>\n        <span class=\"token comment\"># \u63d0\u53d6\u7535\u5f71\u6807\u9898<\/span><br \/>\n        title_elem <span class=\"token operator\">&#061;<\/span> item<span class=\"token punctuation\">.<\/span>find<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;span&#039;<\/span><span class=\"token punctuation\">,<\/span> class_<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#039;title&#039;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        title <span class=\"token operator\">&#061;<\/span> title_elem<span class=\"token punctuation\">.<\/span>text <span class=\"token keyword\">if<\/span> title_elem <span class=\"token keyword\">else<\/span> <span class=\"token string\">&#034;\u65e0\u6807\u9898&#034;<\/span><\/p>\n<p>        <span class=\"token comment\"># \u63d0\u53d6\u8bc4\u5206<\/span><br \/>\n        rating_elem <span class=\"token operator\">&#061;<\/span> item<span class=\"token punctuation\">.<\/span>find<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;span&#039;<\/span><span class=\"token punctuation\">,<\/span> class_<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#039;rating_num&#039;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        rating <span class=\"token operator\">&#061;<\/span> rating_elem<span class=\"token punctuation\">.<\/span>text <span class=\"token keyword\">if<\/span> rating_elem <span class=\"token keyword\">else<\/span> <span class=\"token string\">&#034;\u65e0\u8bc4\u5206&#034;<\/span><\/p>\n<p>        <span class=\"token comment\"># \u63d0\u53d6\u7b80\u4ecb<\/span><br \/>\n        quote_elem <span class=\"token operator\">&#061;<\/span> item<span class=\"token punctuation\">.<\/span>find<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;span&#039;<\/span><span class=\"token punctuation\">,<\/span> class_<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#039;inq&#039;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        quote <span class=\"token operator\">&#061;<\/span> quote_elem<span class=\"token punctuation\">.<\/span>text <span class=\"token keyword\">if<\/span> quote_elem <span class=\"token keyword\">else<\/span> <span class=\"token string\">&#034;\u65e0\u7b80\u4ecb&#034;<\/span><\/p>\n<p>        movies<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">{<\/span><br \/>\n            <span class=\"token string\">&#039;title&#039;<\/span><span class=\"token punctuation\">:<\/span> title<span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#039;rating&#039;<\/span><span class=\"token punctuation\">:<\/span> rating<span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#039;quote&#039;<\/span><span class=\"token punctuation\">:<\/span> quote<br \/>\n        <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">return<\/span> movies<\/p>\n<p><span class=\"token comment\"># \u6267\u884c\u89e3\u6790<\/span><br \/>\nmovies <span class=\"token operator\">&#061;<\/span> parse_movie_info<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">for<\/span> i<span class=\"token punctuation\">,<\/span> movie <span class=\"token keyword\">in<\/span> <span class=\"token builtin\">enumerate<\/span><span class=\"token punctuation\">(<\/span>movies<span class=\"token punctuation\">,<\/span> <span class=\"token number\">1<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>i<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">. <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>movie<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#039;title&#039;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> &#8211; \u8bc4\u5206: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>movie<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#039;rating&#039;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><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;   \u7b80\u4ecb: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>movie<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#039;quote&#039;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">\\\\n&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<h3>\u4e09\u3001\u5b9e\u6218\u9879\u76ee&#xff1a;\u722c\u53d6\u5929\u6c14\u9884\u62a5\u6570\u636e<\/h3>\n<h4>3.1 \u5206\u6790\u76ee\u6807\u7f51\u7ad9<\/h4>\n<p>\u6211\u4eec\u4ee5\u4e2d\u56fd\u5929\u6c14\u7f51\u4e3a\u4f8b&#xff1a;http:\/\/www.weather.com.cn\/weather\/101010100.shtml<\/p>\n<h4>3.2 \u5b8c\u6574\u722c\u866b\u4ee3\u7801<\/h4>\n<p><span class=\"token keyword\">import<\/span> requests<br \/>\n<span class=\"token keyword\">from<\/span> bs4 <span class=\"token keyword\">import<\/span> BeautifulSoup<br \/>\n<span class=\"token keyword\">import<\/span> pandas <span class=\"token keyword\">as<\/span> pd<br \/>\n<span class=\"token keyword\">import<\/span> time<br \/>\n<span class=\"token keyword\">import<\/span> random<\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">WeatherSpider<\/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>headers <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n            <span class=\"token string\">&#039;User-Agent&#039;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#039;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36&#039;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#039;Referer&#039;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#039;http:\/\/www.weather.com.cn\/&#039;<\/span><br \/>\n        <span class=\"token punctuation\">}<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">get_weather<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> city_code<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#039;101010100&#039;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u83b7\u53d6\u6307\u5b9a\u57ce\u5e02\u7684\u5929\u6c14\u6570\u636e&#034;&#034;&#034;<\/span><br \/>\n        url <span class=\"token operator\">&#061;<\/span> <span class=\"token string-interpolation\"><span class=\"token string\">f&#039;http:\/\/www.weather.com.cn\/weather\/<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>city_code<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">.shtml&#039;<\/span><\/span><\/p>\n<p>        <span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            response <span class=\"token operator\">&#061;<\/span> requests<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">,<\/span> headers<span class=\"token operator\">&#061;<\/span>self<span class=\"token punctuation\">.<\/span>headers<span class=\"token punctuation\">,<\/span> timeout<span class=\"token operator\">&#061;<\/span><span class=\"token number\">15<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            response<span class=\"token punctuation\">.<\/span>encoding <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#039;utf-8&#039;<\/span><\/p>\n<p>            <span class=\"token keyword\">if<\/span> response<span class=\"token punctuation\">.<\/span>status_code <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token number\">200<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                <span class=\"token keyword\">return<\/span> self<span class=\"token punctuation\">.<\/span>parse_weather<span class=\"token punctuation\">(<\/span>response<span class=\"token punctuation\">.<\/span>text<span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">else<\/span><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;\u8bf7\u6c42\u5931\u8d25&#xff0c;\u72b6\u6001\u7801&#xff1a;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>response<span class=\"token punctuation\">.<\/span>status_code<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/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\">except<\/span> Exception <span class=\"token keyword\">as<\/span> e<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;\u53d1\u751f\u9519\u8bef&#xff1a;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>e<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/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\">def<\/span> <span class=\"token function\">parse_weather<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> html<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u89e3\u6790\u5929\u6c14\u6570\u636e&#034;&#034;&#034;<\/span><br \/>\n        soup <span class=\"token operator\">&#061;<\/span> BeautifulSoup<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#039;lxml&#039;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        weather_data <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><\/p>\n<p>        <span class=\"token comment\"># \u67e5\u627e7\u5929\u5929\u6c14\u9884\u62a5<\/span><br \/>\n        days <span class=\"token operator\">&#061;<\/span> soup<span class=\"token punctuation\">.<\/span>select<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;ul.t.clearfix &gt; li&#039;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">for<\/span> day <span class=\"token keyword\">in<\/span> days<span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">:<\/span><span class=\"token number\">7<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span>  <span class=\"token comment\"># \u53d67\u5929\u6570\u636e<\/span><br \/>\n            <span class=\"token comment\"># \u63d0\u53d6\u65e5\u671f<\/span><br \/>\n            date_elem <span class=\"token operator\">&#061;<\/span> day<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;h1&#039;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            date <span class=\"token operator\">&#061;<\/span> date_elem<span class=\"token punctuation\">.<\/span>text <span class=\"token keyword\">if<\/span> date_elem <span class=\"token keyword\">else<\/span> <span class=\"token string\">&#034;\u672a\u77e5\u65e5\u671f&#034;<\/span><\/p>\n<p>            <span class=\"token comment\"># \u63d0\u53d6\u5929\u6c14\u72b6\u51b5<\/span><br \/>\n            wea_elem <span class=\"token operator\">&#061;<\/span> day<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;p.wea&#039;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            weather <span class=\"token operator\">&#061;<\/span> wea_elem<span class=\"token punctuation\">.<\/span>text <span class=\"token keyword\">if<\/span> wea_elem <span class=\"token keyword\">else<\/span> <span class=\"token string\">&#034;\u672a\u77e5\u5929\u6c14&#034;<\/span><\/p>\n<p>            <span class=\"token comment\"># \u63d0\u53d6\u6e29\u5ea6<\/span><br \/>\n            temp_elem <span class=\"token operator\">&#061;<\/span> day<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;p.tem&#039;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> temp_elem<span class=\"token punctuation\">:<\/span><br \/>\n                high_temp <span class=\"token operator\">&#061;<\/span> temp_elem<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;span&#039;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>text <span class=\"token keyword\">if<\/span> temp_elem<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;span&#039;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">else<\/span> <span class=\"token string\">&#034;\u672a\u77e5&#034;<\/span><br \/>\n                low_temp <span class=\"token operator\">&#061;<\/span> temp_elem<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;i&#039;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>text <span class=\"token keyword\">if<\/span> temp_elem<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;i&#039;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">else<\/span> <span class=\"token string\">&#034;\u672a\u77e5&#034;<\/span><br \/>\n            <span class=\"token keyword\">else<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                high_temp <span class=\"token operator\">&#061;<\/span> low_temp <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;\u672a\u77e5&#034;<\/span><\/p>\n<p>            <span class=\"token comment\"># \u63d0\u53d6\u98ce\u5411\u98ce\u529b<\/span><br \/>\n            win_elem <span class=\"token operator\">&#061;<\/span> day<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;p.win&#039;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> win_elem<span class=\"token punctuation\">:<\/span><br \/>\n                wind <span class=\"token operator\">&#061;<\/span> win_elem<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;i&#039;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>text <span class=\"token keyword\">if<\/span> win_elem<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;i&#039;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">else<\/span> <span class=\"token string\">&#034;\u672a\u77e5&#034;<\/span><br \/>\n            <span class=\"token keyword\">else<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                wind <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;\u672a\u77e5&#034;<\/span><\/p>\n<p>            weather_data<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">{<\/span><br \/>\n                <span class=\"token string\">&#039;\u65e5\u671f&#039;<\/span><span class=\"token punctuation\">:<\/span> date<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#039;\u5929\u6c14&#039;<\/span><span class=\"token punctuation\">:<\/span> weather<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#039;\u6700\u9ad8\u6e29&#039;<\/span><span class=\"token punctuation\">:<\/span> high_temp<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#039;\u6700\u4f4e\u6e29&#039;<\/span><span class=\"token punctuation\">:<\/span> low_temp<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#039;\u98ce\u5411\u98ce\u529b&#039;<\/span><span class=\"token punctuation\">:<\/span> wind<br \/>\n            <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">return<\/span> weather_data<\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">save_to_csv<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> data<span class=\"token punctuation\">,<\/span> filename<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#039;weather.csv&#039;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u4fdd\u5b58\u6570\u636e\u5230CSV\u6587\u4ef6&#034;&#034;&#034;<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> data<span class=\"token punctuation\">:<\/span><br \/>\n            df <span class=\"token operator\">&#061;<\/span> pd<span class=\"token punctuation\">.<\/span>DataFrame<span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">)<\/span><br \/>\n            df<span class=\"token punctuation\">.<\/span>to_csv<span class=\"token punctuation\">(<\/span>filename<span class=\"token punctuation\">,<\/span> index<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">False<\/span><span class=\"token punctuation\">,<\/span> encoding<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#039;utf-8-sig&#039;<\/span><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;\u6570\u636e\u5df2\u4fdd\u5b58\u5230 <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>filename<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> <span class=\"token boolean\">True<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> <span class=\"token boolean\">False<\/span><\/p>\n<p><span class=\"token comment\"># \u4f7f\u7528\u793a\u4f8b<\/span><br \/>\n<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    spider <span class=\"token operator\">&#061;<\/span> WeatherSpider<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token comment\"># \u57ce\u5e02\u4ee3\u7801&#xff1a;\u5317\u4eac101010100&#xff0c;\u4e0a\u6d77101020100&#xff0c;\u5e7f\u5dde101280101<\/span><br \/>\n    weather_data <span class=\"token operator\">&#061;<\/span> spider<span class=\"token punctuation\">.<\/span>get_weather<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;101010100&#039;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">if<\/span> weather_data<span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u5317\u4eac7\u5929\u5929\u6c14\u9884\u62a5&#xff1a;&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;&#061;&#034;<\/span><span class=\"token operator\">*<\/span><span class=\"token number\">60<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">for<\/span> day <span class=\"token keyword\">in<\/span> weather_data<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;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>day<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#039;\u65e5\u671f&#039;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><span class=\"token format-spec\">10<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>day<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#039;\u5929\u6c14&#039;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><span class=\"token format-spec\">10<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> &#034;<\/span><\/span><br \/>\n                  <span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\u6e29\u5ea6&#xff1a;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>day<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#039;\u6700\u4f4e\u6e29&#039;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">~<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>day<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#039;\u6700\u9ad8\u6e29&#039;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> &#034;<\/span><\/span><br \/>\n                  <span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\u98ce\u529b&#xff1a;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>day<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#039;\u98ce\u5411\u98ce\u529b&#039;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token comment\"># \u4fdd\u5b58\u6570\u636e<\/span><br \/>\n        spider<span class=\"token punctuation\">.<\/span>save_to_csv<span class=\"token punctuation\">(<\/span>weather_data<span class=\"token punctuation\">)<\/span><\/p>\n<h3>\u56db\u3001\u9ad8\u7ea7\u6280\u5de7\u4e0e\u6ce8\u610f\u4e8b\u9879<\/h3>\n<h4>4.1 \u5904\u7406\u52a8\u6001\u52a0\u8f7d\u5185\u5bb9<\/h4>\n<p><span class=\"token keyword\">from<\/span> selenium <span class=\"token keyword\">import<\/span> webdriver<br \/>\n<span class=\"token keyword\">from<\/span> selenium<span class=\"token punctuation\">.<\/span>webdriver<span class=\"token punctuation\">.<\/span>common<span class=\"token punctuation\">.<\/span>by <span class=\"token keyword\">import<\/span> By<br \/>\n<span class=\"token keyword\">from<\/span> selenium<span class=\"token punctuation\">.<\/span>webdriver<span class=\"token punctuation\">.<\/span>support<span class=\"token punctuation\">.<\/span>ui <span class=\"token keyword\">import<\/span> WebDriverWait<br \/>\n<span class=\"token keyword\">from<\/span> selenium<span class=\"token punctuation\">.<\/span>webdriver<span class=\"token punctuation\">.<\/span>support <span class=\"token keyword\">import<\/span> expected_conditions <span class=\"token keyword\">as<\/span> EC<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">dynamic_crawler<\/span><span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u4f7f\u7528Selenium\u5904\u7406\u52a8\u6001\u9875\u9762&#034;&#034;&#034;<\/span><br \/>\n    options <span class=\"token operator\">&#061;<\/span> webdriver<span class=\"token punctuation\">.<\/span>ChromeOptions<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    options<span class=\"token punctuation\">.<\/span>add_argument<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;&#8211;headless&#039;<\/span><span class=\"token punctuation\">)<\/span>  <span class=\"token comment\"># \u65e0\u5934\u6a21\u5f0f<\/span><br \/>\n    options<span class=\"token punctuation\">.<\/span>add_argument<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;&#8211;disable-gpu&#039;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    driver <span class=\"token operator\">&#061;<\/span> webdriver<span class=\"token punctuation\">.<\/span>Chrome<span class=\"token punctuation\">(<\/span>options<span class=\"token operator\">&#061;<\/span>options<span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        driver<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token comment\"># \u7b49\u5f85\u5143\u7d20\u52a0\u8f7d<\/span><br \/>\n        wait <span class=\"token operator\">&#061;<\/span> WebDriverWait<span class=\"token punctuation\">(<\/span>driver<span class=\"token punctuation\">,<\/span> <span class=\"token number\">10<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        element <span class=\"token operator\">&#061;<\/span> wait<span class=\"token punctuation\">.<\/span>until<span class=\"token punctuation\">(<\/span><br \/>\n            EC<span class=\"token punctuation\">.<\/span>presence_of_element_located<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">(<\/span>By<span class=\"token punctuation\">.<\/span>CLASS_NAME<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;content&#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 comment\"># \u83b7\u53d6\u9875\u9762\u6e90\u7801<\/span><br \/>\n        html <span class=\"token operator\">&#061;<\/span> driver<span class=\"token punctuation\">.<\/span>page_source<br \/>\n        <span class=\"token keyword\">return<\/span> html<br \/>\n    <span class=\"token keyword\">finally<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        driver<span class=\"token punctuation\">.<\/span>quit<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<h4>4.2 \u53cd\u722c\u866b\u7b56\u7565\u5e94\u5bf9<\/h4>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">AntiAntiSpider<\/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>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>delay_range <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">(<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">3<\/span><span class=\"token punctuation\">)<\/span>  <span class=\"token comment\"># \u968f\u673a\u5ef6\u8fdf1-3\u79d2<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">random_delay<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u968f\u673a\u5ef6\u8fdf&#xff0c;\u907f\u514d\u8bf7\u6c42\u8fc7\u5feb&#034;&#034;&#034;<\/span><br \/>\n        time<span class=\"token punctuation\">.<\/span>sleep<span class=\"token punctuation\">(<\/span>random<span class=\"token punctuation\">.<\/span>uniform<span class=\"token punctuation\">(<\/span><span class=\"token operator\">*<\/span>self<span class=\"token punctuation\">.<\/span>delay_range<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">rotate_user_agent<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u8f6e\u6362User-Agent&#034;&#034;&#034;<\/span><br \/>\n        user_agents <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><br \/>\n            <span class=\"token string\">&#039;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36&#039;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#039;Mozilla\/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit\/605.1.15&#039;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#039;Mozilla\/5.0 (X11; Linux x86_64) AppleWebKit\/537.36&#039;<\/span><br \/>\n        <span class=\"token punctuation\">]<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> random<span class=\"token punctuation\">.<\/span>choice<span class=\"token punctuation\">(<\/span>user_agents<span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">make_request<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">,<\/span> max_retries<span class=\"token operator\">&#061;<\/span><span class=\"token number\">3<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u5e26\u6709\u91cd\u8bd5\u673a\u5236\u7684\u8bf7\u6c42&#034;&#034;&#034;<\/span><br \/>\n        <span class=\"token keyword\">for<\/span> attempt <span class=\"token keyword\">in<\/span> <span class=\"token builtin\">range<\/span><span class=\"token punctuation\">(<\/span>max_retries<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                headers <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><span class=\"token string\">&#039;User-Agent&#039;<\/span><span class=\"token punctuation\">:<\/span> self<span class=\"token punctuation\">.<\/span>rotate_user_agent<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">}<\/span><br \/>\n                response <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>session<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">,<\/span> headers<span class=\"token operator\">&#061;<\/span>headers<span class=\"token punctuation\">,<\/span> timeout<span class=\"token operator\">&#061;<\/span><span class=\"token number\">15<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>                <span class=\"token keyword\">if<\/span> response<span class=\"token punctuation\">.<\/span>status_code <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token number\">200<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                    <span class=\"token keyword\">return<\/span> response<br \/>\n                <span class=\"token keyword\">elif<\/span> response<span class=\"token punctuation\">.<\/span>status_code <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token number\">429<\/span><span class=\"token punctuation\">:<\/span>  <span class=\"token comment\"># \u8bf7\u6c42\u8fc7\u591a<\/span><br \/>\n                    <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u89e6\u53d1\u9891\u7387\u9650\u5236&#xff0c;\u7b49\u5f85\u540e\u91cd\u8bd5&#8230;&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n                    time<span class=\"token punctuation\">.<\/span>sleep<span class=\"token punctuation\">(<\/span><span class=\"token number\">10<\/span><span class=\"token punctuation\">)<\/span><br \/>\n                <span class=\"token keyword\">else<\/span><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;\u8bf7\u6c42\u5931\u8d25&#xff0c;\u72b6\u6001\u7801&#xff1a;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>response<span class=\"token punctuation\">.<\/span>status_code<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\">except<\/span> Exception <span class=\"token keyword\">as<\/span> e<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;\u8bf7\u6c42\u5f02\u5e38&#xff1a;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>e<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>            self<span class=\"token punctuation\">.<\/span>random_delay<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">return<\/span> <span class=\"token boolean\">None<\/span><\/p>\n<h4>4.3 \u6570\u636e\u5b58\u50a8\u65b9\u6848<\/h4>\n<p><span class=\"token keyword\">import<\/span> json<br \/>\n<span class=\"token keyword\">import<\/span> sqlite3<br \/>\n<span class=\"token keyword\">from<\/span> datetime <span class=\"token keyword\">import<\/span> datetime<\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">DataStorage<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u6570\u636e\u5b58\u50a8\u7ba1\u7406\u7c7b&#034;&#034;&#034;<\/span><\/p>\n<p>    <span class=\"token decorator annotation punctuation\">&#064;staticmethod<\/span><br \/>\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">save_json<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">,<\/span> filename<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u4fdd\u5b58\u4e3aJSON\u683c\u5f0f&#034;&#034;&#034;<\/span><br \/>\n        <span class=\"token keyword\">with<\/span> <span class=\"token builtin\">open<\/span><span class=\"token punctuation\">(<\/span>filename<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#039;w&#039;<\/span><span class=\"token punctuation\">,<\/span> encoding<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#039;utf-8&#039;<\/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><br \/>\n        <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;JSON\u6570\u636e\u5df2\u4fdd\u5b58\u5230 <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>filename<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token decorator annotation punctuation\">&#064;staticmethod<\/span><br \/>\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">save_sqlite<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">,<\/span> db_name<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#039;spider_data.db&#039;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u4fdd\u5b58\u5230SQLite\u6570\u636e\u5e93&#034;&#034;&#034;<\/span><br \/>\n        conn <span class=\"token operator\">&#061;<\/span> sqlite3<span class=\"token punctuation\">.<\/span>connect<span class=\"token punctuation\">(<\/span>db_name<span class=\"token punctuation\">)<\/span><br \/>\n        cursor <span class=\"token operator\">&#061;<\/span> conn<span class=\"token punctuation\">.<\/span>cursor<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token comment\"># \u521b\u5efa\u8868<\/span><br \/>\n        cursor<span class=\"token punctuation\">.<\/span>execute<span class=\"token punctuation\">(<\/span><span class=\"token triple-quoted-string string\">&#039;&#039;&#039;<br \/>\n            CREATE TABLE IF NOT EXISTS weather (<br \/>\n                id INTEGER PRIMARY KEY AUTOINCREMENT,<br \/>\n                date TEXT,<br \/>\n                weather TEXT,<br \/>\n                high_temp TEXT,<br \/>\n                low_temp TEXT,<br \/>\n                wind TEXT,<br \/>\n                crawl_time TIMESTAMP<br \/>\n            )<br \/>\n        &#039;&#039;&#039;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token comment\"># \u63d2\u5165\u6570\u636e<\/span><br \/>\n        <span class=\"token keyword\">for<\/span> item <span class=\"token keyword\">in<\/span> data<span class=\"token punctuation\">:<\/span><br \/>\n            cursor<span class=\"token punctuation\">.<\/span>execute<span class=\"token punctuation\">(<\/span><span class=\"token triple-quoted-string string\">&#039;&#039;&#039;<br \/>\n                INSERT INTO weather (date, weather, high_temp, low_temp, wind, crawl_time)<br \/>\n                VALUES (?, ?, ?, ?, ?, ?)<br \/>\n            &#039;&#039;&#039;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">(<\/span><br \/>\n                item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#039;\u65e5\u671f&#039;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#039;\u5929\u6c14&#039;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#039;\u6700\u9ad8\u6e29&#039;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#039;\u6700\u4f4e\u6e29&#039;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                item<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#039;\u98ce\u5411\u98ce\u529b&#039;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n                datetime<span class=\"token punctuation\">.<\/span>now<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        conn<span class=\"token punctuation\">.<\/span>commit<span class=\"token punctuation\">(<\/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><br \/>\n        <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\u6570\u636e\u5df2\u4fdd\u5b58\u5230\u6570\u636e\u5e93 <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>db_name<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<h3>\u4e94\u3001\u4f26\u7406\u4e0e\u6cd5\u5f8b\u6ce8\u610f\u4e8b\u9879<\/h3>\n<h4>5.1 \u722c\u866b\u9053\u5fb7\u89c4\u8303<\/h4>\n<li>\u9075\u5b88robots.txt&#xff1a;\u68c0\u67e5\u76ee\u6807\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6<\/li>\n<li>\u9650\u5236\u8bf7\u6c42\u9891\u7387&#xff1a;\u907f\u514d\u5bf9\u670d\u52a1\u5668\u9020\u6210\u538b\u529b<\/li>\n<li>\u5c0a\u91cd\u7248\u6743&#xff1a;\u4e0d\u6293\u53d6\u7248\u6743\u4fdd\u62a4\u5185\u5bb9<\/li>\n<li>\u4fdd\u62a4\u9690\u79c1&#xff1a;\u4e0d\u6536\u96c6\u4e2a\u4eba\u654f\u611f\u4fe1\u606f<\/li>\n<h4>5.2 \u68c0\u67e5robots.txt<\/h4>\n<p><span class=\"token keyword\">import<\/span> urllib<span class=\"token punctuation\">.<\/span>robotparser<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">check_robots_permission<\/span><span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">,<\/span> user_agent<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#039;*&#039;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u68c0\u67e5robots.txt\u6743\u9650&#034;&#034;&#034;<\/span><br \/>\n    rp <span class=\"token operator\">&#061;<\/span> urllib<span class=\"token punctuation\">.<\/span>robotparser<span class=\"token punctuation\">.<\/span>RobotFileParser<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    base_url <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#039;\/&#039;<\/span><span class=\"token punctuation\">.<\/span>join<span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">.<\/span>split<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;\/&#039;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">:<\/span><span class=\"token number\">3<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    rp<span class=\"token punctuation\">.<\/span>set_url<span class=\"token punctuation\">(<\/span>base_url <span class=\"token operator\">&#043;<\/span> <span class=\"token string\">&#034;\/robots.txt&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    rp<span class=\"token punctuation\">.<\/span>read<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">return<\/span> rp<span class=\"token punctuation\">.<\/span>can_fetch<span class=\"token punctuation\">(<\/span>user_agent<span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u4f7f\u7528\u793a\u4f8b<\/span><br \/>\nurl <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;https:\/\/www.example.com\/data&#034;<\/span><br \/>\n<span class=\"token keyword\">if<\/span> check_robots_permission<span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u5141\u8bb8\u722c\u53d6&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">else<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u7981\u6b62\u722c\u53d6&#xff0c;\u8bf7\u5c0a\u91cd\u7f51\u7ad9\u89c4\u5219&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<h3>\u516d\u3001\u5b8c\u6574\u9879\u76ee&#xff1a;\u4e66\u7c4d\u4fe1\u606f\u722c\u866b<\/h3>\n<p><span class=\"token keyword\">import<\/span> requests<br \/>\n<span class=\"token keyword\">from<\/span> bs4 <span class=\"token keyword\">import<\/span> BeautifulSoup<br \/>\n<span class=\"token keyword\">import<\/span> csv<br \/>\n<span class=\"token keyword\">import<\/span> time<\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">BookSpider<\/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>base_url <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;http:\/\/books.toscrape.com\/&#034;<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>books_data <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">scrape_all_books<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u722c\u53d6\u6240\u6709\u4e66\u7c4d\u4fe1\u606f&#034;&#034;&#034;<\/span><br \/>\n        page <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">1<\/span><br \/>\n        <span class=\"token keyword\">while<\/span> <span class=\"token boolean\">True<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            url <span class=\"token operator\">&#061;<\/span> <span class=\"token string-interpolation\"><span class=\"token string\">f&#034;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>self<span class=\"token punctuation\">.<\/span>base_url<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">catalogue\/page-<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>page<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">.html&#034;<\/span><\/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;\u6b63\u5728\u722c\u53d6\u7b2c <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>page<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> \u9875&#8230;&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>            html <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>get_page<span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> html<span class=\"token punctuation\">:<\/span><br \/>\n                <span class=\"token keyword\">break<\/span><\/p>\n<p>            books <span class=\"token operator\">&#061;<\/span> self<span class=\"token punctuation\">.<\/span>parse_books<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> books<span class=\"token punctuation\">:<\/span><br \/>\n                <span class=\"token keyword\">break<\/span><\/p>\n<p>            self<span class=\"token punctuation\">.<\/span>books_data<span class=\"token punctuation\">.<\/span>extend<span class=\"token punctuation\">(<\/span>books<span class=\"token punctuation\">)<\/span><br \/>\n            page <span class=\"token operator\">&#043;&#061;<\/span> <span class=\"token number\">1<\/span><br \/>\n            time<span class=\"token punctuation\">.<\/span>sleep<span class=\"token punctuation\">(<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">)<\/span>  <span class=\"token comment\"># \u793c\u8c8c\u5ef6\u8fdf<\/span><\/p>\n<p>        <span class=\"token keyword\">return<\/span> self<span class=\"token punctuation\">.<\/span>books_data<\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">get_page<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> url<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u83b7\u53d6\u9875\u9762\u5185\u5bb9&#034;&#034;&#034;<\/span><br \/>\n        <span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            response <span class=\"token operator\">&#061;<\/span> requests<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span>url<span class=\"token punctuation\">,<\/span> timeout<span class=\"token operator\">&#061;<\/span><span class=\"token number\">10<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> response<span class=\"token punctuation\">.<\/span>status_code <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token number\">200<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                <span class=\"token keyword\">return<\/span> response<span class=\"token punctuation\">.<\/span>content<br \/>\n            <span class=\"token keyword\">return<\/span> <span class=\"token boolean\">None<\/span><br \/>\n        <span class=\"token keyword\">except<\/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\">def<\/span> <span class=\"token function\">parse_books<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> html<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u89e3\u6790\u4e66\u7c4d\u4fe1\u606f&#034;&#034;&#034;<\/span><br \/>\n        soup <span class=\"token operator\">&#061;<\/span> BeautifulSoup<span class=\"token punctuation\">(<\/span>html<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#039;html.parser&#039;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        books <span class=\"token operator\">&#061;<\/span> soup<span class=\"token punctuation\">.<\/span>find_all<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;article&#039;<\/span><span class=\"token punctuation\">,<\/span> class_<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#039;product_pod&#039;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        book_list <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n        <span class=\"token keyword\">for<\/span> book <span class=\"token keyword\">in<\/span> books<span class=\"token punctuation\">:<\/span><br \/>\n            title <span class=\"token operator\">&#061;<\/span> book<span class=\"token punctuation\">.<\/span>h3<span class=\"token punctuation\">.<\/span>a<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#039;title&#039;<\/span><span class=\"token punctuation\">]<\/span><br \/>\n            price <span class=\"token operator\">&#061;<\/span> book<span class=\"token punctuation\">.<\/span>select_one<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;p.price_color&#039;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>text<br \/>\n            rating <span class=\"token operator\">&#061;<\/span> book<span class=\"token punctuation\">.<\/span>p<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#039;class&#039;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">]<\/span>  <span class=\"token comment\"># \u8bc4\u5206\u7b49\u7ea7<\/span><\/p>\n<p>            book_list<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">{<\/span><br \/>\n                <span class=\"token string\">&#039;title&#039;<\/span><span class=\"token punctuation\">:<\/span> title<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#039;price&#039;<\/span><span class=\"token punctuation\">:<\/span> price<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#039;rating&#039;<\/span><span class=\"token punctuation\">:<\/span> rating<br \/>\n            <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">return<\/span> book_list<\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">export_data<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">format<\/span><span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#039;csv&#039;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u5bfc\u51fa\u6570\u636e&#034;&#034;&#034;<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token builtin\">format<\/span> <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token string\">&#039;csv&#039;<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">with<\/span> <span class=\"token builtin\">open<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;books.csv&#039;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#039;w&#039;<\/span><span class=\"token punctuation\">,<\/span> newline<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#039;&#039;<\/span><span class=\"token punctuation\">,<\/span> encoding<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#039;utf-8&#039;<\/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><span class=\"token punctuation\">[<\/span><span class=\"token string\">&#039;title&#039;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#039;price&#039;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#039;rating&#039;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><br \/>\n                writer<span class=\"token punctuation\">.<\/span>writeheader<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n                writer<span class=\"token punctuation\">.<\/span>writerows<span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">.<\/span>books_data<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;\u5df2\u5bfc\u51fa <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span><span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">.<\/span>books_data<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> \u672c\u4e66\u7c4d\u4fe1\u606f\u5230 books.csv&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u8fd0\u884c\u722c\u866b<\/span><br \/>\n<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    spider <span class=\"token operator\">&#061;<\/span> BookSpider<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    books <span class=\"token operator\">&#061;<\/span> spider<span class=\"token punctuation\">.<\/span>scrape_all_books<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\\\\n\u5171\u722c\u53d6\u5230 <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span><span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>books<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> \u672c\u4e66\u7c4d&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">for<\/span> i<span class=\"token punctuation\">,<\/span> book <span class=\"token keyword\">in<\/span> <span class=\"token builtin\">enumerate<\/span><span class=\"token punctuation\">(<\/span>books<span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">:<\/span><span class=\"token number\">5<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">1<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>i<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">. \u300a<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>book<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#039;title&#039;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">\u300b &#8211; \u4ef7\u683c: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>book<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#039;price&#039;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> &#8211; \u8bc4\u5206: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>book<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#039;rating&#039;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    spider<span class=\"token punctuation\">.<\/span>export_data<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<h3>\u4e03\u3001\u5e38\u89c1\u95ee\u9898\u4e0e\u89e3\u51b3\u65b9\u6848<\/h3>\n<h4>Q1: \u9047\u5230403 Forbidden\u9519\u8bef\u600e\u4e48\u529e&#xff1f;<\/h4>\n<ul>\n<li>\u6dfb\u52a0\u5408\u9002\u7684\u8bf7\u6c42\u5934&#xff08;User-Agent\u3001Referer\u7b49&#xff09;<\/li>\n<li>\u4f7f\u7528\u4ee3\u7406IP<\/li>\n<li>\u964d\u4f4e\u8bf7\u6c42\u9891\u7387<\/li>\n<\/ul>\n<h4>Q2: \u6570\u636e\u7f16\u7801\u6df7\u4e71\u600e\u4e48\u529e&#xff1f;<\/h4>\n<ul>\n<li>\u4f7f\u7528response.encoding &#061; response.apparent_encoding<\/li>\n<li>\u5c1d\u8bd5\u4e0d\u540c\u7f16\u7801&#xff1a;utf-8\u3001gbk\u3001gb2312<\/li>\n<li>\u4f7f\u7528chardet\u5e93\u81ea\u52a8\u68c0\u6d4b\u7f16\u7801<\/li>\n<\/ul>\n<h4>Q3: \u5982\u4f55\u63d0\u9ad8\u722c\u866b\u6548\u7387&#xff1f;<\/h4>\n<ul>\n<li>\u4f7f\u7528concurrent.futures\u5b9e\u73b0\u591a\u7ebf\u7a0b<\/li>\n<li>\u4f7f\u7528aiohttp\u5b9e\u73b0\u5f02\u6b65\u722c\u866b<\/li>\n<li>\u5408\u7406\u8bbe\u7f6e\u5ef6\u8fdf&#xff0c;\u907f\u514d\u88ab\u5c01<\/li>\n<\/ul>\n<h3>\u516b\u3001\u5b66\u4e60\u8d44\u6e90\u63a8\u8350<\/h3>\n<h4>8.1 \u8fdb\u4e00\u6b65\u5b66\u4e60<\/h4>\n<li>\n<p>\u5b98\u65b9\u6587\u6863&#xff1a;<\/p>\n<ul>\n<li>requests&#xff1a;https:\/\/docs.python-requests.org\/<\/li>\n<li>BeautifulSoup&#xff1a;https:\/\/www.crummy.com\/software\/BeautifulSoup\/bs4\/doc\/<\/li>\n<\/ul>\n<\/li>\n<li>\n<p>\u8fdb\u9636\u5e93&#xff1a;<\/p>\n<ul>\n<li>Scrapy&#xff1a;\u4e13\u4e1a\u722c\u866b\u6846\u67b6<\/li>\n<li>Playwright&#xff1a;\u73b0\u4ee3\u5316\u6d4f\u89c8\u5668\u81ea\u52a8\u5316<\/li>\n<li>PyQuery&#xff1a;jQuery\u98ce\u683c\u7684\u89e3\u6790\u5e93<\/li>\n<\/ul>\n<\/li>\n<h4>8.2 \u7ec3\u4e60\u7f51\u7ad9<\/h4>\n<li>\u7ec3\u4e60\u53cb\u597d\u7f51\u7ad9&#xff1a;\n<ul>\n<li>http:\/\/books.toscrape.com\/<\/li>\n<li>http:\/\/quotes.toscrape.com\/<\/li>\n<li>https:\/\/httpbin.org\/<\/li>\n<\/ul>\n<\/li>\n<h3>\u603b\u7ed3<\/h3>\n<p>\u672c\u6587\u4ece\u96f6\u5f00\u59cb\u4ecb\u7ecd\u4e86Python\u722c\u866b\u7684\u5b8c\u6574\u6d41\u7a0b&#xff0c;\u6db5\u76d6\u4e86\u57fa\u7840\u8bf7\u6c42\u3001\u6570\u636e\u89e3\u6790\u3001\u53cd\u722c\u5e94\u5bf9\u3001\u6570\u636e\u5b58\u50a8\u7b49\u5173\u952e\u73af\u8282\u3002\u722c\u866b\u6280\u672f\u7684\u5b66\u4e60\u9700\u8981\u7406\u8bba\u4e0e\u5b9e\u8df5\u7ed3\u5408&#xff0c;\u5efa\u8bae\u521d\u5b66\u8005&#xff1a;<\/p>\n<li>\u4ece\u5c0f\u9879\u76ee\u5f00\u59cb&#xff0c;\u9010\u6b65\u589e\u52a0\u590d\u6742\u5ea6<\/li>\n<li>\u9075\u5b88\u722c\u866b\u4f26\u7406&#xff0c;\u5c0a\u91cd\u7f51\u7ad9\u89c4\u5219<\/li>\n<li>\u6301\u7eed\u5b66\u4e60&#xff0c;\u5173\u6ce8\u6280\u672f\u53d1\u5c55<\/li>\n<li>\u591a\u505a\u7ec3\u4e60&#xff0c;\u79ef\u7d2f\u5b9e\u6218\u7ecf\u9a8c<\/li>\n<p>\u8bb0\u4f4f&#xff0c;\u722c\u866b\u4e0d\u4ec5\u4ec5\u662f\u6280\u672f\u6d3b&#xff0c;\u66f4\u662f\u5bf9\u8010\u5fc3\u548c\u7ec6\u81f4\u7a0b\u5ea6\u7684\u8003\u9a8c\u3002\u9047\u5230\u95ee\u9898\u65f6&#xff0c;\u591a\u67e5\u9605\u6587\u6863\u3001\u591a\u8c03\u8bd5\u4ee3\u7801&#xff0c;\u4f60\u4e00\u5b9a\u4f1a\u6210\u4e3a\u722c\u866b\u9ad8\u624b&#xff01;<\/p>\n<p>\u58f0\u660e&#xff1a;\u672c\u6587\u4ec5\u4f9b\u5b66\u4e60\u4ea4\u6d41\u4f7f\u7528&#xff0c;\u8bf7\u9075\u5b88\u76f8\u5173\u6cd5\u5f8b\u6cd5\u89c4\u548c\u7f51\u7ad9\u89c4\u5b9a&#xff0c;\u4e0d\u5f97\u7528\u4e8e\u975e\u6cd5\u7528\u9014\u3002<\/p>\n<hr \/>\n<p>\u5e0c\u671b\u8fd9\u7bc7\u6559\u7a0b\u80fd\u5e2e\u52a9\u4f60\u987a\u5229\u5165\u95e8Python\u722c\u866b&#xff01;\u5982\u679c\u6709\u4efb\u4f55\u95ee\u9898&#xff0c;\u6b22\u8fce\u5728\u8bc4\u8bba\u533a\u7559\u8a00\u8ba8\u8bba\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u524d\u8a00&#xff1a;\u4e3a\u4ec0\u4e48\u5b66\u4e60\u722c\u866b&#xff1f;<br \/>\n\u5728\u5f53\u4eca\u5927\u6570\u636e\u65f6\u4ee3&#xff0c;\u7f51\u7edc\u6570\u636e\u91c7\u96c6&#xff08;\u722c\u866b&#xff09;\u5df2\u6210\u4e3a\u6570\u636e\u5206\u6790\u548c\u4eba\u5de5\u667a\u80fd\u9886\u57df\u7684\u91cd\u8981\u6280\u80fd\u3002\u65e0\u8bba\u662f\u5e02\u573a\u8c03\u7814\u3001\u7ade\u54c1\u5206\u6790&#xff0c;\u8fd8\u662f\u5b66\u672f\u7814\u7a76&#xff0c;\u722c\u866b\u6280\u672f\u90fd\u80fd\u5e2e\u52a9\u6211\u4eec\u9ad8\u6548\u83b7\u53d6\u6240\u9700\u4fe1\u606f\u3002\u672c\u6587\u5c06\u5e26\u9886Python\u521d\u5b66\u8005\u4e00\u6b65\u6b65\u638c\u63e1\u722c\u866b\u6838\u5fc3\u6280\u672f\u3002<br \/>\n\u4e00\u3001\u722c\u866b\u57fa\u7840\u51c6\u5907<br \/>\n1.1 \u73af\u5883\u642d\u5efa<br \/>\n# \u521b\u5efa\u865a\u62df\u73af\u5883&#xff08;\u63a8\u8350&#xff09;<br \/>\npython -m venv spider_env<br \/>\nsou<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[81,190,677],"topic":[],"class_list":["post-69211","post","type-post","status-publish","format-standard","hentry","category-server","tag-python","tag-190","tag-677"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v20.3 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Python\u722c\u866b\u5165\u95e8\u5b9e\u6218\uff1a\u4ece\u96f6\u5f00\u59cb\u6293\u53d6\u7f51\u9875\u6570\u636e - \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\/69211.html\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Python\u722c\u866b\u5165\u95e8\u5b9e\u6218\uff1a\u4ece\u96f6\u5f00\u59cb\u6293\u53d6\u7f51\u9875\u6570\u636e - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"og:description\" content=\"\u524d\u8a00&#xff1a;\u4e3a\u4ec0\u4e48\u5b66\u4e60\u722c\u866b&#xff1f; \u5728\u5f53\u4eca\u5927\u6570\u636e\u65f6\u4ee3&#xff0c;\u7f51\u7edc\u6570\u636e\u91c7\u96c6&#xff08;\u722c\u866b&#xff09;\u5df2\u6210\u4e3a\u6570\u636e\u5206\u6790\u548c\u4eba\u5de5\u667a\u80fd\u9886\u57df\u7684\u91cd\u8981\u6280\u80fd\u3002\u65e0\u8bba\u662f\u5e02\u573a\u8c03\u7814\u3001\u7ade\u54c1\u5206\u6790&#xff0c;\u8fd8\u662f\u5b66\u672f\u7814\u7a76&#xff0c;\u722c\u866b\u6280\u672f\u90fd\u80fd\u5e2e\u52a9\u6211\u4eec\u9ad8\u6548\u83b7\u53d6\u6240\u9700\u4fe1\u606f\u3002\u672c\u6587\u5c06\u5e26\u9886Python\u521d\u5b66\u8005\u4e00\u6b65\u6b65\u638c\u63e1\u722c\u866b\u6838\u5fc3\u6280\u672f\u3002 \u4e00\u3001\u722c\u866b\u57fa\u7840\u51c6\u5907 1.1 \u73af\u5883\u642d\u5efa # \u521b\u5efa\u865a\u62df\u73af\u5883&#xff08;\u63a8\u8350&#xff09; python -m venv spider_env sou\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wsisp.com\/helps\/69211.html\" \/>\n<meta property=\"og:site_name\" content=\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"article:published_time\" content=\"2026-01-31T00:05:56+00:00\" \/>\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=\"6 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/69211.html\",\"url\":\"https:\/\/www.wsisp.com\/helps\/69211.html\",\"name\":\"Python\u722c\u866b\u5165\u95e8\u5b9e\u6218\uff1a\u4ece\u96f6\u5f00\u59cb\u6293\u53d6\u7f51\u9875\u6570\u636e - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"isPartOf\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\"},\"datePublished\":\"2026-01-31T00:05:56+00:00\",\"dateModified\":\"2026-01-31T00:05:56+00:00\",\"author\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/69211.html#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.wsisp.com\/helps\/69211.html\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/69211.html#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.wsisp.com\/helps\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Python\u722c\u866b\u5165\u95e8\u5b9e\u6218\uff1a\u4ece\u96f6\u5f00\u59cb\u6293\u53d6\u7f51\u9875\u6570\u636e\"}]},{\"@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":"Python\u722c\u866b\u5165\u95e8\u5b9e\u6218\uff1a\u4ece\u96f6\u5f00\u59cb\u6293\u53d6\u7f51\u9875\u6570\u636e - \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\/69211.html","og_locale":"zh_CN","og_type":"article","og_title":"Python\u722c\u866b\u5165\u95e8\u5b9e\u6218\uff1a\u4ece\u96f6\u5f00\u59cb\u6293\u53d6\u7f51\u9875\u6570\u636e - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","og_description":"\u524d\u8a00&#xff1a;\u4e3a\u4ec0\u4e48\u5b66\u4e60\u722c\u866b&#xff1f; \u5728\u5f53\u4eca\u5927\u6570\u636e\u65f6\u4ee3&#xff0c;\u7f51\u7edc\u6570\u636e\u91c7\u96c6&#xff08;\u722c\u866b&#xff09;\u5df2\u6210\u4e3a\u6570\u636e\u5206\u6790\u548c\u4eba\u5de5\u667a\u80fd\u9886\u57df\u7684\u91cd\u8981\u6280\u80fd\u3002\u65e0\u8bba\u662f\u5e02\u573a\u8c03\u7814\u3001\u7ade\u54c1\u5206\u6790&#xff0c;\u8fd8\u662f\u5b66\u672f\u7814\u7a76&#xff0c;\u722c\u866b\u6280\u672f\u90fd\u80fd\u5e2e\u52a9\u6211\u4eec\u9ad8\u6548\u83b7\u53d6\u6240\u9700\u4fe1\u606f\u3002\u672c\u6587\u5c06\u5e26\u9886Python\u521d\u5b66\u8005\u4e00\u6b65\u6b65\u638c\u63e1\u722c\u866b\u6838\u5fc3\u6280\u672f\u3002 \u4e00\u3001\u722c\u866b\u57fa\u7840\u51c6\u5907 1.1 \u73af\u5883\u642d\u5efa # \u521b\u5efa\u865a\u62df\u73af\u5883&#xff08;\u63a8\u8350&#xff09; python -m venv spider_env sou","og_url":"https:\/\/www.wsisp.com\/helps\/69211.html","og_site_name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","article_published_time":"2026-01-31T00:05:56+00:00","author":"admin","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"admin","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"6 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wsisp.com\/helps\/69211.html","url":"https:\/\/www.wsisp.com\/helps\/69211.html","name":"Python\u722c\u866b\u5165\u95e8\u5b9e\u6218\uff1a\u4ece\u96f6\u5f00\u59cb\u6293\u53d6\u7f51\u9875\u6570\u636e - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","isPartOf":{"@id":"https:\/\/www.wsisp.com\/helps\/#website"},"datePublished":"2026-01-31T00:05:56+00:00","dateModified":"2026-01-31T00:05:56+00:00","author":{"@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41"},"breadcrumb":{"@id":"https:\/\/www.wsisp.com\/helps\/69211.html#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wsisp.com\/helps\/69211.html"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wsisp.com\/helps\/69211.html#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.wsisp.com\/helps"},{"@type":"ListItem","position":2,"name":"Python\u722c\u866b\u5165\u95e8\u5b9e\u6218\uff1a\u4ece\u96f6\u5f00\u59cb\u6293\u53d6\u7f51\u9875\u6570\u636e"}]},{"@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\/69211","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=69211"}],"version-history":[{"count":0,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/69211\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media?parent=69211"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/categories?post=69211"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/tags?post=69211"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/topic?post=69211"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}