{"id":1233,"date":"2022-07-14T17:08:00","date_gmt":"2022-07-14T09:08:00","guid":{"rendered":"https:\/\/fireinsect.top\/?p=1233"},"modified":"2022-07-14T17:08:46","modified_gmt":"2022-07-14T09:08:46","slug":"python%e7%88%ac%e8%99%ab%e7%ae%80%e8%bf%b0","status":"publish","type":"post","link":"https:\/\/fireinsect.top\/index.php\/2022\/07\/14\/python%e7%88%ac%e8%99%ab%e7%ae%80%e8%bf%b0\/","title":{"rendered":"Python\u722c\u866b\u7b80\u8ff0"},"content":{"rendered":"\n<p>Python\u722c\u866b\u6280\u672f\u662f\u73b0\u5728\u4e3b\u6d41\u7684\u722c\u866b\u6280\u672f\uff0c\u6b64\u7bc7\u5c06\u4ece\u57fa\u7840\u65b9\u9762\u7b80\u8ff0\u57fa\u4e8ePython\u722c\u866b\u7684\u4e00\u7cfb\u5217\u65b9\u6cd5\u3002<\/p>\n\n\n\n<!--more-->\n\n\n\n<p>\u8fd9\u7bc7\u6587\u7ae0\u4f7f\u7528\u7684\u662fPython\u7684requests-html\u5e93\u6765\u8fdb\u884c\u6570\u636e\u722c\u53d6\u3002<\/p>\n\n\n\n<p>\u9996\u5148\u6211\u4eec\u9700\u8981\u5728python\u4e2d\u5b89\u88c5requests-html\u5e93\uff0c\u4f7f\u7528\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code lang=\"bash\" class=\"language-bash\">pip3 install requests-html<\/code><\/pre>\n\n\n\n<p>requests-html\u7684\u57fa\u672c\u4f7f\u7528\u65b9\u6cd5\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code lang=\"python\" class=\"language-python\">from requests_html import HTMLSession\r\n# \u83b7\u53d6\u8bf7\u6c42\u5bf9\u8c61\r\nsession = HTMLSession()\r\n# \u5f80\u65b0\u6d6a\u65b0\u95fb\u4e3b\u9875\u53d1\u9001get\u8bf7\u6c42\r\nsina = session.get('https:\/\/news.sina.com.cn\/')\r\n# print(sina.status_code)\r\nsina.encoding = 'utf-8'\r\n# \u83b7\u53d6\u54cd\u5e94\u6587\u672c\u4fe1\u606f\uff0c\u4e0erequests\u65e0\u533a\u522b\r\n print(sina.text)<\/code><\/pre>\n\n\n\n<p>\u6211\u4eec\u6765\u89e3\u6790\u4e00\u4e0b\u8fd9\u6bb5\u4ee3\u7801\u3002\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5728py\u6587\u4ef6\u4e2d\u5f15\u5165\u8fd9\u4e2a\u722c\u53d6\u5e93\uff08\u5e9f\u8bdd\uff09\u3002\u4e4b\u540e\u6211\u4eec\u901a\u8fc7<code>session = HTMLSession()<\/code>\u521b\u5efa\u4e86\u4e00\u4e2aSession\u5bf9\u8c61\uff0c\u8fd9\u4e2a\u5bf9\u8c61\u7684\u529f\u80fd\u662f\u8fdb\u884c\u7f51\u9875\u8bbf\u95ee\uff08\u8fd9\u91cc\u4e0d\u591a\u8ff0\uff09\u3002<\/p>\n\n\n\n<p>\u4e4b\u540e\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u8fd9\u4e2a\u5bf9\u8c61\u6765\u8fdb\u884c\u4e00\u7cfb\u5217\u7f51\u9875\u8bbf\u95ee\u65b9\u6cd5\u3002<\/p>\n\n\n\n<p>\u8fd9\u91cc\u6211\u4eec\u4f7f\u7528\u4e86<code>sina = session.get('https:\/\/news.sina.com.cn\/')<\/code>\u8fd9\u4e2a\u51fd\u6570\u3002\u5b83\u7684\u610f\u601d\u662f\u4f7f\u7528get\u65b9\u6cd5\u8bbf\u95ee\u4e86\u65b0\u6d6a\u4e3b\u9875\uff0c\u5f53\u7136\u8fd9\u91cc\u4e5f\u5b58\u5728post\u65b9\u6cd5\uff0c\u8fd9\u4e2a\u5c31\u4e0d\u7ec6\u7ec6\u8bb2\u89e3\u4e86\uff0c\u5177\u4f53\u53c2\u8003\u6211<a rel=\"noreferrer noopener\" href=\"https:\/\/fireinsect.top\/index.php\/2021\/02\/04\/post%e8%a1%a8%e5%8d%95%e6%95%b0%e6%8d%ae\/#more-400\" target=\"_blank\">\u4ee5\u524d\u7684\u6587\u732e<\/a>\u3002\u6211\u4eec\u6682\u65f6\u53ea\u9700\u8981\u4f7f\u7528<code>get<\/code>\u5c31\u884c\u3002<\/p>\n\n\n\n<p>\u4e4b\u540e\uff0c\u6211\u4eec\u6210\u529f\u8bbf\u95ee\u4e86\u8fd9\u4e2a\u7f51\u9875\uff0c\u5e76\u901a\u8fc7sina.text\u6253\u5370\u4e86\u6574\u4e2a\u7f51\u9875\u7684\u4fe1\u606f\u3002\u6211\u4eec\u5f97\u5230\u7684\u7ed3\u679c\u5927\u6982\u662f\u8fd9\u6837\u7684\uff1a<\/p>\n\n\n\n<p>\u8fd9\u91cc\uff0c\u6211\u4eec\u76f4\u63a5\u8bbf\u95ee\u5e76\u6253\u5370\u4e86\u5173\u4e8e\u65b0\u6d6a\u9996\u9875\u7684HTML\u4fe1\u606f\uff08\u6ce8\uff1aHTML\u5373\u6784\u6210\u7f51\u9875\u7684\u4ee3\u7801\uff0c\u5373\u6574\u4e2a\u7f51\u9875\u7684\u6e90\u6570\u636e\uff09\uff0c\u8fd9\u5c31\u65b9\u4fbf\u6211\u4eec\u8fdb\u884c\u6570\u636e\u5206\u6790\u3002<\/p>\n\n\n\n<p>\u5176\u6b21\uff0c\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7<code>xx.html.links<\/code>\u6765\u83b7\u53d6\u7f51\u9875\u4e2d\u6240\u6709\u7684\u94fe\u63a5\u5e76\u6253\u5370\uff1a<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"501\" src=\"https:\/\/i1.wp.com\/fireinsect.top\/wp-content\/uploads\/2022\/07\/image.png?resize=1024%2C501&#038;ssl=1\" alt=\"\" class=\"wp-image-1234\" srcset=\"https:\/\/i1.wp.com\/fireinsect.top\/wp-content\/uploads\/2022\/07\/image.png?resize=1024%2C501&amp;ssl=1 1024w, https:\/\/i1.wp.com\/fireinsect.top\/wp-content\/uploads\/2022\/07\/image.png?resize=300%2C147&amp;ssl=1 300w, https:\/\/i1.wp.com\/fireinsect.top\/wp-content\/uploads\/2022\/07\/image.png?resize=768%2C376&amp;ssl=1 768w, https:\/\/i1.wp.com\/fireinsect.top\/wp-content\/uploads\/2022\/07\/image.png?resize=1536%2C751&amp;ssl=1 1536w, https:\/\/i1.wp.com\/fireinsect.top\/wp-content\/uploads\/2022\/07\/image.png?w=1746&amp;ssl=1 1746w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" data-recalc-dims=\"1\" \/><\/figure>\n\n\n\n<pre class=\"wp-block-code\"><code lang=\"python\" class=\"language-python\">sina = session.get('https:\/\/jd.com\/')\r\n# \u5f97\u5230\u4eac\u4e1c\u4e3b\u9875\u6240\u6709\u7684\u94fe\u63a5\uff0c\u8fd4\u56de\u7684\u662f\u4e00\u4e2aset\u96c6\u5408\r\nprint(sina.html.links)<\/code><\/pre>\n\n\n\n<div style=\"height:23px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p>\u4f46\u5149\u662f\u83b7\u53d6\u5230\u6574\u4e2a\u7f51\u9875\u4fe1\u606f\u8fd8\u4e0d\u591f\uff0c\u6211\u4eec\u8fd8\u9700\u8981\u5bf9\u7f51\u9875\u4fe1\u606f\u8fdb\u884c\u7b5b\u9009\u624d\u80fd\u83b7\u53d6\u6211\u4eec\u9700\u8981\u7684\u4fe1\u606f\u3002<\/p>\n\n\n\n<p>\u8fd9\u91cc\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u4e86\u89e3\u4e00\u4e2a\u6982\u5ff5\uff1a\u9009\u62e9\u5668<\/p>\n\n\n\n<p>\u6211\u4eec\u89c2\u5bdf\u4e4b\u524d\u6240\u6253\u5370\u7684\u7f51\u9875\u4fe1\u606f\uff0c\u53ef\u4ee5\u53d1\u73b0\u5b58\u5728\u5f88\u591a\u5982 <code>&lt;div><\/code>\u7684\u5b57\u6837\uff0c\u8fd9\u662f\u4e00\u4e2aHTML\u6807\u7b7e\uff0c\u6bcf\u4e2a\u6807\u7b7e\u4ee3\u8868\u7740\u4e00\u4e2aHTML\u5143\u7d20\uff0c\u6362\u4e2a\u597d\u7406\u89e3\u7684\u8bf4\u6cd5\uff0c\u5b83\u5c31\u50cf\u662fPS\u4e2d\u6240\u4f7f\u7528\u7684\u56fe\u5c42\uff0c\u4e00\u4e2a\u7cbe\u81f4\u7684\u56fe\u7247\u662f\u7531\u65e0\u6570\u4e2a\u5f62\u72b6\u3001\u5927\u5c0f\u4e0d\u540c\u7684\u56fe\u5c42\u7ec4\u6210\u7684\u3002\u800c\u7f51\u9875\u4e5f\u662f\u5982\u6b64\u3002\u50cf&lt;div>\u8fd9\u6837\u4f5c\u4e3a\u56fe\u5c42\u5b58\u5728\u7684\u6807\u7b7e\u8fd8\u6709\u5f88\u591a\u5305\u62ec&lt;li>\u3001&lt;span>\u7b49\u7b49\uff0c\u4ed6\u4eec\u4e00\u822c\u901a\u8fc7\u5982 <code>&lt;div>\u5185\u5bb9&lt;\/div><\/code> \u7684\u5f62\u5f0f\u6765\u8868\u793a\u8fd9\u91cc\u6211\u4eec\u4e0d\u591a\u505a\u8ba8\u8bba\u3002<\/p>\n\n\n\n<p>\u6211\u4eec\u9700\u8981\u5bf9\u6574\u4e2a\u9875\u9762\u6570\u636e\u8fdb\u884c\u7b5b\u9009\uff0c\u5c31\u662f\u8981\u9009\u62e9\u5230\u5408\u9002\u7684HTML\u6807\u7b7e\u5e76\u8f93\u51fa\u5176\u4e2d\u7684\u5185\u5bb9\u3002\u8fd9\u91cc\u6211\u4eec\u5c31\u8981\u7528\u5230\u9009\u62e9\u5668\u3002<\/p>\n\n\n\n<p>\u9009\u62e9\u5668\u5c31\u662f\u7528\u6765\u9009\u62e9\u5408\u9002HTML\u6807\u7b7e\u7684\u5de5\u5177\uff0c\u8fd9\u91cc\u6211\u4eec\u4e0d\u591a\u8ff0\uff0c\u5177\u4f53\u53c2\u8003<a rel=\"noreferrer noopener\" href=\"https:\/\/fireinsect.top\/index.php\/2021\/02\/02\/%e5%b8%b8%e7%94%a8%e9%80%89%e6%8b%a9%e5%99%a8\/#more-366\" data-type=\"URL\" data-id=\"https:\/\/fireinsect.top\/index.php\/2021\/02\/02\/%e5%b8%b8%e7%94%a8%e9%80%89%e6%8b%a9%e5%99%a8\/#more-366\" target=\"_blank\">\u4ee5\u524d\u7684\u6587\u6863<\/a>\uff0c\u6211\u4eec\u76f4\u63a5\u4f7f\u7528Python\u6570\u636e\u722c\u53d6\uff0c\u9700\u8981\u660e\u767d\uff0c\u4e00\u822c\u76f8\u540c\u7684\u6570\u636e\u90fd\u6709\u7740\u7c7b\u4f3c\u7684\u9009\u62e9\u5668\uff0c\u6211\u4eec\u901a\u8fc7\u5728\u9700\u8981\u722c\u53d6\u7684\u9875\u9762\u6309f12\uff0c<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"498\" src=\"https:\/\/i0.wp.com\/fireinsect.top\/wp-content\/uploads\/2022\/07\/image-1.png?resize=1024%2C498&#038;ssl=1\" alt=\"\" class=\"wp-image-1235\" srcset=\"https:\/\/i0.wp.com\/fireinsect.top\/wp-content\/uploads\/2022\/07\/image-1.png?resize=1024%2C498&amp;ssl=1 1024w, https:\/\/i0.wp.com\/fireinsect.top\/wp-content\/uploads\/2022\/07\/image-1.png?resize=300%2C146&amp;ssl=1 300w, https:\/\/i0.wp.com\/fireinsect.top\/wp-content\/uploads\/2022\/07\/image-1.png?resize=768%2C373&amp;ssl=1 768w, https:\/\/i0.wp.com\/fireinsect.top\/wp-content\/uploads\/2022\/07\/image-1.png?resize=1536%2C746&amp;ssl=1 1536w, https:\/\/i0.wp.com\/fireinsect.top\/wp-content\/uploads\/2022\/07\/image-1.png?w=1893&amp;ssl=1 1893w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" data-recalc-dims=\"1\" \/><\/figure>\n\n\n\n<p>\u901a\u8fc7\u4e00\u6b65\u6b65\u70b9\u51fb\u5c0f\u4e09\u89d2\uff0c\u627e\u5230\u9700\u8981\u722c\u53d6\u7684\u5185\u5bb9\u518d\u590d\u5236\u9009\u62e9\u5668\uff1a<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"658\" height=\"513\" src=\"https:\/\/i1.wp.com\/fireinsect.top\/wp-content\/uploads\/2022\/07\/image-2.png?resize=658%2C513&#038;ssl=1\" alt=\"\" class=\"wp-image-1236\" srcset=\"https:\/\/i1.wp.com\/fireinsect.top\/wp-content\/uploads\/2022\/07\/image-2.png?w=658&amp;ssl=1 658w, https:\/\/i1.wp.com\/fireinsect.top\/wp-content\/uploads\/2022\/07\/image-2.png?resize=300%2C234&amp;ssl=1 300w\" sizes=\"(max-width: 658px) 100vw, 658px\" data-recalc-dims=\"1\" \/><\/figure>\n\n\n\n<p>\u5373\u53ef\u627e\u5230\u5176\u9009\u62e9\u5668\u65b9\u6cd5<\/p>\n\n\n\n<p>\u4e4b\u540e\u56de\u5230Python\u4e0a\u6765\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code lang=\"python\" class=\"language-python\">obj = session.get(url)\r\n# 1.\u901a\u8fc7css\u9009\u62e9\u5668\u9009\u53d6\u4e00\u4e2aElement\u5bf9\u8c61\r\n \u83b7\u53d6id\u4e3acontent-left\u7684div\u6807\u7b7e\uff0c\u5e76\u4e14\u8fd4\u56de\u4e00\u4e2a\u5bf9\u8c61\r\ncontent = obj.html.find('div#content-left', first=True)\nprint(content.text)<\/code><\/pre>\n\n\n\n<p>\u8fd9\u4e2a\u65b9\u6cd5\u6211\u4eec\u4e5f\u53ef\u4ee5\u7406\u89e3\uff0c\u9996\u5148\u83b7\u53d6\u4e86\u7f51\u9875\u5185\u5bb9\u65b0\u5efa\u4e86obj\u5bf9\u8c61\uff0c\u4e4b\u540e\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7<code>obj.html.find(\u9009\u62e9\u5668)<\/code>\u5373\u53ef\u627e\u5230\u76f8\u5e94\u7684\u9009\u62e9\u5668\uff0c\u4e0d\u8fc7\u8fd9\u91cc\uff0c\u6211\u4eec\u4e00\u822c\u627e\u5230\u7684\u53ef\u80fd\u4e0d\u6b62\u4e00\u4e2aHTML\u5bf9\u8c61\uff0c\u8fd4\u56de\u7684\u662f\u4e00\u4e2a\u6570\u7ec4\uff0c\u4f7f\u7528\uff1a<code>content = obj.html.find('div#content-left', first=True)[0]<\/code>\u6765\u9009\u62e9\u6570\u7ec4\u5185\u5bf9\u8c61\u3002<\/p>\n\n\n\n<p>\u4ee5\u4e0a\u5927\u6982\u4e3a\u57fa\u7840\u7684Python\u722c\u53d6\u4f7f\u7528\u65b9\u6cd5\u3002\u66f4\u52a0\u8fdb\u9636\u7684\u7528\u6cd5\u8bf7\u81ea\u884c\u767e\u5ea6\u53c2\u8003\u3002<\/p>\n\n\n\n<p>\u987a\u4fbf\u63d2\u4e00\u53e5\uff0c\u7531\u4e8e\u6570\u636e\u722c\u53d6\u4e0e\u5206\u6790\u7684\u9700\u8981\uff0c\u5176\u722c\u53d6\u7ed3\u679c\u5f80\u5f80\u9700\u8981\u5b58\u5165\u6570\u636e\u5e93\u4e2d\uff0c\u6570\u636e\u5e93\u7684\u4f7f\u7528\u4e0ePython\u7684\u6570\u636e\u5e93\u5e94\u7528\u8bf7\u53c2\u8003&#8212;<a href=\"https:\/\/fireinsect.top\/?s=%E6%95%B0%E6%8D%AE%E5%BA%93%E5%9F%BA%E7%A1%80\" target=\"_blank\" rel=\"noreferrer noopener\">MySQL\u6570\u636e\u5e93\u57fa\u7840<\/a>  <a rel=\"noreferrer noopener\" href=\"https:\/\/fireinsect.top\/index.php\/2022\/04\/04\/python-mysql%e6%95%b0%e6%8d%ae%e5%ba%93%e5%9f%ba%e7%a1%80%ef%bc%88%e4%b8%80%ef%bc%89\/#more-1118\" target=\"_blank\">Python\u6570\u636e\u5e93\u5e94\u7528<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Python\u722c\u866b\u6280\u672f\u662f\u73b0\u5728\u4e3b\u6d41\u7684\u722c\u866b\u6280\u672f\uff0c\u6b64\u7bc7\u5c06\u4ece\u57fa\u7840\u65b9\u9762\u7b80\u8ff0\u57fa\u4e8ePython\u722c\u866b\u7684\u4e00\u7cfb\u5217\u65b9\u6cd5\u3002<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"spay_email":"","footnotes":""},"categories":[6,1],"tags":[],"class_list":["post-1233","post","type-post","status-publish","format-standard","hentry","category-6","category-wcd"],"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/fireinsect.top\/index.php\/wp-json\/wp\/v2\/posts\/1233"}],"collection":[{"href":"https:\/\/fireinsect.top\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/fireinsect.top\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/fireinsect.top\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/fireinsect.top\/index.php\/wp-json\/wp\/v2\/comments?post=1233"}],"version-history":[{"count":2,"href":"https:\/\/fireinsect.top\/index.php\/wp-json\/wp\/v2\/posts\/1233\/revisions"}],"predecessor-version":[{"id":1238,"href":"https:\/\/fireinsect.top\/index.php\/wp-json\/wp\/v2\/posts\/1233\/revisions\/1238"}],"wp:attachment":[{"href":"https:\/\/fireinsect.top\/index.php\/wp-json\/wp\/v2\/media?parent=1233"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/fireinsect.top\/index.php\/wp-json\/wp\/v2\/categories?post=1233"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/fireinsect.top\/index.php\/wp-json\/wp\/v2\/tags?post=1233"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}