{"id":49780,"date":"2024-12-03T12:19:53","date_gmt":"2024-12-03T04:19:53","guid":{"rendered":"https:\/\/fwq.ai\/blog\/49780\/"},"modified":"2024-12-03T12:19:53","modified_gmt":"2024-12-03T04:19:53","slug":"%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8-python-selenium-%e8%8e%b7%e5%8f%96%e9%a1%b5%e9%9d%a2%e4%b8%8a%e6%89%80%e6%9c%89%e5%8f%af%e7%82%b9%e5%87%bb%e7%9a%84%e5%85%83%e7%b4%a0%ef%bc%9f","status":"publish","type":"post","link":"https:\/\/fwq.ai\/blog\/49780\/","title":{"rendered":"\u5982\u4f55\u4f7f\u7528 Python Selenium \u83b7\u53d6\u9875\u9762\u4e0a\u6240\u6709\u53ef\u70b9\u51fb\u7684\u5143\u7d20\uff1f"},"content":{"rendered":"<p><b><\/b>     <\/p>\n<h1>\u5982\u4f55\u4f7f\u7528 Python Selenium \u83b7\u53d6\u9875\u9762\u4e0a\u6240\u6709\u53ef\u70b9\u51fb\u7684\u5143\u7d20\uff1f<\/h1>\n<p>\u5077\u5077\u52aa\u529b\uff0c\u6084\u65e0\u58f0\u606f\u5730\u53d8\u5f3a\uff0c\u7136\u540e\u60ca\u8273\u6240\u6709\u4eba\uff01\u54c8\u54c8\uff0c\u5c0f\u4f19\u4f34\u4eec\u53c8\u6765\u5b66\u4e60\u5566~\u4eca\u5929\u6211\u5c06\u7ed9\u5927\u5bb6\u4ecb\u7ecd\uff0c\u8fd9\u7bc7\u6587\u7ae0\u4e3b\u8981\u4f1a\u8bb2\u5230<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\"><\/span>\u7b49\u7b49\u77e5\u8bc6\u70b9\uff0c\u4e0d\u77e5\u9053\u5927\u5bb6\u5bf9\u5176\u90fd\u6709\u591a\u5c11\u4e86\u89e3\uff0c\u4e0b\u9762\u6211\u4eec\u5c31\u4e00\u8d77\u6765\u770b\u4e00\u5427\uff01\u5f53\u7136\uff0c\u975e\u5e38\u5e0c\u671b\u5927\u5bb6\u80fd\u591a\u591a\u8bc4\u8bba\uff0c\u7ed9\u51fa\u5408\u7406\u7684\u5efa\u8bae\uff0c\u6211\u4eec\u4e00\u8d77\u5b66\u4e60\uff0c\u4e00\u8d77\u8fdb\u6b65\uff01<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.17golang.com\/uploads\/20241103\/1730628051672749d32d32a.jpg\" class=\"aligncenter\" title=\"\u5982\u4f55\u4f7f\u7528 Python Selenium \u83b7\u53d6\u9875\u9762\u4e0a\u6240\u6709\u53ef\u70b9\u51fb\u7684\u5143\u7d20\uff1f\u63d2\u56fe\" alt=\"\u5982\u4f55\u4f7f\u7528 Python Selenium \u83b7\u53d6\u9875\u9762\u4e0a\u6240\u6709\u53ef\u70b9\u51fb\u7684\u5143\u7d20\uff1f\u63d2\u56fe\" \/><\/p>\n<p><strong>\u5982\u4f55\u83b7\u53d6 python selenium \u4e2d\u6240\u6709\u53ef\u70b9\u51fb\u7684\u9875\u9762\u5143\u7d20<\/strong><\/p>\n<p>\u5728\u4f7f\u7528 python \u4e2d\u7684 selenium \u5e93\u5bf9\u4f60\u611f\u5174\u8da3\u7684\u9875\u9762\u8fdb\u884c\u81ea\u52a8\u5316\u64cd\u4f5c\u65f6\uff0c\u4f60\u53ef\u80fd\u4f1a\u60f3\u8981\u68c0\u7d22\u9875\u9762\u4e0a\u6240\u6709\u53ef\u70b9\u51fb\u7684\u5143\u7d20\u3002\u8fd9\u4e9b\u5143\u7d20\u5305\u62ec\u94fe\u63a5\u3001\u6309\u94ae\u3001\u83dc\u5355\u9879\u548c\u5176\u4ed6\u7528\u6237\u53ef\u4ee5\u4e0e\u4e4b\u4ea4\u4e92\u7684\u9875\u9762\u5143\u7d20\u3002<\/p>\n<p>\u867d\u7136 selenium \u63d0\u4f9b\u4e86\u83b7\u53d6\u67d0\u4e9b\u53ef\u70b9\u51fb\u5143\u7d20\u7684\u65b9\u6cd5\uff0c\u4f8b\u5982\u94fe\u63a5\u548c\u6309\u94ae\uff0c\u4f46\u5b83\u5e76\u4e0d\u80fd\u76f4\u63a5\u68c0\u7d22\u6240\u6709\u53ef\u70b9\u51fb\u7684\u5143\u7d20\u3002\u8fd9\u662f\u56e0\u4e3a\u201c\u53ef\u70b9\u51fb\u6027\u201d\u5e76\u4e0d\u662f\u4e00\u4e2a\u660e\u786e\u5b9a\u4e49\u7684\u6982\u5ff5\uff0c\u800c\u4e14\u6709\u4e9b\u5143\u7d20\u53ef\u80fd\u53ef\u4ee5\u901a\u8fc7\u4e0d\u540c\u7684\u65b9\u6cd5\u8fdb\u884c\u70b9\u51fb\uff0c\u4f8b\u5982\u4f7f\u7528\u9f20\u6807\u6216\u901a\u8fc7\u952e\u76d8\u5feb\u6377\u952e\u3002<\/p>\n<p>\u89e3\u51b3\u65b9\u6cd5\u662f\u8bbf\u95ee\u9875\u9762\u7684 dom \u7ed3\u6784\u5e76\u904d\u5386\u5176\u5143\u7d20\u3002\u8fd9\u6837\uff0c\u4f60\u53ef\u4ee5\u68c0\u67e5\u6bcf\u4e2a\u5143\u7d20\u7684\u5c5e\u6027\u548c\u4e8b\u4ef6\u76d1\u542c\u5668\uff0c\u4ee5\u786e\u5b9a\u5b83\u4eec\u662f\u5426\u53ef\u4ee5\u70b9\u51fb\u3002\u4ee5\u4e0b\u6b65\u9aa4\u6982\u8ff0\u4e86\u5982\u4f55\u6267\u884c\u6b64\u64cd\u4f5c\uff1a<\/p>\n<ol>\n<li>\u5bfc\u5165 selenium \u548c beautifulsoup \u5e93\uff1a<\/li>\n<\/ol>\n<pre>from selenium import webdriver\nfrom bs4 import beautifulsoup<\/pre>\n<ol>\n<li>\u521b\u5efa\u4e00\u4e2a webdriver \u5b9e\u4f8b\u6765\u52a0\u8f7d\u611f\u5174\u8da3\u7684\u9875\u9762\uff1a<\/li>\n<\/ol>\n<pre>driver = webdriver.chrome()\ndriver.get(\"https:\/\/example.com\")<\/pre>\n<ol>\n<li>\u83b7\u53d6\u9875\u9762\u7684 html \u5185\u5bb9\uff1a<\/li>\n<\/ol>\n<pre>html = driver.page_source<\/pre>\n<ol>\n<li>\u4f7f\u7528 beautifulsoup \u89e3\u6790 html \u5185\u5bb9\uff1a<\/li>\n<\/ol>\n<pre>soup = beautifulsoup(html, \"html.parser\")<\/pre>\n<ol>\n<li>\u904d\u5386\u6587\u6863\u6811\u5e76\u68c0\u67e5\u6bcf\u4e2a\u5143\u7d20\u662f\u5426\u53ef\u4ee5\u70b9\u51fb\uff1a<\/li>\n<\/ol>\n<pre>for element in soup.find_all():\n    if element.has_attr(\"href\") or element.has_attr(\"onclick\"):\n        # \u5143\u7d20\u5177\u6709 `href` \u5c5e\u6027\u6216 `onclick` \u4e8b\u4ef6\uff0c\u56e0\u6b64\u662f\u53ef\u70b9\u51fb\u7684\n        print(element)<\/pre>\n<p>\u4ee5\u4e0a\u5c31\u662f\u672c\u6587\u7684\u5168\u90e8\u5185\u5bb9\u4e86\uff0c\u662f\u5426\u6709\u987a\u5229\u5e2e\u52a9\u4f60\u89e3\u51b3\u95ee\u9898\uff1f\u82e5\u662f\u80fd\u7ed9\u4f60\u5e26\u6765\u5b66\u4e60\u4e0a\u7684\u5e2e\u52a9\uff0c\u8bf7\u5927\u5bb6\u591a\u591a\u652f\u6301\u7c73\u4e91\uff01\u66f4\u591a\u5173\u4e8e\u6587\u7ae0\u7684\u76f8\u5173\u77e5\u8bc6\uff0c\u4e5f\u53ef\u5173\u6ce8\u7c73\u4e91\u516c\u4f17\u53f7\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u5982\u4f55\u4f7f\u7528 Python Selenium \u83b7\u53d6\u9875\u9762\u4e0a\u6240\u6709\u53ef\u70b9\u51fb\u7684\u5143\u7d20\uff1f \u5077\u5077\u52aa\u529b\uff0c\u6084\u65e0\u58f0\u606f\u5730\u53d8\u5f3a\uff0c\u7136\u540e\u60ca\u8273\u6240\u6709\u4eba\uff01\u54c8\u54c8\uff0c\u5c0f\u4f19\u4f34\u4eec\u53c8\u6765\u5b66\u4e60\u5566~\u4eca\u5929\u6211\u5c06\u7ed9\u5927\u5bb6\u4ecb\u7ecd\uff0c\u8fd9\u7bc7\u6587\u7ae0\u4e3b\u8981\u4f1a\u8bb2\u5230\u7b49\u7b49\u77e5\u8bc6\u70b9\uff0c\u4e0d\u77e5\u9053\u5927\u5bb6\u5bf9\u5176\u90fd\u6709\u591a\u5c11\u4e86\u89e3\uff0c\u4e0b\u9762\u6211\u4eec\u5c31\u4e00\u8d77\u6765\u770b\u4e00\u5427\uff01\u5f53\u7136\uff0c\u975e\u5e38\u5e0c\u671b\u5927\u5bb6\u80fd\u591a\u591a\u8bc4\u8bba\uff0c\u7ed9\u51fa\u5408\u7406\u7684\u5efa\u8bae\uff0c\u6211\u4eec\u4e00\u8d77\u5b66\u4e60\uff0c\u4e00\u8d77\u8fdb\u6b65\uff01 \u5982\u4f55\u83b7\u53d6 python selenium \u4e2d\u6240\u6709\u53ef\u70b9\u51fb\u7684\u9875\u9762\u5143\u7d20 \u5728\u4f7f\u7528 python \u4e2d\u7684 selenium \u5e93\u5bf9\u4f60\u611f\u5174\u8da3\u7684\u9875\u9762\u8fdb\u884c\u81ea\u52a8\u5316\u64cd\u4f5c\u65f6\uff0c\u4f60\u53ef\u80fd\u4f1a\u60f3\u8981\u68c0\u7d22\u9875\u9762\u4e0a\u6240\u6709\u53ef\u70b9\u51fb\u7684\u5143\u7d20\u3002\u8fd9\u4e9b\u5143\u7d20\u5305\u62ec\u94fe\u63a5\u3001\u6309\u94ae\u3001\u83dc\u5355\u9879\u548c\u5176\u4ed6\u7528\u6237\u53ef\u4ee5\u4e0e\u4e4b\u4ea4\u4e92\u7684\u9875\u9762\u5143\u7d20\u3002 \u867d\u7136 selenium \u63d0\u4f9b\u4e86\u83b7\u53d6\u67d0\u4e9b\u53ef\u70b9\u51fb\u5143\u7d20\u7684\u65b9\u6cd5\uff0c\u4f8b\u5982\u94fe\u63a5\u548c\u6309\u94ae\uff0c\u4f46\u5b83\u5e76\u4e0d\u80fd\u76f4\u63a5\u68c0\u7d22\u6240\u6709\u53ef\u70b9\u51fb\u7684\u5143\u7d20\u3002\u8fd9\u662f\u56e0\u4e3a\u201c\u53ef\u70b9\u51fb\u6027\u201d\u5e76\u4e0d\u662f\u4e00\u4e2a\u660e\u786e\u5b9a\u4e49\u7684\u6982\u5ff5\uff0c\u800c\u4e14\u6709\u4e9b\u5143\u7d20\u53ef\u80fd\u53ef\u4ee5\u901a\u8fc7\u4e0d\u540c\u7684\u65b9\u6cd5\u8fdb\u884c\u70b9\u51fb\uff0c\u4f8b\u5982\u4f7f\u7528\u9f20\u6807\u6216\u901a\u8fc7\u952e\u76d8\u5feb\u6377\u952e\u3002 \u89e3\u51b3\u65b9\u6cd5\u662f\u8bbf\u95ee\u9875\u9762\u7684 dom \u7ed3\u6784\u5e76\u904d\u5386\u5176\u5143\u7d20\u3002\u8fd9\u6837\uff0c\u4f60\u53ef\u4ee5\u68c0\u67e5\u6bcf\u4e2a\u5143\u7d20\u7684\u5c5e\u6027\u548c\u4e8b\u4ef6\u76d1\u542c\u5668\uff0c\u4ee5\u786e\u5b9a\u5b83\u4eec\u662f\u5426\u53ef\u4ee5\u70b9\u51fb\u3002\u4ee5\u4e0b\u6b65\u9aa4\u6982\u8ff0\u4e86\u5982\u4f55\u6267\u884c\u6b64\u64cd\u4f5c\uff1a \u5bfc\u5165 selenium \u548c beautifulsoup \u5e93\uff1a from selenium import webdriver from bs4 import beautifulsoup \u521b\u5efa\u4e00\u4e2a webdriver \u5b9e\u4f8b\u6765\u52a0\u8f7d\u611f\u5174\u8da3\u7684\u9875\u9762\uff1a driver = webdriver.chrome() driver.get(&#8220;https:\/\/example.com&#8221;) \u83b7\u53d6\u9875\u9762\u7684 html \u5185\u5bb9\uff1a html = driver.page_source \u4f7f\u7528 beautifulsoup \u89e3\u6790 html \u5185\u5bb9\uff1a soup = beautifulsoup(html, &#8220;html.parser&#8221;) [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[16],"tags":[],"class_list":["post-49780","post","type-post","status-publish","format-standard","hentry","category-16"],"_links":{"self":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts\/49780","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/comments?post=49780"}],"version-history":[{"count":0,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts\/49780\/revisions"}],"wp:attachment":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/media?parent=49780"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/categories?post=49780"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/tags?post=49780"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}