{"id":2062,"date":"2024-10-30T17:13:21","date_gmt":"2024-10-30T09:13:21","guid":{"rendered":"http:\/\/blog.xtaa.cn\/?p=2062"},"modified":"2024-10-30T17:13:21","modified_gmt":"2024-10-30T09:13:21","slug":"selenium-%e9%9a%90%e8%97%8f%e6%b5%8f%e8%a7%88%e5%99%a8%e6%8c%87%e7%ba%b9%e7%89%b9%e5%be%81%e7%9a%84%e5%87%a0%e7%a7%8d%e6%96%b9%e5%bc%8f","status":"publish","type":"post","link":"http:\/\/blog.xtaa.cn\/index.php\/2024\/10\/30\/selenium-%e9%9a%90%e8%97%8f%e6%b5%8f%e8%a7%88%e5%99%a8%e6%8c%87%e7%ba%b9%e7%89%b9%e5%be%81%e7%9a%84%e5%87%a0%e7%a7%8d%e6%96%b9%e5%bc%8f\/","title":{"rendered":"Selenium \u9690\u85cf\u6d4f\u89c8\u5668\u6307\u7eb9\u7279\u5f81\u7684\u51e0\u79cd\u65b9\u5f0f"},"content":{"rendered":"\n<p>\u5bf9\u4e00\u4e9b\u505a\u4e86\u53cd\u722c\u7684\u7f51\u7ad9\uff0c\u505a\u4e86\u7279\u5f81\u68c0\u6d4b\uff0c\u7528\u6765\u963b\u6b62\u4e00\u4e9b\u6076\u610f\u722c\u866b<\/p>\n\n\n\n<p><a href=\"https:\/\/bot.sannysoft.com\">https:\/\/bot.sannysoft.com<\/a>\u8fd9\u4e2a\u7f51\u7ad9\u53ef\u4ee5\u68c0\u6d4b\u6307\u7eb9\u7279\u5f81<\/p>\n\n\n\n<p>\u672c\u7bc7\u6587\u7ae0\u5c06\u4ecb\u7ecd\u51e0\u79cd\u5e38\u7528\u7684\u9690\u85cf\u6d4f\u89c8\u5668\u6307\u7eb9\u7279\u5f81\u7684\u65b9\u5f0f<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">1. \u76f4\u63a5\u722c\u53d6<\/h2>\n\n\n\n<p>\u76ee\u6807\u5bf9\u8c61\uff1a<\/p>\n\n\n\n<p>aHR0cHM6Ly9xaWthbi5jcXZpcC5jb20vUWlrYW4vU2VhcmNoL0FkdmFuY2U=<\/p>\n\n\n\n<p>\u6211\u4eec\u4f7f\u7528 Selenium \u76f4\u63a5\u722c\u53d6\u76ee\u6807\u9875\u9762<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>#&nbsp;selenium&nbsp;\u76f4\u63a5\u722c\u53d6<br><br>from&nbsp;selenium&nbsp;import&nbsp;webdriver<br>from&nbsp;selenium.webdriver.chrome.options&nbsp;import&nbsp;Options<br>from&nbsp;selenium.webdriver.chrome.service&nbsp;import&nbsp;Service<br>import&nbsp;time<br><br>chrome_options&nbsp;=&nbsp;Options()<br><br>s&nbsp;=&nbsp;Service(r\"chromedriver.exe\u8def\u5f84\")<br><br>driver&nbsp;=&nbsp;webdriver.Chrome(service=s,&nbsp;options=chrome_options)<br><br>driver.get(url='URL')<br><br>driver.save_screenshot('result.png')<br><br>#&nbsp;\u4fdd\u5b58<br>source&nbsp;=&nbsp;driver.page_source<br>with&nbsp;open('result.html',&nbsp;'w')&nbsp;as&nbsp;f:<br>&nbsp;&nbsp;&nbsp;&nbsp;f.write(source)<br><br>time.sleep(200)<\/code><\/pre>\n\n\n\n<p>\u9875\u9762\u660e\u663e\u505a\u4e86\u53cd\u722c\uff0c\u7f51\u9875\u8fd4\u56de\u76f4\u63a5\u8fd4\u56de\u7a7a\u767d\u5185\u5bb9<\/p>\n\n\n\n<figure class=\"wp-block-image\"><img decoding=\"async\" src=\"https:\/\/mmbiz.qpic.cn\/mmbiz_png\/atOH362BoysjUib2EMBCv6O96CwLp7fa4zk0Qs0ibcSbsK2yEkRnfbgy3apGicoMTKAAEoyQEVMt6UKkricCwjN3Ew\/640?wx_fmt=png&amp;tp=webp&amp;wxfrom=5&amp;wx_lazy=1&amp;wx_co=1\" alt=\"\u56fe\u7247\"\/><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">2. CDP<\/h2>\n\n\n\n<p>CDP \u5168\u79f0\u4e3a&nbsp;Chrome Devtools-Protocol<\/p>\n\n\n\n<figure class=\"wp-block-embed\"><div class=\"wp-block-embed__wrapper\">\nhttps:\/\/chromedevtools.github.io\/devtools-protocol\n<\/div><\/figure>\n\n\n\n<p>\u901a\u8fc7\u6267\u884c CDP \u547d\u4ee4\uff0c\u53ef\u4ee5\u5728\u7f51\u9875\u52a0\u8f7d\u524d\u8fd0\u884c\u4e00\u6bb5\u4ee3\u7801\uff0c\u8fdb\u800c\u6539\u53d8\u6d4f\u89c8\u5668\u7684\u6307\u7eb9\u7279\u5f81<\/p>\n\n\n\n<p>\u6bd4\u5982\uff0cwindow.navigator.webdriver&nbsp;\u5728 Selenium \u76f4\u63a5\u6253\u5f00\u7f51\u9875\u65f6\u8fd4\u56de\u7ed3\u679c\u4e3a true\uff1b\u800c\u624b\u52a8\u6253\u5f00\u7f51\u9875\u65f6\uff0c\u8be5\u5bf9\u8c61\u503c\u4e3a undefined<\/p>\n\n\n\n<p>\u56e0\u6b64\uff0c\u6211\u4eec\u53ef\u4ee5\u5229\u7528&nbsp;CDP \u547d\u4ee4\u4fee\u6539\u8be5\u5bf9\u8c61\u7684\u503c\uff0c\u8fbe\u5230\u9690\u85cf\u6307\u7eb9\u7279\u5f81\u7684\u76ee\u7684<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from&nbsp;selenium&nbsp;import&nbsp;webdriver<br>from&nbsp;selenium.webdriver.chrome.options&nbsp;import&nbsp;Options<br>from&nbsp;selenium.webdriver.chrome.service&nbsp;import&nbsp;Service<br>import&nbsp;time<br><br>chrome_options&nbsp;=&nbsp;Options()<br><br>s&nbsp;=&nbsp;Service(r\"chromedriver.exe\u8def\u5f84\")<br><br>driver&nbsp;=&nbsp;webdriver.Chrome(service=s,&nbsp;options=chrome_options)<br><br>#&nbsp;\u6267\u884ccdp\u547d\u4ee4\uff0c\u4fee\u6539\uff08window.navigator.webdriver&nbsp;\uff09\u5bf9\u8c61\u7684\u503c<br>driver.execute_cdp_cmd(\"Page.addScriptToEvaluateOnNewDocument\",&nbsp;{<br>&nbsp;&nbsp;&nbsp;&nbsp;\"source\":&nbsp;\"\"\"<br>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Object.defineProperty(navigator,&nbsp;'webdriver',&nbsp;{<br>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;get:&nbsp;()&nbsp;=&gt;&nbsp;undefined<br>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;})<br>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\"\"\"<br>})<br><br>driver.get(url='URL')<br><br>driver.save_screenshot('result.png')<br><br>#&nbsp;\u4fdd\u5b58<br>source&nbsp;=&nbsp;driver.page_source<br>with&nbsp;open('result.html',&nbsp;'w',&nbsp;encoding='utf-8')&nbsp;as&nbsp;f:<br>&nbsp;&nbsp;&nbsp;&nbsp;f.write(source)<br><br>time.sleep(200)<\/code><\/pre>\n\n\n\n<p>\u9700\u8981\u6307\u51fa\u7684\u662f\uff0c\u6d4f\u89c8\u5668\u7684\u6307\u7eb9\u7279\u5f81\u5f88\u591a\uff0c\u4f7f\u7528\u8be5\u65b9\u6cd5\u5b58\u5728\u4e00\u4e9b\u5c40\u9650\u6027<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">3.&nbsp;stealth.min.js<\/h2>\n\n\n\n<p>\u8be5\u6587\u4ef6\u5305\u542b\u4e86\u5e38\u7528\u7684\u6d4f\u89c8\u5668\u7279\u5f81\uff0c\u6211\u4eec\u53ea\u9700\u8981\u8bfb\u53d6\u8be5\u6587\u4ef6\uff0c\u7136\u540e\u6267\u884c CDP \u547d\u4ee4\u5373\u53ef<\/p>\n\n\n\n<p>\u4e0b\u8f7d\u5730\u5740\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-preformatted\">https:\/\/github.com\/berstend\/puppeteer-extra\/tree\/stealth-js<\/pre>\n\n\n\n<pre class=\"wp-block-code\"><code>from\u00a0selenium\u00a0import\u00a0webdriver\nfrom\u00a0selenium.webdriver.chrome.options\u00a0import\u00a0Options\nfrom\u00a0selenium.webdriver.chrome.service\u00a0import\u00a0Service\nfrom\u00a0selenium.webdriver.common.by\u00a0import\u00a0By\nimport\u00a0time\n\nchrome_options\u00a0=\u00a0Options()\n\n#\u00a0\u65e0\u5934\u6a21\u5f0f\n#\u00a0chrome_options.add_argument(\"--headless\")\n\n#\u00a0\u6dfb\u52a0\u8bf7\u6c42\u5934\nchrome_options.add_argument(\n\u00a0\u00a0\u00a0\u00a0'user-agent=Mozilla\/5.0\u00a0(Windows\u00a0NT\u00a010.0;\u00a0Win64;\u00a0x64)\u00a0AppleWebKit\/537.36\u00a0(KHTML,\u00a0like\u00a0Gecko)\u00a0Chrome\/109.0.0.0\u00a0Safari\/537.36')\n\ns\u00a0=\u00a0Service(r\"chromedriver.exe\u8def\u5f84\")\n\ndriver\u00a0=\u00a0webdriver.Chrome(service=s,\u00a0options=chrome_options)\n\n#\u00a0\u5229\u7528stealth.min.js\u9690\u85cf\u6d4f\u89c8\u5668\u6307\u7eb9\u7279\u5f81,\u5148\u4e0b\u8f7d\uff0c\u5e76\u4e0e\u6587\u4ef6\u653e\u540c\u4e00\u76ee\u5f55\u4e0b\n# stealth.min.js\u4e0b\u8f7d\u5730\u5740\uff1ahttps:\/\/github.com\/berstend\/puppeteer-extra\/tree\/stealth-js\nwith\u00a0open('.\/stealth.min.js')\u00a0as\u00a0f:\n\u00a0\u00a0\u00a0\u00a0driver.execute_cdp_cmd(\"Page.addScriptToEvaluateOnNewDocument\",\u00a0{\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"source\":\u00a0f.read()\n\u00a0\u00a0\u00a0\u00a0})\n\ndriver.get(url='URL')\n#\u00a0driver.get(url='https:\/\/bot.sannysoft.com\/')\n\n#\u00a0\u4fdd\u5b58\u56fe\u7247\ndriver.save_screenshot('result.png')\n\ntime.sleep(200)<\/code><\/pre>\n\n\n\n<h2 class=\"wp-block-heading\">4.&nbsp;undetected_chromedriver<\/h2>\n\n\n\n<p>\u8fd9\u662f\u4e00\u4e2a\u9632\u6b62\u6d4f\u89c8\u5668\u6307\u7eb9\u7279\u5f81\u88ab\u8bc6\u522b\u7684\u4f9d\u8d56\u5e93\uff0c\u53ef\u4ee5\u81ea\u52a8\u4e0b\u8f7d\u9a71\u52a8\u914d\u7f6e\u518d\u8fd0\u884c<\/p>\n\n\n\n<p>\u9879\u76ee\u5730\u5740\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-preformatted\">https:\/\/github.com\/ultrafunkamsterdam\/undetected-chromedriver<\/pre>\n\n\n\n<p>\u4f7f\u7528\u6b65\u9aa4\u4e5f\u5f88\u65b9\u4fbf<\/p>\n\n\n\n<p>\u9996\u5148\uff0c\u6211\u4eec\u5b89\u88c5\u4f9d\u8d56\u5e93<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>#&nbsp;\u5b89\u88c5\u4f9d\u8d56<br>pip3&nbsp;install&nbsp;undetected-chromedriver<\/code><\/pre>\n\n\n\n<p>\u7136\u540e\uff0c\u901a\u8fc7\u4e0b\u9762\u51e0\u884c\u4ee3\u7801\u5c31\u80fd\u5b8c\u7f8e\u9690\u85cf\u6d4f\u89c8\u5668\u7684\u6307\u7eb9\u7279\u5f81<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from&nbsp;selenium.webdriver.chrome.options&nbsp;import&nbsp;Options<br>from&nbsp;selenium.webdriver.chrome.service&nbsp;import&nbsp;Service<br>import&nbsp;time<br>import&nbsp;undetected_chromedriver&nbsp;as&nbsp;uc<br><br>chrome_options&nbsp;=&nbsp;Options()<br>#&nbsp;chrome_options.add_argument(\"--headless\")<br><br>s&nbsp;=&nbsp;Service(r\"chromedriver.exe\")<br><br>driver&nbsp;=&nbsp;uc.Chrome(service=s,&nbsp;options=chrome_options)<br><br>driver.get(url='URL')<br>#&nbsp;driver.get(url='https:\/\/bot.sannysoft.com\/')<br><br>driver.save_screenshot('result.png')<br>time.sleep(100)<\/code><\/pre>\n\n\n\n<h2 class=\"wp-block-heading\">5.&nbsp;\u64cd\u4f5c\u5df2\u5f00\u542f\u7684\u6d4f\u89c8\u5668<\/h2>\n\n\n\n<p>\u6700\u540e\u4e00\u79cd\u65b9\u5f0f\u4e0a\u7bc7\u6587\u7ae0\u5df2\u7ecf\u4ecb\u7ecd\u8fc7<\/p>\n\n\n\n<p><a target=\"_blank\" href=\"http:\/\/mp.weixin.qq.com\/s?__biz=MzU1OTI0NjI1NQ==&amp;mid=2247491689&amp;idx=1&amp;sn=654d30f30a75926f96e8fd80e0bbabfc&amp;chksm=fc189ea9cb6f17bf37d35c00bb2e613b928b83f5fcccee535f4d8fbc09c1804ab075f9318357&amp;scene=21#wechat_redirect\" rel=\"noreferrer noopener\">\u5982\u4f55\u5229\u7528 Selenium \u5bf9\u5df2\u6253\u5f00\u7684\u6d4f\u89c8\u5668\u8fdb\u884c\u722c\u866b\uff01<\/a><\/p>\n\n\n\n<p>\u6211\u4eec\u53ea\u9700\u8981\u901a\u8fc7\u547d\u4ee4\u884c\u542f\u52a8\u4e00\u4e2a\u6d4f\u89c8\u5668<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>import&nbsp;subprocess<br><br>#&nbsp;1\u3001\u6253\u5f00\u6d4f\u89c8\u5668<br>#&nbsp;\u6307\u5b9a\u7aef\u53e3\u53f7\u4e3a\uff1a1234<br>#&nbsp;\u914d\u7f6e\u7528\u6237\u6570\u636e\u8def\u5f84\uff1a--user-data-dir<br>cmd&nbsp;=&nbsp;'C:\\\\Program&nbsp;Files\\\\Google\\\\Chrome\\\\Application\\\\chrome.exe&nbsp;--remote-debugging-port=1234&nbsp;--user-data-dir=\"C:\\\\selenum\\\\user_data\"'<br><br>subprocess.run(cmd)<\/code><\/pre>\n\n\n\n<p>\u7136\u540e\uff0c\u5229\u7528 Selenium \u76f4\u63a5\u64cd\u4f5c\u4e0a\u9762\u7684\u6d4f\u89c8\u5668\u5373\u53ef\u6a21\u62df\u6b63\u5e38\u64cd\u4f5c\u6d4f\u89c8\u5668\u7684\u884c\u4e3a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>import&nbsp;time<br>from&nbsp;selenium&nbsp;import&nbsp;webdriver<br>from&nbsp;selenium.webdriver.chrome.options&nbsp;import&nbsp;Options<br>from&nbsp;selenium.webdriver.chrome.service&nbsp;import&nbsp;Service<br><br>#&nbsp;\u64cd\u4f5c\u4e0a\u9762\u5df2\u7ecf\u6253\u5f00\u7684\u6d4f\u89c8\u5668\uff0c\u8fdb\u884c\u767e\u5ea6\u641c\u7d22<br>chrome_options&nbsp;=&nbsp;Options()<br><br>#&nbsp;\u6307\u5b9a\u5df2\u7ecf\u6253\u5f00\u6d4f\u89c8\u5668\u7684\u5730\u5740\u53ca\u7aef\u53e3\u53f7<br>chrome_options.add_experimental_option(\"debuggerAddress\",&nbsp;\"127.0.0.1:1234\")<br><br>#&nbsp;\u6ce8\u610f\uff1achrome\u7248\u672c\u4e0echromedirver\u9a71\u52a8\u8981\u4fdd\u6301\u4e00\u81f4<br>#&nbsp;\u4e0b\u8f7d\u5730\u5740\uff1ahttp:\/\/chromedriver.storage.googleapis.com\/index.html<br>s&nbsp;=&nbsp;Service(r\"chromedriver.exe\")<br><br>driver&nbsp;=&nbsp;webdriver.Chrome(service=s,&nbsp;options=chrome_options)<br><br>#&nbsp;\u6253\u5f00\u76ee\u6807\u7f51\u7ad9<br>driver.get(url=\"URL\")<br><br>time.sleep(200)<\/code><\/pre>\n\n\n\n<p><\/p>\n\n\n\n<p><\/p>\n\n\n\n<p><\/p>\n\n\n\n<p>\u5b9e\u64cd\uff1a<a href=\"https:\/\/mp.weixin.qq.com\/s\/GToE_UWcuckTKBe7CIRrWQ\">\u81ea\u52a8\u5316\u79d2\u6740<\/a>\u62a2\u8d2d<\/p>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u5bf9\u4e00\u4e9b\u505a\u4e86\u53cd\u722c\u7684\u7f51\u7ad9\uff0c\u505a\u4e86\u7279\u5f81\u68c0\u6d4b\uff0c\u7528\u6765\u963b\u6b62\u4e00\u4e9b\u6076\u610f\u722c\u866b https:\/\/bot.sannysoft.com\u8fd9 [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[10],"tags":[],"class_list":["post-2062","post","type-post","status-publish","format-standard","hentry","category-10"],"_links":{"self":[{"href":"http:\/\/blog.xtaa.cn\/index.php\/wp-json\/wp\/v2\/posts\/2062","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/blog.xtaa.cn\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/blog.xtaa.cn\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/blog.xtaa.cn\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/blog.xtaa.cn\/index.php\/wp-json\/wp\/v2\/comments?post=2062"}],"version-history":[{"count":1,"href":"http:\/\/blog.xtaa.cn\/index.php\/wp-json\/wp\/v2\/posts\/2062\/revisions"}],"predecessor-version":[{"id":2063,"href":"http:\/\/blog.xtaa.cn\/index.php\/wp-json\/wp\/v2\/posts\/2062\/revisions\/2063"}],"wp:attachment":[{"href":"http:\/\/blog.xtaa.cn\/index.php\/wp-json\/wp\/v2\/media?parent=2062"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/blog.xtaa.cn\/index.php\/wp-json\/wp\/v2\/categories?post=2062"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/blog.xtaa.cn\/index.php\/wp-json\/wp\/v2\/tags?post=2062"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}