{"id":1036009,"date":"2024-12-31T12:03:31","date_gmt":"2024-12-31T04:03:31","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1036009.html"},"modified":"2024-12-31T12:03:33","modified_gmt":"2024-12-31T04:03:33","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e7%88%ac%e7%be%8e%e5%9b%a2%e7%9a%84%e6%95%b0%e6%8d%ae","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1036009.html","title":{"rendered":"\u5982\u4f55\u7528python\u722c\u7f8e\u56e2\u7684\u6570\u636e"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-docs.pingcode.com\/wp-content\/uploads\/2024\/12\/b72f9da4-ee3d-45d9-957b-f1946ca917d6.webp?x-oss-process=image\/auto-orient,1\/format,webp\" alt=\"\u5982\u4f55\u7528python\u722c\u7f8e\u56e2\u7684\u6570\u636e\" \/><\/p>\n<p><p> <strong>\u5982\u4f55\u7528python\u722c\u7f8e\u56e2\u7684\u6570\u636e<\/strong><\/p>\n<\/p>\n<p><p>\u7528Python\u722c\u7f8e\u56e2\u7684\u6570\u636e\u6d89\u53ca<strong>\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u89e3\u6790HTML\u9875\u9762\u3001\u5904\u7406JavaScript\u52a0\u8f7d\u7684\u6570\u636e\u3001\u5e94\u5bf9\u53cd\u722c\u866b\u673a\u5236<\/strong>\u7b49\u51e0\u4e2a\u65b9\u9762\u3002\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u53d1\u9001HTTP\u8bf7\u6c42\u6765\u83b7\u53d6\u7f8e\u56e2\u7684\u7f51\u9875\u5185\u5bb9\u3002\u89e3\u6790HTML\u9875\u9762\u65f6\uff0c\u53ef\u80fd\u4f1a\u9047\u5230JavaScript\u52a8\u6001\u52a0\u8f7d\u7684\u6570\u636e\uff0c\u9700\u8981\u4f7f\u7528Selenium\u7b49\u5de5\u5177\u8fdb\u884c\u5904\u7406\u3002\u6700\u91cd\u8981\u7684\u662f\uff0c\u7f8e\u56e2\u7f51\u7ad9\u6709\u4e25\u683c\u7684\u53cd\u722c\u866b\u673a\u5236\uff0c\u9700\u8981\u901a\u8fc7\u8bbe\u7f6e\u8bf7\u6c42\u5934\u3001\u4f7f\u7528\u4ee3\u7406\u7b49\u65b9\u5f0f\u6765\u5e94\u5bf9\u3002\u4e0b\u9762\u6211\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u8fd9\u4e9b\u6b65\u9aa4\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u53d1\u9001HTTP\u8bf7\u6c42<\/h3>\n<\/p>\n<p><p>\u4e3a\u4e86\u722c\u53d6\u7f8e\u56e2\u7684\u6570\u636e\uff0c\u6211\u4eec\u9996\u5148\u9700\u8981\u53d1\u9001HTTP\u8bf7\u6c42\u6765\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3002\u901a\u5e38\u4f7f\u7528 <code>requests<\/code> \u5e93\u6765\u5b9e\u73b0\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;https:\/\/www.meituan.com\/&#39;<\/p>\n<p>headers = {<\/p>\n<p>    &#39;User-Agent&#39;: &#39;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/58.0.3029.110 Safari\/537.3&#39;}<\/p>\n<p>response = requests.get(url, headers=headers)<\/p>\n<p>print(response.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528 <code>requests.get()<\/code> \u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u5e76\u901a\u8fc7\u8bbe\u7f6e <code>headers<\/code> \u6765\u6a21\u62df\u6d4f\u89c8\u5668\u8bf7\u6c42\uff0c\u4ee5\u6b64\u7ed5\u8fc7\u4e00\u4e9b\u7b80\u5355\u7684\u53cd\u722c\u866b\u63aa\u65bd\u3002<\/p>\n<\/p>\n<p><h3>\u4e8c\u3001\u89e3\u6790HTML\u9875\u9762<\/h3>\n<\/p>\n<p><p>\u83b7\u5f97\u7f51\u9875\u5185\u5bb9\u540e\uff0c\u6211\u4eec\u9700\u8981\u89e3\u6790HTML\u9875\u9762\uff0c\u4ee5\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\u3002\u901a\u5e38\u4f7f\u7528 <code>BeautifulSoup<\/code> \u5e93\u6765\u89e3\u6790HTML\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>soup = BeautifulSoup(response.text, &#39;html.parser&#39;)<\/p>\n<p>titles = soup.find_all(&#39;h1&#39;)<\/p>\n<p>for title in titles:<\/p>\n<p>    print(title.get_text())<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528 <code>BeautifulSoup<\/code> \u89e3\u6790HTML\uff0c\u5e76\u63d0\u53d6\u6240\u6709 <code>&lt;h1&gt;<\/code> \u6807\u7b7e\u5185\u7684\u6587\u672c\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h3>\u4e09\u3001\u5904\u7406JavaScript\u52a0\u8f7d\u7684\u6570\u636e<\/h3>\n<\/p>\n<p><p>\u7f8e\u56e2\u7b49\u73b0\u4ee3\u7f51\u7ad9\u901a\u5e38\u4f7f\u7528JavaScript\u6765\u52a8\u6001\u52a0\u8f7d\u6570\u636e\uff0c\u8fd9\u4f7f\u5f97\u7b80\u5355\u7684HTML\u89e3\u6790\u65e0\u6cd5\u83b7\u53d6\u5230\u6240\u6709\u6570\u636e\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528 <code>Selenium<\/code> \u5e93\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u52a0\u8f7d\u5e76\u83b7\u53d6\u52a8\u6001\u6570\u636e\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>driver = webdriver.Chrome()<\/p>\n<p>driver.get(url)<\/p>\n<p>content = driver.page_source<\/p>\n<p>soup = BeautifulSoup(content, &#39;html.parser&#39;)<\/p>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7 <code>Selenium<\/code> \u542f\u52a8\u4e00\u4e2a\u6d4f\u89c8\u5668\u5b9e\u4f8b\uff0c\u52a0\u8f7d\u7f51\u9875\u5e76\u83b7\u53d6\u9875\u9762\u6e90\u4ee3\u7801\uff0c\u7136\u540e\u518d\u4f7f\u7528 <code>BeautifulSoup<\/code> \u8fdb\u884c\u89e3\u6790\u3002<\/p>\n<\/p>\n<p><h3>\u56db\u3001\u5e94\u5bf9\u53cd\u722c\u866b\u673a\u5236<\/h3>\n<\/p>\n<p><p>\u7f8e\u56e2\u7b49\u5927\u578b\u7f51\u7ad9\u901a\u5e38\u5177\u6709\u590d\u6742\u7684\u53cd\u722c\u866b\u673a\u5236\uff0c\u5982IP\u5c01\u7981\u3001\u9a8c\u8bc1\u7801\u7b49\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u4e00\u4e9b\u7b56\u7565\u6765\u5e94\u5bf9\u8fd9\u4e9b\u673a\u5236\u3002<\/p>\n<\/p>\n<p><h4>1\u3001\u8bbe\u7f6e\u8bf7\u6c42\u5934<\/h4>\n<\/p>\n<p><p>\u901a\u8fc7\u8bbe\u7f6e\u8bf7\u6c42\u5934\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u8bf7\u6c42\uff0c\u907f\u514d\u88ab\u8bc6\u522b\u4e3a\u722c\u866b\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">headers = {<\/p>\n<p>    &#39;User-Agent&#39;: &#39;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/58.0.3029.110 Safari\/537.3&#39;,<\/p>\n<p>    &#39;Referer&#39;: &#39;https:\/\/www.meituan.com\/&#39;<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, headers=headers)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2\u3001\u4f7f\u7528\u4ee3\u7406<\/h4>\n<\/p>\n<p><p>\u901a\u8fc7\u4f7f\u7528\u4ee3\u7406IP\uff0c\u53ef\u4ee5\u907f\u514d\u56e0\u9891\u7e41\u8bf7\u6c42\u540c\u4e00IP\u800c\u88ab\u5c01\u7981\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">proxies = {<\/p>\n<p>    &#39;http&#39;: &#39;http:\/\/10.10.1.10:3128&#39;,<\/p>\n<p>    &#39;https&#39;: &#39;http:\/\/10.10.1.10:1080&#39;,<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, headers=headers, proxies=proxies)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e94\u3001\u5b8c\u6574\u793a\u4f8b<\/h3>\n<\/p>\n<p><p>\u4ee5\u4e0b\u662f\u4e00\u4e2a\u5b8c\u6574\u7684\u793a\u4f8b\u4ee3\u7801\uff0c\u6f14\u793a\u5982\u4f55\u4f7f\u7528Python\u722c\u53d6\u7f8e\u56e2\u7f51\u9875\uff0c\u5e76\u5e94\u5bf9\u5404\u79cd\u53cd\u722c\u866b\u673a\u5236\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<p>from selenium import webdriver<\/p>\n<p>import time<\/p>\n<h2><strong>\u8bbe\u7f6e\u8bf7\u6c42\u5934<\/strong><\/h2>\n<p>headers = {<\/p>\n<p>    &#39;User-Agent&#39;: &#39;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/58.0.3029.110 Safari\/537.3&#39;,<\/p>\n<p>    &#39;Referer&#39;: &#39;https:\/\/www.meituan.com\/&#39;<\/p>\n<p>}<\/p>\n<h2><strong>\u4f7f\u7528Selenium\u83b7\u53d6\u52a8\u6001\u52a0\u8f7d\u7684\u6570\u636e<\/strong><\/h2>\n<p>url = &#39;https:\/\/www.meituan.com\/&#39;<\/p>\n<p>driver = webdriver.Chrome()<\/p>\n<p>driver.get(url)<\/p>\n<p>time.sleep(5)  # \u7b49\u5f85\u9875\u9762\u52a0\u8f7d<\/p>\n<p>content = driver.page_source<\/p>\n<p>driver.quit()<\/p>\n<h2><strong>\u89e3\u6790HTML<\/strong><\/h2>\n<p>soup = BeautifulSoup(content, &#39;html.parser&#39;)<\/p>\n<p>titles = soup.find_all(&#39;h1&#39;)<\/p>\n<p>for title in titles:<\/p>\n<p>    print(title.get_text())<\/p>\n<h2><strong>\u4f7f\u7528\u4ee3\u7406\u53d1\u9001\u8bf7\u6c42<\/strong><\/h2>\n<p>proxies = {<\/p>\n<p>    &#39;http&#39;: &#39;http:\/\/10.10.1.10:3128&#39;,<\/p>\n<p>    &#39;https&#39;: &#39;http:\/\/10.10.1.10:1080&#39;,<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, headers=headers, proxies=proxies)<\/p>\n<p>print(response.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u722c\u53d6\u7f8e\u56e2\u7684\u6570\u636e\u3002\u5173\u952e\u5728\u4e8e<strong>\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u89e3\u6790HTML\u9875\u9762\u3001\u5904\u7406JavaScript\u52a0\u8f7d\u7684\u6570\u636e\u3001\u5e94\u5bf9\u53cd\u722c\u866b\u673a\u5236<\/strong>\u3002\u4f7f\u7528 <code>requests<\/code> \u5e93\u53d1\u9001\u8bf7\u6c42\uff0c<code>BeautifulSoup<\/code> \u89e3\u6790HTML\uff0c<code>Selenium<\/code> \u5904\u7406\u52a8\u6001\u52a0\u8f7d\u7684\u6570\u636e\uff0c\u5e76\u901a\u8fc7\u8bbe\u7f6e\u8bf7\u6c42\u5934\u548c\u4f7f\u7528\u4ee3\u7406\u6765\u5e94\u5bf9\u53cd\u722c\u866b\u673a\u5236\u3002\u5e0c\u671b\u8fd9\u7bc7\u6587\u7ae0\u5bf9\u4f60\u6709\u6240\u5e2e\u52a9\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u9009\u62e9\u5408\u9002\u7684Python\u5e93\u8fdb\u884c\u7f8e\u56e2\u6570\u636e\u722c\u53d6\uff1f<\/strong><br \/>\u5728\u8fdb\u884c\u7f8e\u56e2\u6570\u636e\u722c\u53d6\u65f6\uff0c\u9009\u62e9\u5408\u9002\u7684Python\u5e93\u81f3\u5173\u91cd\u8981\u3002\u5e38\u7528\u7684\u5e93\u5305\u62ecRequests\u548cBeautifulSoup\uff0c\u524d\u8005\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u540e\u8005\u7528\u4e8e\u89e3\u6790HTML\u6587\u6863\u3002\u6b64\u5916\uff0cScrapy\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u6846\u67b6\uff0c\u9002\u5408\u5927\u89c4\u6a21\u722c\u53d6\u3002\u5982\u679c\u9700\u8981\u5904\u7406JavaScript\u6e32\u67d3\u7684\u9875\u9762\uff0c\u53ef\u4ee5\u8003\u8651\u4f7f\u7528Selenium\u6216Playwright\u3002\u6839\u636e\u5177\u4f53\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u5de5\u5177\uff0c\u53ef\u4ee5\u63d0\u9ad8\u722c\u866b\u7684\u6548\u7387\u548c\u7a33\u5b9a\u6027\u3002<\/p>\n<p><strong>\u5728\u722c\u53d6\u7f8e\u56e2\u6570\u636e\u65f6\uff0c\u5e94\u8be5\u6ce8\u610f\u54ea\u4e9b\u6cd5\u5f8b\u548c\u9053\u5fb7\u95ee\u9898\uff1f<\/strong><br \/>\u722c\u53d6\u7f8e\u56e2\u6570\u636e\u65f6\uff0c\u9700\u8981\u9075\u5faa\u76f8\u5173\u6cd5\u5f8b\u6cd5\u89c4\uff0c\u786e\u4fdd\u4e0d\u8fdd\u53cd\u7f51\u7ad9\u7684\u4f7f\u7528\u6761\u6b3e\u3002\u52a1\u5fc5\u5173\u6ce8robots.txt\u6587\u4ef6\uff0c\u4e86\u89e3\u7f51\u7ad9\u5bf9\u722c\u866b\u7684\u9650\u5236\u3002\u540c\u65f6\uff0c\u907f\u514d\u5bf9\u670d\u52a1\u5668\u9020\u6210\u8fc7\u5927\u8d1f\u8377\uff0c\u5efa\u8bae\u8bbe\u7f6e\u5408\u7406\u7684\u8bf7\u6c42\u95f4\u9694\u3002\u6b64\u5916\uff0c\u4f7f\u7528\u722c\u53d6\u7684\u6570\u636e\u65f6\uff0c\u5e94\u5c0a\u91cd\u6570\u636e\u7684\u7248\u6743\u548c\u9690\u79c1\u6743\uff0c\u786e\u4fdd\u5408\u6cd5\u5408\u89c4\u4f7f\u7528\u3002<\/p>\n<p><strong>\u5982\u4f55\u5904\u7406\u7f8e\u56e2\u7f51\u7ad9\u4e2d\u7684\u53cd\u722c\u673a\u5236\uff1f<\/strong><br \/>\u7f8e\u56e2\u7f51\u7ad9\u53ef\u80fd\u4f1a\u5b9e\u65bd\u591a\u79cd\u53cd\u722c\u673a\u5236\uff0c\u4f8b\u5982IP\u9650\u5236\u3001\u8bf7\u6c42\u9891\u7387\u76d1\u63a7\u548c\u9a8c\u8bc1\u7801\u9a8c\u8bc1\u7b49\u3002\u5e94\u5bf9\u8fd9\u4e9b\u673a\u5236\u53ef\u4ee5\u91c7\u53d6\u4ee5\u4e0b\u7b56\u7565\uff1a\u4f7f\u7528\u4ee3\u7406IP\u6c60\u6765\u66f4\u6362\u8bf7\u6c42IP\uff0c\u964d\u4f4e\u8bf7\u6c42\u9891\u7387\u4ee5\u89c4\u907f\u68c0\u6d4b\uff0c\u5fc5\u8981\u65f6\u91c7\u7528\u81ea\u52a8\u5316\u5de5\u5177\u5904\u7406\u9a8c\u8bc1\u7801\u3002\u6b64\u5916\uff0c\u53ef\u4ee5\u901a\u8fc7\u6a21\u62df\u7528\u6237\u884c\u4e3a\u6765\u51cf\u5c11\u88ab\u8bc6\u522b\u4e3a\u722c\u866b\u7684\u98ce\u9669\uff0c\u4f8b\u5982\u968f\u673a\u4fee\u6539\u8bf7\u6c42\u5934\u548c\u4f7f\u7528\u6d4f\u89c8\u5668\u6a21\u62df\u5de5\u5177\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5982\u4f55\u7528python\u722c\u7f8e\u56e2\u7684\u6570\u636e \u7528Python\u722c\u7f8e\u56e2\u7684\u6570\u636e\u6d89\u53ca\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u89e3\u6790HTML\u9875\u9762\u3001\u5904\u7406Java [&hellip;]","protected":false},"author":3,"featured_media":1036016,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1036009"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1036009"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1036009\/revisions"}],"predecessor-version":[{"id":1036017,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1036009\/revisions\/1036017"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1036016"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1036009"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1036009"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1036009"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}