{"id":1039914,"date":"2024-12-31T12:36:49","date_gmt":"2024-12-31T04:36:49","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1039914.html"},"modified":"2024-12-31T12:37:04","modified_gmt":"2024-12-31T04:37:04","slug":"python%e5%a6%82%e4%bd%95%e7%88%ac%e5%8f%96%e6%96%87%e4%bb%b6%e4%b8%ad%e7%9a%84%e6%95%b0%e6%8d%ae","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1039914.html","title":{"rendered":"python\u5982\u4f55\u722c\u53d6\u6587\u4ef6\u4e2d\u7684\u6570\u636e"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-docs.pingcode.com\/wp-content\/uploads\/2024\/12\/6b2f48e0-e4f9-42ae-8fad-22c3cafaf870.webp?x-oss-process=image\/auto-orient,1\/format,webp\" alt=\"python\u5982\u4f55\u722c\u53d6\u6587\u4ef6\u4e2d\u7684\u6570\u636e\" \/><\/p>\n<p><p> Python \u722c\u53d6\u6587\u4ef6\u4e2d\u7684\u6570\u636e\u662f\u4e00\u9879\u975e\u5e38\u5e38\u89c1\u7684\u6570\u636e\u5904\u7406\u4efb\u52a1\uff0c<strong>\u53ef\u4ee5\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u3001\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u7279\u5b9a\u5185\u5bb9\u3001\u4f7f\u7528pandas\u5904\u7406\u6570\u636e<\/strong>\u3002\u5176\u4e2d\uff0c\u6700\u5e38\u7528\u7684\u65b9\u6cd5\u662f\u7ed3\u5408requests\u548cBeautifulSoup\u5e93\u6765\u722c\u53d6\u7f51\u9875\u6570\u636e\u5e76\u89e3\u6790\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u63cf\u8ff0\u5982\u4f55\u5b9e\u73b0\u8fd9\u4e9b\u6b65\u9aa4\u3002<\/p>\n<\/p>\n<p><p>\u4e00\u3001requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/p>\n<p>requests\u5e93\u662fPython\u4e2d\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\u7684\u5e93\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3002\u9996\u5148\uff0c\u786e\u4fdd\u5df2\u7ecf\u5b89\u88c5requests\u5e93\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u547d\u4ee4\u5b89\u88c5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install requests<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u7136\u540e\uff0c\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u5e76\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>html_content = response.text<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u4e0a\u8ff0\u4ee3\u7801\uff0c\u6211\u4eec\u53ef\u4ee5\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><p>\u4e8c\u3001BeautifulSoup\u89e3\u6790HTML<\/p>\n<p>\u83b7\u53d6\u5230HTML\u5185\u5bb9\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u5e93\u89e3\u6790HTML\u5185\u5bb9\u5e76\u63d0\u53d6\u9700\u8981\u7684\u6570\u636e\u3002\u9996\u5148\uff0c\u786e\u4fdd\u5df2\u7ecf\u5b89\u88c5BeautifulSoup\u5e93\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u547d\u4ee4\u5b89\u88c5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install beautifulsoup4<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u7136\u540e\uff0c\u4f7f\u7528BeautifulSoup\u5e93\u89e3\u6790HTML\u5185\u5bb9\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u89e3\u6790HTML\u5185\u5bb9\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u63d0\u4f9b\u7684\u5404\u79cd\u65b9\u6cd5\u6765\u63d0\u53d6\u7279\u5b9a\u7684\u6570\u636e\u3002\u4f8b\u5982\uff0c\u63d0\u53d6\u6240\u6709\u7684\u94fe\u63a5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">links = soup.find_all(&#39;a&#39;)<\/p>\n<p>for link in links:<\/p>\n<p>    print(link.get(&#39;href&#39;))<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e09\u3001\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u7279\u5b9a\u5185\u5bb9<\/p>\n<p>\u6709\u65f6\u5019\uff0c\u6211\u4eec\u9700\u8981\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u7279\u5b9a\u5185\u5bb9\uff0c\u53ef\u4ee5\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u6765\u5b9e\u73b0\u3002Python\u4e2d\u53ef\u4ee5\u4f7f\u7528re\u5e93\u6765\u5904\u7406\u6b63\u5219\u8868\u8fbe\u5f0f\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff0c\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u6240\u6709\u7535\u5b50\u90ae\u4ef6\u5730\u5740\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import re<\/p>\n<p>em<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>ls = re.findall(r&#39;[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\\.[A-Z|a-z]{2,}&#39;, html_content)<\/p>\n<p>for email in emails:<\/p>\n<p>    print(email)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u56db\u3001pandas\u5904\u7406\u6570\u636e<\/p>\n<p>\u722c\u53d6\u5230\u6570\u636e\u540e\uff0c\u6211\u4eec\u53ef\u80fd\u9700\u8981\u5bf9\u6570\u636e\u8fdb\u884c\u8fdb\u4e00\u6b65\u5904\u7406\u548c\u5206\u6790\u3002pandas\u5e93\u662fPython\u4e2d\u975e\u5e38\u5f3a\u5927\u7684\u6570\u636e\u5904\u7406\u5e93\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u5bf9\u6570\u636e\u8fdb\u884c\u64cd\u4f5c\u3002\u9996\u5148\uff0c\u786e\u4fdd\u5df2\u7ecf\u5b89\u88c5pandas\u5e93\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u547d\u4ee4\u5b89\u88c5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install pandas<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u7136\u540e\uff0c\u4f7f\u7528pandas\u5904\u7406\u6570\u636e\u3002\u4f8b\u5982\uff0c\u5c06\u722c\u53d6\u5230\u7684\u94fe\u63a5\u4fdd\u5b58\u5230\u4e00\u4e2aCSV\u6587\u4ef6\u4e2d\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import pandas as pd<\/p>\n<p>data = {&#39;links&#39;: [link.get(&#39;href&#39;) for link in links]}<\/p>\n<p>df = pd.DataFrame(data)<\/p>\n<p>df.to_csv(&#39;links.csv&#39;, index=False)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e94\u3001\u793a\u4f8b\u4ee3\u7801<\/p>\n<p>\u4ee5\u4e0b\u662f\u4e00\u4e2a\u5b8c\u6574\u7684\u793a\u4f8b\u4ee3\u7801\uff0c\u6f14\u793a\u4e86\u5982\u4f55\u4f7f\u7528requests\u548cBeautifulSoup\u5e93\u722c\u53d6\u7f51\u9875\u6570\u636e\u5e76\u4fdd\u5b58\u5230CSV\u6587\u4ef6\u4e2d\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<p>import pandas as pd<\/p>\n<h2><strong>\u53d1\u9001HTTP\u8bf7\u6c42<\/strong><\/h2>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>html_content = response.text<\/p>\n<h2><strong>\u89e3\u6790HTML\u5185\u5bb9<\/strong><\/h2>\n<p>soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<h2><strong>\u63d0\u53d6\u6240\u6709\u7684\u94fe\u63a5<\/strong><\/h2>\n<p>links = soup.find_all(&#39;a&#39;)<\/p>\n<p>link_list = [link.get(&#39;href&#39;) for link in links]<\/p>\n<h2><strong>\u5c06\u94fe\u63a5\u4fdd\u5b58\u5230CSV\u6587\u4ef6\u4e2d<\/strong><\/h2>\n<p>data = {&#39;links&#39;: link_list}<\/p>\n<p>df = pd.DataFrame(data)<\/p>\n<p>df.to_csv(&#39;links.csv&#39;, index=False)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u4e0a\u8ff0\u6b65\u9aa4\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u722c\u53d6\u7f51\u9875\u4e2d\u7684\u6570\u636e\u5e76\u8fdb\u884c\u5904\u7406\u3002\u5e0c\u671b\u672c\u6587\u5bf9\u60a8\u6709\u6240\u5e2e\u52a9\uff0c\u5982\u679c\u6709\u4efb\u4f55\u95ee\u9898\uff0c\u8bf7\u968f\u65f6\u4e0e\u6211\u4eec\u8054\u7cfb\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u722c\u53d6\u7f51\u9875\u4e2d\u7684\u6570\u636e\uff1f<\/strong><br \/>\u4f7f\u7528Python\u722c\u53d6\u7f51\u9875\u6570\u636e\u901a\u5e38\u9700\u8981\u7528\u5230\u4e00\u4e9b\u5e93\uff0c\u6bd4\u5982<code>requests<\/code>\u7528\u4e8e\u53d1\u9001\u7f51\u7edc\u8bf7\u6c42\uff0c<code>BeautifulSoup<\/code>\u7528\u4e8e\u89e3\u6790HTML\u6587\u6863\u3002\u4f60\u53ef\u4ee5\u5148\u5b89\u88c5\u8fd9\u4e24\u4e2a\u5e93\uff0c\u7136\u540e\u901a\u8fc7\u53d1\u9001\u8bf7\u6c42\u83b7\u53d6\u9875\u9762\u5185\u5bb9\uff0c\u63a5\u7740\u5229\u7528BeautifulSoup\u89e3\u6790\u5e76\u63d0\u53d6\u6240\u9700\u6570\u636e\u3002<\/p>\n<p><strong>\u5728Python\u4e2d\u5904\u7406\u722c\u53d6\u7684\u6570\u636e\u65f6\uff0c\u6709\u54ea\u4e9b\u5e38\u89c1\u7684\u6570\u636e\u5b58\u50a8\u65b9\u5f0f\uff1f<\/strong><br \/>\u722c\u53d6\u7684\u6570\u636e\u53ef\u4ee5\u5b58\u50a8\u5728\u591a\u79cd\u683c\u5f0f\u4e2d\uff0c\u5e38\u89c1\u7684\u65b9\u5f0f\u6709\u5c06\u6570\u636e\u4fdd\u5b58\u4e3aCSV\u6587\u4ef6\u3001JSON\u6587\u4ef6\u6216\u6570\u636e\u5e93\uff08\u5982SQLite\u3001MySQL\u7b49\uff09\u3002\u9009\u62e9\u5b58\u50a8\u65b9\u5f0f\u65f6\uff0c\u53ef\u4ee5\u8003\u8651\u6570\u636e\u7684\u7ed3\u6784\u548c\u540e\u7eed\u5904\u7406\u7684\u9700\u6c42\u3002\u4f8b\u5982\uff0cCSV\u9002\u5408\u5b58\u50a8\u8868\u683c\u6570\u636e\uff0c\u800cJSON\u5219\u66f4\u9002\u5408\u5b58\u50a8\u5c42\u7ea7\u6570\u636e\u3002<\/p>\n<p><strong>\u722c\u53d6\u6570\u636e\u65f6\u5982\u4f55\u907f\u514d\u88ab\u7f51\u7ad9\u5c4f\u853d\uff1f<\/strong><br \/>\u4e3a\u4e86\u907f\u514d\u88ab\u7f51\u7ad9\u5c4f\u853d\uff0c\u53ef\u4ee5\u91c7\u53d6\u591a\u79cd\u63aa\u65bd\uff0c\u5982\u8bbe\u7f6e\u5408\u7406\u7684\u8bf7\u6c42\u95f4\u9694\u3001\u4f7f\u7528\u4ee3\u7406IP\u3001\u4fee\u6539\u8bf7\u6c42\u5934\u90e8\u4fe1\u606f\uff08\u5982User-Agent\uff09\uff0c\u4ee5\u53ca\u9075\u5faa\u7f51\u7ad9\u7684<code>robots.txt<\/code>\u534f\u8bae\u3002\u9002\u5f53\u7684\u7b56\u7565\u53ef\u4ee5\u964d\u4f4e\u88ab\u5c01\u7981\u7684\u98ce\u9669\uff0c\u786e\u4fdd\u722c\u866b\u7684\u6b63\u5e38\u8fd0\u884c\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python \u722c\u53d6\u6587\u4ef6\u4e2d\u7684\u6570\u636e\u662f\u4e00\u9879\u975e\u5e38\u5e38\u89c1\u7684\u6570\u636e\u5904\u7406\u4efb\u52a1\uff0c\u53ef\u4ee5\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u4f7f\u7528Bea [&hellip;]","protected":false},"author":3,"featured_media":1039946,"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\/1039914"}],"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=1039914"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1039914\/revisions"}],"predecessor-version":[{"id":1039950,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1039914\/revisions\/1039950"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1039946"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1039914"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1039914"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1039914"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}