{"id":1035432,"date":"2024-12-31T11:58:47","date_gmt":"2024-12-31T03:58:47","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1035432.html"},"modified":"2024-12-31T11:58:49","modified_gmt":"2024-12-31T03:58:49","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e5%85%ad%e8%a1%8c%e4%bb%a3%e7%a0%81%e7%88%ac%e5%8f%96","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1035432.html","title":{"rendered":"\u5982\u4f55\u7528python\u516d\u884c\u4ee3\u7801\u722c\u53d6"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-docs.pingcode.com\/wp-content\/uploads\/2024\/12\/c3fb8897-c263-4468-a2ca-556400481ceb.webp?x-oss-process=image\/auto-orient,1\/format,webp\" alt=\"\u5982\u4f55\u7528python\u516d\u884c\u4ee3\u7801\u722c\u53d6\" \/><\/p>\n<p><p> <strong>\u4f7f\u7528Python\u8fdb\u884c\u7f51\u7edc\u722c\u53d6\u662f\u4e00\u9879\u5f3a\u5927\u7684\u6280\u80fd\uff0c\u5c24\u5176\u662f\u5728\u6570\u636e\u79d1\u5b66\u548cWeb\u5f00\u53d1\u9886\u57df\u3002\u901a\u8fc7\u4f7f\u7528\u7b80\u5355\u7684\u516d\u884c\u4ee3\u7801\uff0c\u6211\u4eec\u53ef\u4ee5\u8f7b\u677e\u5730\u4ece\u7f51\u9875\u4e0a\u83b7\u53d6\u6570\u636e\u3002\u4ee5\u4e0b\u662f\u5b9e\u73b0\u8fd9\u4e00\u76ee\u6807\u7684\u51e0\u4e2a\u5173\u952e\u6b65\u9aa4\uff1a\u4f7f\u7528requests\u5e93\u3001BeautifulSoup\u8fdb\u884cHTML\u89e3\u6790\u3001\u9009\u62e9\u76ee\u6807\u6570\u636e\u3001\u5904\u7406\u5f02\u5e38\u60c5\u51b5\u3001\u4f7f\u7528\u5408\u9002\u7684HTTP\u5934\u3001\u548c\u4fdd\u5b58\u6570\u636e\u3002<\/strong>\u5176\u4e2d\uff0c\u4f7f\u7528requests\u5e93\u548cBeautifulSoup\u8fdb\u884cHTML\u89e3\u6790\u662f\u6838\u5fc3\u6b65\u9aa4\u3002<\/p>\n<\/p>\n<p><p>\u4e00\u3001\u4f7f\u7528REQUESTS\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/p>\n<\/p>\n<p><p>requests\u5e93\u662fPython\u4e2d\u6700\u5e38\u7528\u7684HTTP\u5e93\u4e4b\u4e00\uff0c\u5b83\u53ef\u4ee5\u8ba9\u6211\u4eec\u8f7b\u677e\u5730\u5411\u76ee\u6807\u7f51\u9875\u53d1\u9001\u8bf7\u6c42\u5e76\u83b7\u53d6\u54cd\u5e94\u3002\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5requests\u5e93\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\u7528\u4ee5\u4e0b\u4ee3\u7801\u6765\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &quot;http:\/\/example.com&quot;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>html_content = response.text<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c<code>requests.get(url)<\/code>\u65b9\u6cd5\u5411\u76ee\u6807\u7f51\u9875\u53d1\u9001GET\u8bf7\u6c42\uff0c\u5e76\u5c06\u54cd\u5e94\u5185\u5bb9\u5b58\u50a8\u5728<code>response<\/code>\u5bf9\u8c61\u4e2d\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u901a\u8fc7<code>response.text<\/code>\u5c5e\u6027\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\uff0c\u5e76\u5c06\u5176\u5b58\u50a8\u5728<code>html_content<\/code>\u53d8\u91cf\u4e2d\u3002<\/p>\n<\/p>\n<p><p>\u4e8c\u3001\u89e3\u6790HTML\u5185\u5bb9<\/p>\n<\/p>\n<p><p>\u83b7\u53d6\u5230\u7f51\u9875\u5185\u5bb9\u540e\uff0c\u6211\u4eec\u9700\u8981\u4f7f\u7528BeautifulSoup\u5e93\u5bf9HTML\u8fdb\u884c\u89e3\u6790\u3002BeautifulSoup\u662f\u4e00\u4e2a\u975e\u5e38\u5f3a\u5927\u7684HTML\u89e3\u6790\u5e93\uff0c\u5b83\u53ef\u4ee5\u8ba9\u6211\u4eec\u8f7b\u677e\u5730\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u7279\u5b9a\u6570\u636e\u3002\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5BeautifulSoup\u5e93\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\u7528\u4ee5\u4e0b\u4ee3\u7801\u6765\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, &quot;html.parser&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u521b\u5efa\u4e86\u4e00\u4e2aBeautifulSoup\u5bf9\u8c61\uff0c\u5e76\u5c06HTML\u5185\u5bb9\u548c\u89e3\u6790\u5668\u7c7b\u578b\u4f20\u9012\u7ed9\u5b83\u3002\u8fd9\u91cc\u6211\u4eec\u4f7f\u7528\u7684\u662f<code>html.parser<\/code>\u89e3\u6790\u5668\uff0c\u5f53\u7136\u4f60\u4e5f\u53ef\u4ee5\u9009\u62e9\u5176\u4ed6\u89e3\u6790\u5668\uff0c\u6bd4\u5982<code>lxml<\/code>\u3002<\/p>\n<\/p>\n<p><p>\u4e09\u3001\u9009\u62e9\u76ee\u6807\u6570\u636e<\/p>\n<\/p>\n<p><p>\u5728\u89e3\u6790\u5b8c\u7f51\u9875\u540e\uff0c\u6211\u4eec\u9700\u8981\u9009\u62e9\u76ee\u6807\u6570\u636e\u3002\u901a\u5e38\uff0c\u8fd9\u6d89\u53ca\u5230\u67e5\u627e\u7279\u5b9a\u7684HTML\u6807\u7b7e\u548c\u5c5e\u6027\u3002\u5047\u8bbe\u6211\u4eec\u8981\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u6240\u6709\u94fe\u63a5\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">links = soup.find_all(&quot;a&quot;)<\/p>\n<p>for link in links:<\/p>\n<p>    print(link.get(&quot;href&quot;))<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528<code>soup.find_all(&quot;a&quot;)<\/code>\u65b9\u6cd5\u67e5\u627e\u6240\u6709\u7684<code>&lt;a&gt;<\/code>\u6807\u7b7e\uff0c\u5e76\u5c06\u5176\u5b58\u50a8\u5728<code>links<\/code>\u5217\u8868\u4e2d\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u904d\u5386<code>links<\/code>\u5217\u8868\uff0c\u5e76\u4f7f\u7528<code>link.get(&quot;href&quot;)<\/code>\u65b9\u6cd5\u83b7\u53d6\u6bcf\u4e2a\u94fe\u63a5\u7684URL\u3002<\/p>\n<\/p>\n<p><p>\u56db\u3001\u5904\u7406\u5f02\u5e38\u60c5\u51b5<\/p>\n<\/p>\n<p><p>\u5728\u5b9e\u9645\u64cd\u4f5c\u4e2d\uff0c\u6211\u4eec\u53ef\u80fd\u4f1a\u9047\u5230\u5404\u79cd\u5f02\u5e38\u60c5\u51b5\uff0c\u6bd4\u5982\u7f51\u7edc\u8fde\u63a5\u5931\u8d25\u3001\u76ee\u6807\u7f51\u9875\u4e0d\u5b58\u5728\u7b49\u3002\u56e0\u6b64\uff0c\u6211\u4eec\u9700\u8981\u6dfb\u52a0\u5f02\u5e38\u5904\u7406\u4ee3\u7801\u6765\u63d0\u9ad8\u7a0b\u5e8f\u7684\u9c81\u68d2\u6027\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">try:<\/p>\n<p>    response = requests.get(url)<\/p>\n<p>    response.r<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>se_for_status()<\/p>\n<p>except requests.exceptions.RequestException as e:<\/p>\n<p>    print(f&quot;Error: {e}&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528<code>try<\/code>\u5757\u6765\u53d1\u9001\u8bf7\u6c42\uff0c\u5e76\u4f7f\u7528<code>response.raise_for_status()<\/code>\u65b9\u6cd5\u68c0\u67e5\u54cd\u5e94\u72b6\u6001\u7801\u3002\u5982\u679c\u8bf7\u6c42\u5931\u8d25\uff0c<code>except<\/code>\u5757\u5c06\u6355\u83b7\u5f02\u5e38\u5e76\u8f93\u51fa\u9519\u8bef\u4fe1\u606f\u3002<\/p>\n<\/p>\n<p><p>\u4e94\u3001\u4f7f\u7528\u5408\u9002\u7684HTTP\u5934<\/p>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u7ad9\u53ef\u80fd\u4f1a\u68c0\u6d4b\u5e76\u963b\u6b62\u81ea\u52a8\u5316\u8bf7\u6c42\uff0c\u4e3a\u4e86\u907f\u514d\u8fd9\u79cd\u60c5\u51b5\uff0c\u6211\u4eec\u53ef\u4ee5\u5728\u8bf7\u6c42\u4e2d\u6dfb\u52a0\u5408\u9002\u7684HTTP\u5934\uff0c\u6bd4\u5982User-Agent\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">headers = {<\/p>\n<p>    &quot;User-Agent&quot;: &quot;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/58.0.3029.110 Safari\/537.3&quot;<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, headers=headers)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u521b\u5efa\u4e86\u4e00\u4e2a\u5305\u542bUser-Agent\u7684<code>headers<\/code>\u5b57\u5178\uff0c\u5e76\u5c06\u5176\u4f20\u9012\u7ed9<code>requests.get<\/code>\u65b9\u6cd5\u3002<\/p>\n<\/p>\n<p><p>\u516d\u3001\u4fdd\u5b58\u6570\u636e<\/p>\n<\/p>\n<p><p>\u6700\u540e\uff0c\u6211\u4eec\u9700\u8981\u5c06\u63d0\u53d6\u5230\u7684\u6570\u636e\u4fdd\u5b58\u5230\u6587\u4ef6\u4e2d\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">with open(&quot;links.txt&quot;, &quot;w&quot;) as file:<\/p>\n<p>    for link in links:<\/p>\n<p>        file.write(link.get(&quot;href&quot;) + &quot;\\n&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528<code>with open(&quot;links.txt&quot;, &quot;w&quot;) as file<\/code>\u8bed\u53e5\u6253\u5f00\u4e00\u4e2a\u6587\u4ef6\uff0c\u5e76\u4f7f\u7528<code>file.write()<\/code>\u65b9\u6cd5\u5c06\u6bcf\u4e2a\u94fe\u63a5\u5199\u5165\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n<p><p>\u901a\u8fc7\u4ee5\u4e0a\u516d\u4e2a\u6b65\u9aa4\uff0c\u6211\u4eec\u53ef\u4ee5\u8f7b\u677e\u5730\u4f7f\u7528Python\u8fdb\u884c\u7f51\u7edc\u722c\u53d6\u3002\u5e0c\u671b\u8fd9\u7bc7\u6587\u7ae0\u5bf9\u4f60\u6709\u6240\u5e2e\u52a9\u3002\u5982\u679c\u4f60\u60f3\u8981\u8fdb\u4e00\u6b65\u5b66\u4e60\u7f51\u7edc\u722c\u53d6\uff0c\u6211\u5efa\u8bae\u4f60\u9605\u8bfb\u66f4\u591a\u76f8\u5173\u6587\u6863\u548c\u6559\u7a0b\uff0c\u5e76\u5c1d\u8bd5\u5728\u5b9e\u9645\u9879\u76ee\u4e2d\u5e94\u7528\u8fd9\u4e9b\u6280\u672f\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u7528Python\u722c\u53d6\u6570\u636e\u7684\u57fa\u672c\u6b65\u9aa4\u662f\u4ec0\u4e48\uff1f<\/strong><br \/>\u5728\u4f7f\u7528Python\u8fdb\u884c\u6570\u636e\u722c\u53d6\u65f6\uff0c\u901a\u5e38\u9700\u8981\u5b89\u88c5\u76f8\u5173\u5e93\uff0c\u5982<code>requests<\/code>\u548c<code>BeautifulSoup<\/code>\u3002\u9996\u5148\uff0c\u901a\u8fc7<code>requests<\/code>\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u7136\u540e\u5229\u7528<code>BeautifulSoup<\/code>\u89e3\u6790HTML\u6587\u6863\uff0c\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\u3002\u6700\u540e\uff0c\u53ef\u4ee5\u5c06\u6570\u636e\u5b58\u50a8\u5230\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\u3002\u516d\u884c\u4ee3\u7801\u7684\u793a\u4f8b\u901a\u5e38\u5305\u62ec\u5bfc\u5165\u5e93\u3001\u53d1\u9001\u8bf7\u6c42\u3001\u89e3\u6790\u5185\u5bb9\u3001\u63d0\u53d6\u6570\u636e\u548c\u8f93\u51fa\u7ed3\u679c\u3002<\/p>\n<p><strong>\u4f7f\u7528Python\u722c\u53d6\u6570\u636e\u65f6\u9700\u8981\u6ce8\u610f\u54ea\u4e9b\u6cd5\u5f8b\u548c\u4f26\u7406\u95ee\u9898\uff1f<\/strong><br \/>\u5728\u8fdb\u884c\u6570\u636e\u722c\u53d6\u65f6\uff0c\u52a1\u5fc5\u9075\u5faa\u7f51\u7ad9\u7684<code>robots.txt<\/code>\u534f\u8bae\uff0c\u4e86\u89e3\u7f51\u7ad9\u7684\u722c\u53d6\u89c4\u5219\u3002\u6b64\u5916\uff0c\u5c0a\u91cd\u7f51\u7ad9\u7684\u7248\u6743\u548c\u6570\u636e\u4f7f\u7528\u6761\u6b3e\uff0c\u907f\u514d\u8fc7\u4e8e\u9891\u7e41\u7684\u8bf7\u6c42\uff0c\u4ee5\u514d\u5bf9\u7f51\u7ad9\u9020\u6210\u8d1f\u62c5\u3002\u4fdd\u6301\u900f\u660e\uff0c\u5c3d\u91cf\u907f\u514d\u83b7\u53d6\u654f\u611f\u4fe1\u606f\uff0c\u786e\u4fdd\u9075\u5faa\u5408\u6cd5\u7684\u4f7f\u7528\u539f\u5219\u3002<\/p>\n<p><strong>\u5982\u4f55\u5904\u7406\u722c\u53d6\u8fc7\u7a0b\u4e2d\u9047\u5230\u7684\u53cd\u722c\u866b\u673a\u5236\uff1f<\/strong><br \/>\u5728\u9762\u5bf9\u53cd\u722c\u866b\u673a\u5236\u65f6\uff0c\u53ef\u4ee5\u91c7\u53d6\u591a\u79cd\u7b56\u7565\uff0c\u4f8b\u5982\u4f7f\u7528\u968f\u673a\u7528\u6237\u4ee3\u7406\uff08User-Agent\uff09\u3001\u8bbe\u7f6e\u8bf7\u6c42\u95f4\u9694\u65f6\u95f4\u3001\u4f7f\u7528\u4ee3\u7406IP\u3001\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u7b49\u3002\u8fd9\u4e9b\u65b9\u6cd5\u53ef\u4ee5\u5e2e\u52a9\u4f60\u66f4\u597d\u5730\u7ed5\u8fc7\u4e00\u4e9b\u7b80\u5355\u7684\u53cd\u722c\u866b\u63aa\u65bd\uff0c\u786e\u4fdd\u6570\u636e\u7684\u987a\u5229\u83b7\u53d6\u3002\u6ce8\u610f\uff0c\u59cb\u7ec8\u5728\u6cd5\u5f8b\u5141\u8bb8\u7684\u8303\u56f4\u5185\u8fdb\u884c\u722c\u53d6\u64cd\u4f5c\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u4f7f\u7528Python\u8fdb\u884c\u7f51\u7edc\u722c\u53d6\u662f\u4e00\u9879\u5f3a\u5927\u7684\u6280\u80fd\uff0c\u5c24\u5176\u662f\u5728\u6570\u636e\u79d1\u5b66\u548cWeb\u5f00\u53d1\u9886\u57df\u3002\u901a\u8fc7\u4f7f\u7528\u7b80\u5355\u7684\u516d\u884c\u4ee3\u7801\uff0c\u6211\u4eec\u53ef [&hellip;]","protected":false},"author":3,"featured_media":1035446,"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\/1035432"}],"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=1035432"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1035432\/revisions"}],"predecessor-version":[{"id":1035450,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1035432\/revisions\/1035450"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1035446"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1035432"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1035432"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1035432"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}