{"id":1000774,"date":"2024-12-27T09:53:08","date_gmt":"2024-12-27T01:53:08","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1000774.html"},"modified":"2024-12-27T09:53:12","modified_gmt":"2024-12-27T01:53:12","slug":"python%e7%88%ac%e8%99%ab%e5%a6%82%e4%bd%95%e5%88%86%e6%9e%90%e9%a1%b5%e9%9d%a2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1000774.html","title":{"rendered":"python\u722c\u866b\u5982\u4f55\u5206\u6790\u9875\u9762"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25075228\/efbfa264-88d2-4b50-b0ad-725ba085525f.webp\" alt=\"python\u722c\u866b\u5982\u4f55\u5206\u6790\u9875\u9762\" \/><\/p>\n<p><p> \u4e00\u3001\u89e3\u6790HTML\u7ed3\u6784\u3001\u63d0\u53d6\u76ee\u6807\u6570\u636e\u3001\u4f7f\u7528\u5de5\u5177\u5305\u5982BeautifulSoup<br \/>Python\u722c\u866b\u5206\u6790\u9875\u9762\u7684\u6838\u5fc3\u5728\u4e8e\u89e3\u6790HTML\u7ed3\u6784\u3001\u63d0\u53d6\u76ee\u6807\u6570\u636e\u548c\u4f7f\u7528\u5408\u9002\u7684\u5de5\u5177\u5305\u3002<strong>\u89e3\u6790HTML\u7ed3\u6784<\/strong>\u662f\u6307\u5206\u6790\u7f51\u9875\u7684DOM\u7ed3\u6784\uff0c\u8bc6\u522b\u51fa\u9700\u8981\u7684\u6570\u636e\u6240\u5728\u7684HTML\u6807\u7b7e\u6216\u5c5e\u6027\u3002<strong>\u63d0\u53d6\u76ee\u6807\u6570\u636e<\/strong>\u5219\u662f\u901a\u8fc7\u7f16\u7a0b\u624b\u6bb5\u4eceHTML\u4e2d\u83b7\u53d6\u6240\u9700\u7684\u4fe1\u606f\u3002\u5e38\u7528\u5de5\u5177\u5305\u5982BeautifulSoup\u548clxml\u63d0\u4f9b\u4e86\u5f3a\u5927\u7684\u89e3\u6790\u529f\u80fd\uff0c\u53ef\u4ee5\u5e2e\u52a9\u5f00\u53d1\u8005\u8f7b\u677e\u5730\u5b9e\u73b0\u6570\u636e\u63d0\u53d6\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u8bb2\u89e3\u5982\u4f55\u4f7f\u7528BeautifulSoup\u8fdb\u884c\u9875\u9762\u5206\u6790\u3002<\/p>\n<\/p>\n<p><p><strong>BeautifulSoup\u662f\u4e00\u4e2a\u975e\u5e38\u53d7\u6b22\u8fce\u7684Python\u5e93\uff0c\u7528\u4e8e\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u6570\u636e\u3002\u5b83\u63d0\u4f9b\u4e86\u4e00\u4e9b\u7b80\u5355\u7684\u65b9\u6cd5\u6765\u5bfc\u822a\u3001\u641c\u7d22\u548c\u4fee\u6539\u89e3\u6790\u7684\u6811\u5f62\u7ed3\u6784\u3002<\/strong>\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5BeautifulSoup\u548crequests\u5e93\uff0c\u53ef\u4ee5\u901a\u8fc7pip\u547d\u4ee4\u5b8c\u6210\u5b89\u88c5\uff1a<code>pip install beautifulsoup4 requests<\/code>\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u5e76\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<p>url = &quot;http:\/\/example.com&quot;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>html_content = response.content<\/p>\n<p>soup = BeautifulSoup(html_content, &quot;html.parser&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u8fd9\u6bb5\u4ee3\u7801\uff0c\u6211\u4eec\u6210\u529f\u83b7\u53d6\u4e86\u7f51\u9875\u5185\u5bb9\uff0c\u5e76\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u53ef\u4ee5\u5229\u7528BeautifulSoup\u63d0\u4f9b\u7684\u65b9\u6cd5\u8fdb\u884c\u6570\u636e\u63d0\u53d6\u3002\u4f8b\u5982\uff0c\u5047\u8bbe\u6211\u4eec\u8981\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u6240\u6709\u94fe\u63a5\uff0c\u53ef\u4ee5\u4f7f\u7528<code>soup.find_all<\/code>\u65b9\u6cd5\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>\u8fd9\u6bb5\u4ee3\u7801\u5c06\u63d0\u53d6\u9875\u9762\u4e2d\u6240\u6709\u7684<code>&lt;a&gt;<\/code>\u6807\u7b7e\uff0c\u5e76\u6253\u5370\u51fa\u6bcf\u4e2a\u6807\u7b7e\u7684<code>href<\/code>\u5c5e\u6027\uff0c\u5373\u94fe\u63a5\u5730\u5740\u3002\u901a\u8fc7\u8fd9\u79cd\u65b9\u5f0f\uff0c\u6211\u4eec\u53ef\u4ee5\u8f7b\u677e\u5730\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u5404\u79cd\u6570\u636e\u3002<\/p>\n<\/p>\n<p><p>\u4e8c\u3001\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u5339\u914d\u6570\u636e\u3001\u6e05\u6d17\u4e0e\u8fc7\u6ee4<br \/>\u9664\u4e86\u4f7f\u7528BeautifulSoup\u7b49\u5de5\u5177\u5305\uff0c\u6b63\u5219\u8868\u8fbe\u5f0f\u4e5f\u662f\u5206\u6790\u548c\u63d0\u53d6\u7f51\u9875\u6570\u636e\u7684\u91cd\u8981\u5de5\u5177\u3002\u6b63\u5219\u8868\u8fbe\u5f0f\u53ef\u4ee5\u7528\u6765\u5339\u914d\u7279\u5b9a\u683c\u5f0f\u7684\u6570\u636e\uff0c\u5982\u7535\u8bdd\u53f7\u7801\u3001\u7535\u5b50\u90ae\u4ef6\u5730\u5740\u3001\u65e5\u671f\u7b49\u3002Python\u63d0\u4f9b\u4e86re\u6a21\u5757\uff0c\u7528\u4e8e\u5904\u7406\u6b63\u5219\u8868\u8fbe\u5f0f\u3002<\/p>\n<\/p>\n<p><p>\u5728\u7f51\u9875\u5206\u6790\u4e2d\uff0c\u5e38\u5e38\u9700\u8981\u5bf9\u63d0\u53d6\u7684\u6570\u636e\u8fdb\u884c\u6e05\u6d17\u4e0e\u8fc7\u6ee4\uff0c\u4ee5\u786e\u4fdd\u6570\u636e\u7684\u51c6\u786e\u6027\u548c\u5b8c\u6574\u6027\u3002\u6b63\u5219\u8868\u8fbe\u5f0f\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u5b9e\u73b0\u8fd9\u4e00\u76ee\u6807\u3002\u4f8b\u5982\uff0c\u6211\u4eec\u53ef\u80fd\u60f3\u8981\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u6240\u6709\u4ee5\u6570\u5b57\u5f00\u5934\u7684\u6bb5\u843d\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import re<\/p>\n<p>paragraphs = soup.find_all(&#39;p&#39;)<\/p>\n<p>numbered_paragraphs = [p.get_text() for p in paragraphs if re.match(r&#39;^\\d&#39;, p.get_text())]<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u6bb5\u4ee3\u7801\u901a\u8fc7\u6b63\u5219\u8868\u8fbe\u5f0f\u5339\u914d\u4ee5\u6570\u5b57\u5f00\u5934\u7684\u6bb5\u843d\uff0c\u5e76\u5c06\u5176\u63d0\u53d6\u5230\u5217\u8868\u4e2d\u3002\u901a\u8fc7\u8fd9\u79cd\u65b9\u5f0f\uff0c\u6211\u4eec\u53ef\u4ee5\u5bf9\u63d0\u53d6\u7684\u6570\u636e\u8fdb\u884c\u6709\u6548\u7684\u6e05\u6d17\u4e0e\u8fc7\u6ee4\u3002<\/p>\n<\/p>\n<p><p>\u4e09\u3001\u5904\u7406\u52a8\u6001\u52a0\u8f7d\u7684\u5185\u5bb9\u3001\u4f7f\u7528Selenium\u6a21\u62df\u6d4f\u89c8\u5668<br \/>\u5728\u73b0\u4ee3\u7f51\u9875\u4e2d\uff0c\u52a8\u6001\u52a0\u8f7d\u7684\u5185\u5bb9\u8d8a\u6765\u8d8a\u666e\u904d\u3002\u8fd9\u79cd\u5185\u5bb9\u901a\u5e38\u901a\u8fc7JavaScript\u5728\u9875\u9762\u52a0\u8f7d\u540e\u52a8\u6001\u751f\u6210\uff0c\u56e0\u6b64\u4e0d\u80fd\u901a\u8fc7\u7b80\u5355\u7684HTML\u89e3\u6790\u83b7\u53d6\u3002\u4e3a\u4e86\u89e3\u51b3\u8fd9\u4e2a\u95ee\u9898\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Selenium\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u3002<\/p>\n<\/p>\n<p><p>Selenium\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u5de5\u5177\uff0c\u5141\u8bb8\u6211\u4eec\u901a\u8fc7\u4ee3\u7801\u63a7\u5236\u6d4f\u89c8\u5668\u3002\u5b83\u652f\u6301\u591a\u79cd\u6d4f\u89c8\u5668\uff0c\u5982Chrome\u3001Firefox\u7b49\uff0c\u53ef\u4ee5\u6267\u884c\u590d\u6742\u7684\u7528\u6237\u4ea4\u4e92\u64cd\u4f5c\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f7f\u7528Selenium\u63d0\u53d6\u52a8\u6001\u5185\u5bb9\u7684\u793a\u4f8b\uff1a<\/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(&quot;http:\/\/example.com&quot;)<\/p>\n<h2><strong>\u7b49\u5f85\u52a8\u6001\u5185\u5bb9\u52a0\u8f7d\u5b8c\u6210<\/strong><\/h2>\n<p>dynamic_content = driver.find_element_by_id(&quot;dynamic-content&quot;)<\/p>\n<p>print(dynamic_content.text)<\/p>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7Selenium\uff0c\u6211\u4eec\u53ef\u4ee5\u52a0\u8f7d\u7f51\u9875\u5e76\u7b49\u5f85\u52a8\u6001\u5185\u5bb9\u52a0\u8f7d\u5b8c\u6210\uff0c\u7136\u540e\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\u3002\u8fd9\u5bf9\u4e8e\u5904\u7406\u590d\u6742\u7684\u52a8\u6001\u7f51\u9875\u7279\u522b\u6709\u7528\u3002<\/p>\n<\/p>\n<p><p>\u56db\u3001\u5206\u6790\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6\u3001\u9075\u5b88\u722c\u866b\u793c\u4eea<br \/>\u5728\u8fdb\u884c\u7f51\u9875\u722c\u53d6\u65f6\uff0c\u6211\u4eec\u5e94\u9075\u5faa\u7f51\u7edc\u722c\u866b\u7684\u57fa\u672c\u793c\u4eea\uff0c\u5c0a\u91cd\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6\u3002robots.txt\u6587\u4ef6\u662f\u7f51\u7ad9\u7ba1\u7406\u5458\u7528\u6765\u544a\u8bc9\u722c\u866b\u54ea\u4e9b\u9875\u9762\u53ef\u4ee5\u6293\u53d6\uff0c\u54ea\u4e9b\u9875\u9762\u4e0d\u53ef\u4ee5\u6293\u53d6\u7684\u6587\u4ef6\u3002\u5728\u5f00\u59cb\u722c\u53d6\u4e4b\u524d\uff0c\u6211\u4eec\u5e94\u8be5\u5148\u68c0\u67e5\u8be5\u6587\u4ef6\u3002<\/p>\n<\/p>\n<p><p>\u53ef\u4ee5\u4f7f\u7528requests\u5e93\u83b7\u53d6robots.txt\u6587\u4ef6\uff0c\u5e76\u89e3\u6790\u5176\u4e2d\u7684\u89c4\u5219\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">robots_url = &quot;http:\/\/example.com\/robots.txt&quot;<\/p>\n<p>response = requests.get(robots_url)<\/p>\n<p>print(response.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u5206\u6790robots.txt\u6587\u4ef6\uff0c\u6211\u4eec\u53ef\u4ee5\u786e\u5b9a\u54ea\u4e9b\u9875\u9762\u662f\u5141\u8bb8\u722c\u53d6\u7684\u3002\u540c\u65f6\uff0c\u6211\u4eec\u4e5f\u5e94\u9075\u5faa\u5176\u4ed6\u722c\u866b\u793c\u4eea\uff0c\u5982\u8bbe\u7f6e\u5408\u7406\u7684\u8bf7\u6c42\u9891\u7387\uff0c\u907f\u514d\u5bf9\u76ee\u6807\u7f51\u7ad9\u9020\u6210\u8fc7\u5927\u8d1f\u62c5\u3002<\/p>\n<\/p>\n<p><p>\u4e94\u3001\u5904\u7406\u53cd\u722c\u866b\u63aa\u65bd\u3001\u4f7f\u7528\u4ee3\u7406IP\u3001\u968f\u673aUser-Agent<br \/>\u8bb8\u591a\u7f51\u7ad9\u4f1a\u91c7\u53d6\u53cd\u722c\u866b\u63aa\u65bd\u6765\u963b\u6b62\u81ea\u52a8\u5316\u7684\u6570\u636e\u6293\u53d6\u3002\u8fd9\u4e9b\u63aa\u65bd\u53ef\u80fd\u5305\u62ecIP\u5c01\u9501\u3001\u9a8c\u8bc1\u7801\u9a8c\u8bc1\u7b49\u3002\u4e3a\u4e86\u7ed5\u8fc7\u8fd9\u4e9b\u9650\u5236\uff0c\u6211\u4eec\u53ef\u4ee5\u91c7\u53d6\u4e00\u4e9b\u7b56\u7565\uff0c\u5982\u4f7f\u7528\u4ee3\u7406IP\u548c\u968f\u673aUser-Agent\u3002<\/p>\n<\/p>\n<p><p>\u4ee3\u7406IP\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u9690\u85cf\u771f\u5b9e\u7684IP\u5730\u5740\uff0c\u4ece\u800c\u907f\u514d\u56e0\u9891\u7e41\u8bf7\u6c42\u88ab\u5c01\u7981\u3002\u53ef\u4ee5\u4f7f\u7528\u7b2c\u4e09\u65b9\u4ee3\u7406\u670d\u52a1\uff0c\u6216\u901a\u8fc7\u7f16\u7a0b\u52a8\u6001\u5207\u6362\u4ee3\u7406\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">proxies = {<\/p>\n<p>    &quot;http&quot;: &quot;http:\/\/10.10.1.10:3128&quot;,<\/p>\n<p>    &quot;https&quot;: &quot;http:\/\/10.10.1.10:1080&quot;,<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, proxies=proxies)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u540c\u65f6\uff0c\u4f7f\u7528\u968f\u673aUser-Agent\u53ef\u4ee5\u6a21\u62df\u4e0d\u540c\u7684\u6d4f\u89c8\u5668\u548c\u8bbe\u5907\u8bf7\u6c42\uff0c\u589e\u52a0\u722c\u866b\u7684\u9690\u853d\u6027\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import random<\/p>\n<p>user_agents = [<\/p>\n<p>    &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>    &quot;Mozilla\/5.0 (Macintosh; Intel Mac OS X 10_13_5) AppleWebKit\/605.1.15 (KHTML, like Gecko) Version\/11.1.1 Safari\/605.1.15&quot;,<\/p>\n<p>    # \u66f4\u591aUser-Agent<\/p>\n<p>]<\/p>\n<p>headers = {<\/p>\n<p>    &quot;User-Agent&quot;: random.choice(user_agents)<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, headers=headers)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u8fd9\u4e9b\u6280\u672f\u624b\u6bb5\uff0c\u6211\u4eec\u53ef\u4ee5\u6709\u6548\u7ed5\u8fc7\u4e00\u4e9b\u5e38\u89c1\u7684\u53cd\u722c\u866b\u63aa\u65bd\u3002<\/p>\n<\/p>\n<p><p>\u516d\u3001\u6570\u636e\u5b58\u50a8\u4e0e\u7ba1\u7406\u3001\u4f7f\u7528\u6570\u636e\u5e93\u548c\u6587\u4ef6\u7cfb\u7edf<br \/>\u5728\u5b8c\u6210\u6570\u636e\u63d0\u53d6\u540e\uff0c\u5982\u4f55\u6709\u6548\u5730\u5b58\u50a8\u548c\u7ba1\u7406\u6570\u636e\u4e5f\u662f\u4e00\u4e2a\u91cd\u8981\u7684\u95ee\u9898\u3002Python\u63d0\u4f9b\u4e86\u591a\u79cd\u6570\u636e\u5b58\u50a8\u9009\u9879\uff0c\u5982\u6570\u636e\u5e93\u548c\u6587\u4ef6\u7cfb\u7edf\u3002<\/p>\n<\/p>\n<p><p>\u5bf9\u4e8e\u7ed3\u6784\u5316\u6570\u636e\uff0c\u4f7f\u7528\u6570\u636e\u5e93\u5b58\u50a8\u662f\u4e00\u4e2a\u4e0d\u9519\u7684\u9009\u62e9\u3002\u5e38\u7528\u7684\u6570\u636e\u5e93\u5305\u62ecSQLite\u3001MySQL\u3001PostgreSQL\u7b49\u3002\u53ef\u4ee5\u4f7f\u7528Python\u7684\u6570\u636e\u5e93\u8fde\u63a5\u5e93\uff0c\u5982sqlite3\u3001pymysql\u7b49\uff0c\u5c06\u6570\u636e\u5b58\u50a8\u5230\u6570\u636e\u5e93\u4e2d\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import sqlite3<\/p>\n<p>conn = sqlite3.connect(&quot;data.db&quot;)<\/p>\n<p>cursor = conn.cursor()<\/p>\n<p>cursor.execute(&quot;CREATE TABLE IF NOT EXISTS data (id INTEGER PRIMARY KEY, content TEXT)&quot;)<\/p>\n<p>cursor.execute(&quot;INSERT INTO data (content) VALUES (?)&quot;, (data,))<\/p>\n<p>conn.commit()<\/p>\n<p>conn.close()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5bf9\u4e8e\u975e\u7ed3\u6784\u5316\u6570\u636e\u6216\u5c0f\u89c4\u6a21\u6570\u636e\uff0c\u53ef\u4ee5\u9009\u62e9\u4f7f\u7528\u6587\u4ef6\u7cfb\u7edf\u5b58\u50a8\uff0c\u5982CSV\u3001JSON\u7b49\u683c\u5f0f\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import json<\/p>\n<p>with open(&quot;data.json&quot;, &quot;w&quot;) as f:<\/p>\n<p>    json.dump(data, f)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u9009\u62e9\u5408\u9002\u7684\u5b58\u50a8\u65b9\u5f0f\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u66f4\u597d\u5730\u7ba1\u7406\u548c\u5229\u7528\u722c\u53d6\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<p><p>\u4e03\u3001\u6570\u636e\u5206\u6790\u4e0e\u53ef\u89c6\u5316\u3001\u5229\u7528Pandas\u548cMatplotlib<br \/>\u5728\u5b8c\u6210\u6570\u636e\u63d0\u53d6\u548c\u5b58\u50a8\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u8fdb\u4e00\u6b65\u5bf9\u6570\u636e\u8fdb\u884c\u5206\u6790\u548c\u53ef\u89c6\u5316\u3002Pandas\u548cMatplotlib\u662fPython\u4e2d\u5e38\u7528\u7684\u6570\u636e\u5206\u6790\u4e0e\u53ef\u89c6\u5316\u5de5\u5177\u3002<\/p>\n<\/p>\n<p><p>Pandas\u63d0\u4f9b\u4e86\u5f3a\u5927\u7684\u6570\u636e\u5904\u7406\u529f\u80fd\uff0c\u53ef\u4ee5\u8f7b\u677e\u8fdb\u884c\u6570\u636e\u6e05\u6d17\u3001\u8f6c\u6362\u548c\u5206\u6790\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import pandas as pd<\/p>\n<p>df = pd.DataFrame(data)<\/p>\n<p>print(df.describe())<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>Matplotlib\u5219\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u751f\u6210\u5404\u79cd\u56fe\u8868\uff0c\u76f4\u89c2\u5730\u5c55\u793a\u6570\u636e\u5206\u6790\u7ed3\u679c\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import matplotlib.pyplot as plt<\/p>\n<p>df.plot(kind=&quot;bar&quot;)<\/p>\n<p>plt.show()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u6570\u636e\u5206\u6790\u4e0e\u53ef\u89c6\u5316\uff0c\u6211\u4eec\u53ef\u4ee5\u6df1\u5165\u7406\u89e3\u6570\u636e\uff0c\u6316\u6398\u51fa\u6f5c\u5728\u7684\u4fe1\u606f\u548c\u4ef7\u503c\u3002<\/p>\n<\/p>\n<p><p>\u516b\u3001\u5e38\u89c1\u95ee\u9898\u4e0e\u89e3\u51b3\u65b9\u6848\u3001\u63d0\u9ad8\u722c\u866b\u6548\u7387\u548c\u7a33\u5b9a\u6027<br \/>\u5728\u5b9e\u9645\u64cd\u4f5c\u4e2d\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u5404\u79cd\u95ee\u9898\uff0c\u5982\u8fde\u63a5\u8d85\u65f6\u3001\u6570\u636e\u4e22\u5931\u7b49\u3002\u4e3a\u4e86\u89e3\u51b3\u8fd9\u4e9b\u95ee\u9898\uff0c\u63d0\u9ad8\u722c\u866b\u7684\u6548\u7387\u548c\u7a33\u5b9a\u6027\uff0c\u6211\u4eec\u53ef\u4ee5\u91c7\u53d6\u4ee5\u4e0b\u63aa\u65bd\uff1a<\/p>\n<\/p>\n<ol>\n<li><strong>\u8bbe\u7f6e\u8bf7\u6c42\u91cd\u8bd5\u673a\u5236<\/strong>\uff1a\u901a\u8fc7\u8bbe\u7f6e\u91cd\u8bd5\u6b21\u6570\u548c\u65f6\u95f4\u95f4\u9694\uff0c\u53ef\u4ee5\u5728\u7f51\u7edc\u4e0d\u7a33\u5b9a\u65f6\u589e\u52a0\u8bf7\u6c42\u7684\u6210\u529f\u7387\u3002<\/li>\n<\/ol>\n<p><pre><code class=\"language-python\">import time<\/p>\n<p>max_retries = 3<\/p>\n<p>for i in range(max_retries):<\/p>\n<p>    try:<\/p>\n<p>        response = requests.get(url, timeout=5)<\/p>\n<p>        break<\/p>\n<p>    except requests.exceptions.RequestException as e:<\/p>\n<p>        print(f&quot;Attempt {i+1} f<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>led: {e}&quot;)<\/p>\n<p>        time.sleep(2)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<ol start=\"2\">\n<li><strong>\u4f7f\u7528\u5f02\u6b65\u8bf7\u6c42<\/strong>\uff1a\u901a\u8fc7\u5f02\u6b65\u7f16\u7a0b\uff0c\u53ef\u4ee5\u540c\u65f6\u5904\u7406\u591a\u4e2a\u8bf7\u6c42\uff0c\u63d0\u9ad8\u722c\u866b\u7684\u901f\u5ea6\u3002\u53ef\u4ee5\u4f7f\u7528aiohttp\u5e93\u5b9e\u73b0\u5f02\u6b65\u8bf7\u6c42\uff1a<\/li>\n<\/ol>\n<p><pre><code class=\"language-python\">import aiohttp<\/p>\n<p>import asyncio<\/p>\n<p>async def fetch(url):<\/p>\n<p>    async with aiohttp.ClientSession() as session:<\/p>\n<p>        async with session.get(url) as response:<\/p>\n<p>            return await response.text()<\/p>\n<p>async def main():<\/p>\n<p>    urls = [&quot;http:\/\/example.com\/1&quot;, &quot;http:\/\/example.com\/2&quot;]<\/p>\n<p>    tasks = [fetch(url) for url in urls]<\/p>\n<p>    results = await asyncio.gather(*tasks)<\/p>\n<p>    print(results)<\/p>\n<p>asyncio.run(main())<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u8fd9\u4e9b\u6280\u672f\u624b\u6bb5\uff0c\u6211\u4eec\u53ef\u4ee5\u6709\u6548\u63d0\u5347\u722c\u866b\u7684\u6548\u7387\u548c\u7a33\u5b9a\u6027\uff0c\u786e\u4fdd\u6570\u636e\u6293\u53d6\u7684\u6210\u529f\u7387\u548c\u5b8c\u6574\u6027\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u9009\u62e9\u5408\u9002\u7684\u5e93\u6765\u8fdb\u884c\u7f51\u9875\u5206\u6790\uff1f<\/strong><br \/>\u5728\u8fdb\u884c\u7f51\u9875\u5206\u6790\u65f6\uff0c\u53ef\u4ee5\u9009\u62e9\u591a\u79cdPython\u5e93\uff0c\u5982Beautiful Soup\u3001Scrapy\u548clxml\u7b49\u3002Beautiful Soup\u9002\u5408\u8fdb\u884c\u7b80\u5355\u7684HTML\u89e3\u6790\uff0cScrapy\u5219\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u6846\u67b6\uff0c\u9002\u5408\u5904\u7406\u5927\u578b\u722c\u866b\u9879\u76ee\u3002lxml\u4ee5\u5176\u89e3\u6790\u901f\u5ea6\u5feb\u548c\u529f\u80fd\u5f3a\u5927\u800c\u95fb\u540d\u3002\u6839\u636e\u9879\u76ee\u7684\u590d\u6742\u6027\u548c\u9700\u6c42\uff0c\u9009\u62e9\u5408\u9002\u7684\u5de5\u5177\u53ef\u4ee5\u63d0\u9ad8\u5f00\u53d1\u6548\u7387\u3002<\/p>\n<p><strong>\u5728\u5206\u6790\u7f51\u9875\u65f6\uff0c\u5982\u4f55\u5904\u7406JavaScript\u751f\u6210\u7684\u5185\u5bb9\uff1f<\/strong><br \/>\u8bb8\u591a\u73b0\u4ee3\u7f51\u9875\u4f7f\u7528JavaScript\u52a8\u6001\u52a0\u8f7d\u5185\u5bb9\uff0c\u8fd9\u53ef\u80fd\u4f1a\u5bfc\u81f4\u4f20\u7edf\u7684\u722c\u866b\u5de5\u5177\u65e0\u6cd5\u83b7\u53d6\u6240\u9700\u6570\u636e\u3002\u5bf9\u6b64\uff0c\u53ef\u4ee5\u4f7f\u7528Selenium\u6216Playwright\u7b49\u5de5\u5177\uff0c\u8fd9\u4e9b\u5de5\u5177\u80fd\u591f\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u7b49\u5f85\u9875\u9762\u5b8c\u5168\u52a0\u8f7d\u540e\u518d\u63d0\u53d6\u4fe1\u606f\u3002\u901a\u8fc7\u8fd9\u4e9b\u5de5\u5177\uff0c\u53ef\u4ee5\u6709\u6548\u6293\u53d6\u52a8\u6001\u751f\u6210\u7684\u6570\u636e\u3002<\/p>\n<p><strong>\u5982\u4f55\u907f\u514d\u5728\u722c\u866b\u5206\u6790\u4e2d\u88ab\u7f51\u7ad9\u5c01\u7981\uff1f<\/strong><br \/>\u4e3a\u4e86\u964d\u4f4e\u88ab\u7f51\u7ad9\u5c01\u7981\u7684\u98ce\u9669\uff0c\u53ef\u4ee5\u91c7\u53d6\u4e00\u4e9b\u63aa\u65bd\u3002\u9996\u5148\uff0c\u63a7\u5236\u8bf7\u6c42\u9891\u7387\uff0c\u907f\u514d\u53d1\u9001\u8fc7\u4e8e\u9891\u7e41\u7684\u8bf7\u6c42\u3002\u5176\u6b21\uff0c\u4f7f\u7528\u4ee3\u7406IP\u8f6e\u6362\u6765\u9690\u85cf\u771f\u5b9eIP\u5730\u5740\u3002\u6b64\u5916\uff0c\u8bbe\u7f6e\u5408\u9002\u7684User-Agent\u5934\u4fe1\u606f\uff0c\u8ba9\u722c\u866b\u770b\u8d77\u6765\u50cf\u662f\u666e\u901a\u7528\u6237\u8bbf\u95ee\u3002\u9075\u5b88robots.txt\u6587\u4ef6\u4e2d\u7684\u722c\u866b\u89c4\u5219\u4e5f\u662f\u7ef4\u62a4\u826f\u597d\u722c\u866b\u4e60\u60ef\u7684\u91cd\u8981\u6b65\u9aa4\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u4e00\u3001\u89e3\u6790HTML\u7ed3\u6784\u3001\u63d0\u53d6\u76ee\u6807\u6570\u636e\u3001\u4f7f\u7528\u5de5\u5177\u5305\u5982BeautifulSoupPython\u722c\u866b\u5206\u6790\u9875\u9762\u7684\u6838\u5fc3\u5728\u4e8e\u89e3 [&hellip;]","protected":false},"author":3,"featured_media":1000789,"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\/1000774"}],"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=1000774"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1000774\/revisions"}],"predecessor-version":[{"id":1000792,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1000774\/revisions\/1000792"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1000789"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1000774"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1000774"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1000774"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}