{"id":1080239,"date":"2025-01-08T12:28:17","date_gmt":"2025-01-08T04:28:17","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1080239.html"},"modified":"2025-01-08T12:28:19","modified_gmt":"2025-01-08T04:28:19","slug":"python%e5%a6%82%e4%bd%95%e7%88%ac%e5%8f%96%e4%b8%80%e4%b8%aa%e7%bd%91%e9%a1%b5-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1080239.html","title":{"rendered":"python\u5982\u4f55\u722c\u53d6\u4e00\u4e2a\u7f51\u9875"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/24182855\/6aa87061-f348-4a1e-87e2-142015547a05.webp\" alt=\"python\u5982\u4f55\u722c\u53d6\u4e00\u4e2a\u7f51\u9875\" \/><\/p>\n<p><p> <strong>\u4f7f\u7528Python\u722c\u53d6\u7f51\u9875\u7684\u6838\u5fc3\u6b65\u9aa4\u5305\u62ec\uff1a\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u3001\u63d0\u53d6\u6570\u636e\u3001\u5904\u7406\u6570\u636e\u3002\u5176\u4e2d\uff0c\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u662f\u5173\u952e\u6b65\u9aa4\u3002<\/strong> \u4f8b\u5982\uff0c\u4f7f\u7528<code>BeautifulSoup<\/code>\u5e93\u53ef\u4ee5\u65b9\u4fbf\u5730\u89e3\u6790HTML\u6587\u6863\uff0c\u627e\u5230\u6240\u9700\u7684\u6807\u7b7e\u548c\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><p>\u4e00\u3001\u53d1\u9001HTTP\u8bf7\u6c42<\/p>\n<\/p>\n<p><p>\u5728\u8fdb\u884c\u7f51\u9875\u722c\u53d6\u65f6\uff0c\u7b2c\u4e00\u6b65\u662f\u53d1\u9001HTTP\u8bf7\u6c42\u4ee5\u83b7\u53d6\u7f51\u9875\u7684\u5185\u5bb9\u3002Python\u4e2d\u7684<code>requests<\/code>\u5e93\u662f\u4e00\u4e2a\u975e\u5e38\u6d41\u884c\u4e14\u6613\u4e8e\u4f7f\u7528\u7684\u5e93\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u53d1\u9001HTTP\u8bf7\u6c42\u5e76\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;https:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>if response.status_code == 200:<\/p>\n<p>    page_content = response.text<\/p>\n<p>else:<\/p>\n<p>    print(f&quot;F<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>led to retrieve the page. Status code: {response.status_code}&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e8c\u3001\u89e3\u6790\u7f51\u9875\u5185\u5bb9<\/p>\n<\/p>\n<p><p>\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u540e\uff0c\u9700\u8981\u89e3\u6790HTML\u6587\u6863\u4ee5\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\u3002<code>BeautifulSoup<\/code>\u5e93\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u5de5\u5177\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u89e3\u6790HTML\u6587\u6863\u5e76\u63d0\u53d6\u6570\u636e\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>soup = BeautifulSoup(page_content, &#39;html.parser&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e09\u3001\u63d0\u53d6\u6570\u636e<\/p>\n<\/p>\n<p><p>\u89e3\u6790HTML\u6587\u6863\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528<code>BeautifulSoup<\/code>\u63d0\u4f9b\u7684\u5404\u79cd\u65b9\u6cd5\u6765\u67e5\u627e\u548c\u63d0\u53d6\u6570\u636e\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u4f7f\u7528<code>find<\/code>\u548c<code>find_all<\/code>\u65b9\u6cd5\u67e5\u627e\u7279\u5b9a\u7684\u6807\u7b7e\u548c\u5c5e\u6027\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u67e5\u627e\u6240\u6709\u7684\u6807\u9898\u6807\u7b7e<\/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>\u56db\u3001\u5904\u7406\u6570\u636e<\/p>\n<\/p>\n<p><p>\u63d0\u53d6\u6570\u636e\u540e\uff0c\u53ef\u4ee5\u6839\u636e\u9700\u8981\u8fdb\u4e00\u6b65\u5904\u7406\u6570\u636e\u3002\u4f8b\u5982\uff0c\u5c06\u6570\u636e\u4fdd\u5b58\u5230\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\uff0c\u6216\u8005\u5bf9\u6570\u636e\u8fdb\u884c\u6e05\u6d17\u548c\u8f6c\u6362\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u5c06\u63d0\u53d6\u7684\u6570\u636e\u4fdd\u5b58\u5230\u6587\u4ef6\u4e2d<\/p>\n<p>with open(&#39;titles.txt&#39;, &#39;w&#39;) as file:<\/p>\n<p>    for title in titles:<\/p>\n<p>        file.write(title.get_text() + &#39;\\n&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e94\u3001\u5904\u7406\u53cd\u722c\u673a\u5236<\/p>\n<\/p>\n<p><p>\u8bb8\u591a\u7f51\u7ad9\u90fd\u6709\u53cd\u722c\u673a\u5236\uff0c\u4ee5\u9632\u6b62\u81ea\u52a8\u5316\u811a\u672c\u9891\u7e41\u8bbf\u95ee\u3002\u5728\u8fdb\u884c\u7f51\u9875\u722c\u53d6\u65f6\uff0c\u9700\u8981\u9075\u5b88\u7f51\u7ad9\u7684<code>robots.txt<\/code>\u534f\u8bae\uff0c\u5e76\u907f\u514d\u9891\u7e41\u53d1\u9001\u8bf7\u6c42\u3002\u53ef\u4ee5\u901a\u8fc7\u6dfb\u52a0\u5ef6\u8fdf\u548c\u8bbe\u7f6e\u8bf7\u6c42\u5934\u6765\u51cf\u5c11\u88ab\u68c0\u6d4b\u548c\u5c01\u7981\u7684\u98ce\u9669\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import time<\/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<h2><strong>\u6dfb\u52a0\u5ef6\u8fdf<\/strong><\/h2>\n<p>time.sleep(2)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u516d\u3001\u5904\u7406\u52a8\u6001\u7f51\u9875<\/p>\n<\/p>\n<p><p>\u4e00\u4e9b\u7f51\u9875\u5185\u5bb9\u662f\u901a\u8fc7JavaScript\u52a8\u6001\u52a0\u8f7d\u7684\uff0c\u4f7f\u7528\u4f20\u7edf\u7684HTTP\u8bf7\u6c42\u65e0\u6cd5\u83b7\u53d6\u5b8c\u6574\u5185\u5bb9\u3002\u53ef\u4ee5\u4f7f\u7528<code>Selenium<\/code>\u5e93\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u52a0\u8f7d\u52a8\u6001\u5185\u5bb9\u5e76\u63d0\u53d6\u6570\u636e\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<h2><strong>\u8bbe\u7f6e\u6d4f\u89c8\u5668\u9a71\u52a8\u8def\u5f84<\/strong><\/h2>\n<p>driver_path = &#39;\/path\/to\/chromedriver&#39;<\/p>\n<p>driver = webdriver.Chrome(executable_path=driver_path)<\/p>\n<p>driver.get(url)<\/p>\n<p>page_content = driver.page_source<\/p>\n<p>driver.quit()<\/p>\n<p>soup = BeautifulSoup(page_content, &#39;html.parser&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e03\u3001\u5904\u7406\u5206\u9875<\/p>\n<\/p>\n<p><p>\u8bb8\u591a\u7f51\u7ad9\u7684\u6570\u636e\u5206\u5e03\u5728\u591a\u4e2a\u9875\u9762\u4e0a\uff0c\u9700\u5904\u7406\u5206\u9875\u4ee5\u83b7\u53d6\u6240\u6709\u6570\u636e\u3002\u53ef\u4ee5\u901a\u8fc7\u5206\u6790\u5206\u9875\u6309\u94ae\u7684\u94fe\u63a5\u6216\u8868\u5355\u53c2\u6570\uff0c\u7f16\u5199\u5faa\u73af\u6765\u83b7\u53d6\u6bcf\u4e00\u9875\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">base_url = &#39;https:\/\/example.com\/page\/&#39;<\/p>\n<p>for page in range(1, 11):<\/p>\n<p>    url = base_url + str(page)<\/p>\n<p>    response = requests.get(url, headers=headers)<\/p>\n<p>    if response.status_code == 200:<\/p>\n<p>        page_content = response.text<\/p>\n<p>        soup = BeautifulSoup(page_content, &#39;html.parser&#39;)<\/p>\n<p>        # \u63d0\u53d6\u5e76\u5904\u7406\u6570\u636e<\/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>        time.sleep(2)<\/p>\n<p>    else:<\/p>\n<p>        print(f&quot;Failed to retrieve page {page}. Status code: {response.status_code}&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u516b\u3001\u4fdd\u5b58\u6570\u636e<\/p>\n<\/p>\n<p><p>\u722c\u53d6\u7684\u6570\u636e\u53ef\u4ee5\u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\uff0c\u4ee5\u4fbf\u540e\u7eed\u5206\u6790\u548c\u5904\u7406\u3002\u4e0b\u9762\u662f\u5c06\u6570\u636e\u4fdd\u5b58\u5230CSV\u6587\u4ef6\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import csv<\/p>\n<h2><strong>\u63d0\u53d6\u6570\u636e<\/strong><\/h2>\n<p>titles = [title.get_text() for title in soup.find_all(&#39;h1&#39;)]<\/p>\n<h2><strong>\u4fdd\u5b58\u5230CSV\u6587\u4ef6<\/strong><\/h2>\n<p>with open(&#39;titles.csv&#39;, &#39;w&#39;, newline=&#39;&#39;) as file:<\/p>\n<p>    writer = csv.writer(file)<\/p>\n<p>    writer.writerow([&#39;Title&#39;])<\/p>\n<p>    for title in titles:<\/p>\n<p>        writer.writerow([title])<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e5d\u3001\u5f02\u5e38\u5904\u7406<\/p>\n<\/p>\n<p><p>\u5728\u8fdb\u884c\u7f51\u9875\u722c\u53d6\u65f6\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u5404\u79cd\u5f02\u5e38\u60c5\u51b5\uff0c\u5982\u7f51\u7edc\u95ee\u9898\u3001\u7f51\u9875\u7ed3\u6784\u53d8\u5316\u7b49\u3002\u9700\u8981\u7f16\u5199\u5065\u58ee\u7684\u4ee3\u7801\u6765\u5904\u7406\u8fd9\u4e9b\u5f02\u5e38\uff0c\u786e\u4fdd\u7a0b\u5e8f\u80fd\u591f\u7a33\u5b9a\u8fd0\u884c\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">try:<\/p>\n<p>    response = requests.get(url, headers=headers)<\/p>\n<p>    response.raise_for_status()<\/p>\n<p>    page_content = response.text<\/p>\n<p>    soup = BeautifulSoup(page_content, &#39;html.parser&#39;)<\/p>\n<p>except requests.exceptions.RequestException as e:<\/p>\n<p>    print(f&quot;Request failed: {e}&quot;)<\/p>\n<p>except Exception as e:<\/p>\n<p>    print(f&quot;An error occurred: {e}&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5341\u3001\u9075\u5b88\u6cd5\u5f8b\u548c\u9053\u5fb7\u89c4\u8303<\/p>\n<\/p>\n<p><p>\u5728\u8fdb\u884c\u7f51\u9875\u722c\u53d6\u65f6\uff0c\u5e94\u9075\u5b88\u6cd5\u5f8b\u548c\u9053\u5fb7\u89c4\u8303\uff0c\u4e0d\u8981\u5bf9\u7f51\u7ad9\u670d\u52a1\u5668\u9020\u6210\u8fc7\u5927\u8d1f\u62c5\u6216\u4fb5\u72af\u4ed6\u4eba\u7684\u9690\u79c1\u548c\u7248\u6743\u3002\u53ef\u4ee5\u53c2\u8003\u7f51\u7ad9\u7684<code>robots.txt<\/code>\u6587\u4ef6\u4e86\u89e3\u5176\u722c\u53d6\u89c4\u5219\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u67e5\u770b\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6<\/p>\n<p>robots_url = &#39;https:\/\/example.com\/robots.txt&#39;<\/p>\n<p>response = requests.get(robots_url)<\/p>\n<p>print(response.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u603b\u7ed3\uff1a<\/p>\n<\/p>\n<p><p>\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u53ef\u4ee5\u4f7f\u7528Python\u722c\u53d6\u7f51\u9875\u5e76\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\u3002\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u6839\u636e\u5177\u4f53\u9700\u6c42\u548c\u7f51\u9875\u7ed3\u6784\uff0c\u53ef\u4ee5\u7075\u6d3b\u8c03\u6574\u548c\u4f18\u5316\u722c\u53d6\u7b56\u7565\u3002\u5e0c\u671b\u672c\u7bc7\u6587\u7ae0\u80fd\u5bf9\u4f60\u7406\u89e3\u548c\u638c\u63e1\u7f51\u9875\u722c\u53d6\u6280\u672f\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\u9002\u5408\u7684Python\u5e93\u8fdb\u884c\u7f51\u9875\u722c\u53d6\uff1f<\/strong><br \/>\u5728\u8fdb\u884c\u7f51\u9875\u722c\u53d6\u65f6\uff0c\u9009\u62e9\u5408\u9002\u7684\u5e93\u81f3\u5173\u91cd\u8981\u3002\u5e38\u7528\u7684Python\u5e93\u6709BeautifulSoup\u3001Scrapy\u548cRequests\u7b49\u3002BeautifulSoup\u9002\u5408\u89e3\u6790HTML\u548cXML\u6587\u6863\uff0cScrapy\u5219\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u722c\u866b\u6846\u67b6\uff0c\u9002\u5408\u8fdb\u884c\u5927\u89c4\u6a21\u722c\u53d6\uff0cRequests\u5219\u53ef\u4ee5\u7b80\u5316HTTP\u8bf7\u6c42\u7684\u53d1\u9001\u3002\u6839\u636e\u9879\u76ee\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u5de5\u5177\uff0c\u53ef\u4ee5\u63d0\u9ad8\u722c\u53d6\u6548\u7387\u548c\u7b80\u5316\u5f00\u53d1\u8fc7\u7a0b\u3002<\/p>\n<p><strong>\u5728\u722c\u53d6\u7f51\u9875\u65f6\u9700\u8981\u6ce8\u610f\u54ea\u4e9b\u6cd5\u5f8b\u548c\u9053\u5fb7\u95ee\u9898\uff1f<\/strong><br \/>\u5728\u8fdb\u884c\u7f51\u9875\u722c\u53d6\u65f6\uff0c\u52a1\u5fc5\u9075\u5faa\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6\u4e2d\u7684\u89c4\u5b9a\uff0c\u5c0a\u91cd\u7f51\u7ad9\u7684\u9690\u79c1\u653f\u7b56\u548c\u4f7f\u7528\u6761\u6b3e\u3002\u907f\u514d\u5bf9\u76ee\u6807\u7f51\u7ad9\u9020\u6210\u8fc7\u5927\u538b\u529b\uff0c\u63a7\u5236\u722c\u53d6\u901f\u5ea6\uff0c\u5c3d\u91cf\u4f7f\u7528\u5408\u7406\u7684\u8bf7\u6c42\u95f4\u9694\u3002\u6b64\u5916\uff0c\u786e\u4fdd\u4e0d\u722c\u53d6\u654f\u611f\u4fe1\u606f\u6216\u4fb5\u72af\u7248\u6743\u5185\u5bb9\uff0c\u4ee5\u514d\u5f15\u53d1\u6cd5\u5f8b\u7ea0\u7eb7\u3002<\/p>\n<p><strong>\u5982\u4f55\u5904\u7406\u7f51\u9875\u4e2d\u7684\u52a8\u6001\u5185\u5bb9\uff1f<\/strong><br \/>\u8bb8\u591a\u73b0\u4ee3\u7f51\u9875\u4f7f\u7528JavaScript\u52a8\u6001\u52a0\u8f7d\u5185\u5bb9\uff0c\u8fd9\u4f7f\u5f97\u4f20\u7edf\u7684\u722c\u866b\u65b9\u6cd5\u96be\u4ee5\u83b7\u53d6\u6240\u9700\u6570\u636e\u3002\u4e3a\u4e86\u89e3\u51b3\u8fd9\u4e2a\u95ee\u9898\uff0c\u53ef\u4ee5\u4f7f\u7528Selenium\u6216Playwright\u7b49\u5de5\u5177\uff0c\u5b83\u4eec\u53ef\u4ee5\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u5904\u7406\u52a8\u6001\u52a0\u8f7d\u7684\u5185\u5bb9\u3002\u901a\u8fc7\u8fd9\u4e9b\u5de5\u5177\uff0c\u53ef\u4ee5\u7b49\u5f85\u9875\u9762\u5b8c\u5168\u52a0\u8f7d\u540e\u518d\u63d0\u53d6\u6240\u9700\u6570\u636e\uff0c\u786e\u4fdd\u83b7\u53d6\u5230\u5b8c\u6574\u7684\u4fe1\u606f\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u4f7f\u7528Python\u722c\u53d6\u7f51\u9875\u7684\u6838\u5fc3\u6b65\u9aa4\u5305\u62ec\uff1a\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u3001\u63d0\u53d6\u6570\u636e\u3001\u5904\u7406\u6570\u636e\u3002\u5176\u4e2d\uff0c\u89e3\u6790\u7f51\u9875\u5185\u5bb9 [&hellip;]","protected":false},"author":3,"featured_media":1080247,"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\/1080239"}],"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=1080239"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1080239\/revisions"}],"predecessor-version":[{"id":1080252,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1080239\/revisions\/1080252"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1080247"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1080239"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1080239"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1080239"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}