{"id":1089294,"date":"2025-01-08T13:52:18","date_gmt":"2025-01-08T05:52:18","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1089294.html"},"modified":"2025-01-08T13:52:20","modified_gmt":"2025-01-08T05:52:20","slug":"python%e5%a6%82%e4%bd%95%e6%8a%93%e5%8f%96%e5%bd%bc%e5%b2%b8%e6%a1%8c%e9%9d%a2%e5%9b%be%e7%89%87-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1089294.html","title":{"rendered":"python\u5982\u4f55\u6293\u53d6\u5f7c\u5cb8\u684c\u9762\u56fe\u7247"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/24202305\/d33a28d6-351c-4bd2-b8c9-6218be284542.webp\" alt=\"python\u5982\u4f55\u6293\u53d6\u5f7c\u5cb8\u684c\u9762\u56fe\u7247\" \/><\/p>\n<p><p> <strong>Python\u6293\u53d6\u5f7c\u5cb8\u684c\u9762\u56fe\u7247\u7684\u65b9\u6cd5\u5305\u62ec\uff1a\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u3001\u63d0\u53d6\u56fe\u7247\u94fe\u63a5\u3001\u4f7f\u7528OS\u5e93\u4fdd\u5b58\u56fe\u7247\u3002<\/strong> \u5176\u4e2d\uff0c<strong>\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42<\/strong> \u662f\u6293\u53d6\u56fe\u7247\u7684\u6838\u5fc3\u6b65\u9aa4\u4e4b\u4e00\u3002\u901a\u8fc7\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u53ef\u4ee5\u83b7\u53d6\u5230\u5f7c\u5cb8\u684c\u9762\u7f51\u7ad9\u7684HTML\u9875\u9762\u5185\u5bb9\uff0c\u7136\u540e\u8fdb\u4e00\u6b65\u89e3\u6790HTML\u5185\u5bb9\uff0c\u63d0\u53d6\u56fe\u7247\u94fe\u63a5\uff0c\u6700\u540e\u5c06\u56fe\u7247\u4fdd\u5b58\u5230\u672c\u5730\u3002\u8fd9\u662f\u4e00\u79cd\u5e38\u89c1\u7684\u7f51\u9875\u722c\u866b\u65b9\u6cd5\uff0c\u9002\u7528\u4e8e\u6293\u53d6\u9759\u6001\u7f51\u9875\u4e2d\u7684\u56fe\u7247\u3002<\/p>\n<\/p>\n<p><p>\u5728\u8fd9\u7bc7\u6587\u7ae0\u4e2d\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u63a2\u8ba8\u5982\u4f55\u4f7f\u7528Python\u6293\u53d6\u5f7c\u5cb8\u684c\u9762\u56fe\u7247\uff0c\u5e76\u901a\u8fc7\u51e0\u4e2a\u6b65\u9aa4\u6765\u5b9e\u73b0\u8fd9\u4e00\u8fc7\u7a0b\u3002\u6211\u4eec\u5c06\u4ecb\u7ecd\u5982\u4f55\u6784\u5efa\u4e00\u4e2a\u7b80\u5355\u7684Python\u811a\u672c\uff0c\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\uff0c\u63d0\u53d6\u56fe\u7247\u94fe\u63a5\uff0c\u5e76\u5c06\u56fe\u7247\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u5230\u672c\u5730\u3002\u901a\u8fc7\u8fd9\u4e9b\u6b65\u9aa4\uff0c\u4f60\u5c06\u80fd\u591f\u8f7b\u677e\u6293\u53d6\u5f7c\u5cb8\u684c\u9762\u4e0a\u7684\u56fe\u7247\uff0c\u5e76\u4fdd\u5b58\u5230\u4f60\u7684\u7535\u8111\u4e2d\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u8bf7\u6c42\u7f51\u9875\u5185\u5bb9<\/h3>\n<\/p>\n<p><p>\u8981\u6293\u53d6\u5f7c\u5cb8\u684c\u9762\u4e0a\u7684\u56fe\u7247\uff0c\u9996\u5148\u9700\u8981\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\u3002\u8fd9\u53ef\u4ee5\u901a\u8fc7\u53d1\u9001HTTP\u8bf7\u6c42\u6765\u5b9e\u73b0\u3002Python\u7684requests\u5e93\u662f\u4e00\u4e2a\u975e\u5e38\u6d41\u884c\u7684HTTP\u5e93\uff0c\u9002\u7528\u4e8e\u53d1\u9001\u5404\u79cd\u7c7b\u578b\u7684HTTP\u8bf7\u6c42\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &quot;http:\/\/www.netbian.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\u4e0a\u9762\u7684\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u5bfc\u5165\u4e86requests\u5e93\uff0c\u7136\u540e\u5b9a\u4e49\u4e86\u5f7c\u5cb8\u684c\u9762\u7f51\u7ad9\u7684URL\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u53d1\u9001\u4e00\u4e2aGET\u8bf7\u6c42\u6765\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u5e76\u5c06\u54cd\u5e94\u7684HTML\u5185\u5bb9\u5b58\u50a8\u5728<code>html_content<\/code>\u53d8\u91cf\u4e2d\u3002\u8fd9\u6837\uff0c\u6211\u4eec\u5c31\u53ef\u4ee5\u8bbf\u95ee\u7f51\u9875\u7684HTML\u5185\u5bb9\u4e86\u3002<\/p>\n<\/p>\n<p><h3>\u4e8c\u3001\u89e3\u6790HTML\u5185\u5bb9<\/h3>\n<\/p>\n<p><p>\u83b7\u53d6\u5230\u7f51\u9875\u7684HTML\u5185\u5bb9\u540e\uff0c\u9700\u8981\u89e3\u6790HTML\u4ee5\u63d0\u53d6\u56fe\u7247\u94fe\u63a5\u3002BeautifulSoup\u662f\u4e00\u4e2a\u5f3a\u5927\u7684HTML\u89e3\u6790\u5e93\uff0c\u9002\u7528\u4e8e\u89e3\u6790\u548c\u5904\u7406HTML\u5185\u5bb9\u3002<\/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>\u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u5bfc\u5165\u4e86BeautifulSoup\u5e93\uff0c\u7136\u540e\u521b\u5efa\u4e86\u4e00\u4e2aBeautifulSoup\u5bf9\u8c61\uff0c\u5e76\u4f7f\u7528<code>html.parser<\/code>\u4f5c\u4e3a\u89e3\u6790\u5668\u6765\u89e3\u6790HTML\u5185\u5bb9\u3002\u8fd9\u6837\uff0c\u6211\u4eec\u5c31\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u6765\u904d\u5386\u548c\u63d0\u53d6HTML\u4e2d\u7684\u6570\u636e\u4e86\u3002<\/p>\n<\/p>\n<p><h3>\u4e09\u3001\u63d0\u53d6\u56fe\u7247\u94fe\u63a5<\/h3>\n<\/p>\n<p><p>\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u9700\u8981\u627e\u5230HTML\u4e2d\u7684\u56fe\u7247\u94fe\u63a5\u3002\u5728\u5f7c\u5cb8\u684c\u9762\u7684\u7f51\u9875\u4e2d\uff0c\u56fe\u7247\u901a\u5e38\u5d4c\u5165\u5728<code>&lt;img&gt;<\/code>\u6807\u7b7e\u4e2d\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u7684<code>find_all<\/code>\u65b9\u6cd5\u6765\u67e5\u627e\u6240\u6709\u7684<code>&lt;img&gt;<\/code>\u6807\u7b7e\uff0c\u5e76\u63d0\u53d6\u56fe\u7247\u7684\u94fe\u63a5\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">image_tags = soup.find_all(&#39;img&#39;)<\/p>\n<p>image_urls = [img[&#39;src&#39;] for img in image_tags if &#39;src&#39; in img.attrs]<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u4f7f\u7528<code>find_all<\/code>\u65b9\u6cd5\u67e5\u627e\u6240\u6709\u7684<code>&lt;img&gt;<\/code>\u6807\u7b7e\uff0c\u7136\u540e\u904d\u5386\u8fd9\u4e9b\u6807\u7b7e\u5e76\u63d0\u53d6<code>src<\/code>\u5c5e\u6027\u7684\u503c\uff0c\u5c06\u5176\u5b58\u50a8\u5728<code>image_urls<\/code>\u5217\u8868\u4e2d\u3002\u8fd9\u6837\uff0c\u6211\u4eec\u5c31\u5f97\u5230\u4e86\u6240\u6709\u56fe\u7247\u7684\u94fe\u63a5\u3002<\/p>\n<\/p>\n<p><h3>\u56db\u3001\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u56fe\u7247<\/h3>\n<\/p>\n<p><p>\u6700\u540e\u4e00\u6b65\u662f\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u56fe\u7247\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528requests\u5e93\u6765\u4e0b\u8f7d\u56fe\u7247\uff0c\u5e76\u4f7f\u7528OS\u5e93\u6765\u4fdd\u5b58\u56fe\u7247\u5230\u672c\u5730\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import os<\/p>\n<p>def download_image(image_url, save_dir):<\/p>\n<p>    response = requests.get(image_url)<\/p>\n<p>    if response.status_code == 200:<\/p>\n<p>        image_name = os.path.basename(image_url)<\/p>\n<p>        with open(os.path.join(save_dir, image_name), &#39;wb&#39;) as f:<\/p>\n<p>            f.write(response.content)<\/p>\n<p>save_dir = &quot;images&quot;<\/p>\n<p>os.makedirs(save_dir, exist_ok=True)<\/p>\n<p>for image_url in image_urls:<\/p>\n<p>    download_image(image_url, save_dir)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u5b9a\u4e49\u4e86\u4e00\u4e2a<code>download_image<\/code>\u51fd\u6570\uff0c\u8be5\u51fd\u6570\u63a5\u53d7\u56fe\u7247\u7684URL\u548c\u4fdd\u5b58\u76ee\u5f55\u4f5c\u4e3a\u53c2\u6570\u3002\u7136\u540e\uff0c\u6211\u4eec\u53d1\u9001\u4e00\u4e2aGET\u8bf7\u6c42\u6765\u4e0b\u8f7d\u56fe\u7247\uff0c\u5e76\u5c06\u56fe\u7247\u5185\u5bb9\u5199\u5165\u5230\u672c\u5730\u6587\u4ef6\u4e2d\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u521b\u5efa\u4e00\u4e2a\u4fdd\u5b58\u56fe\u7247\u7684\u76ee\u5f55\uff0c\u5e76\u904d\u5386\u6240\u6709\u7684\u56fe\u7247\u94fe\u63a5\uff0c\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u6bcf\u4e00\u5f20\u56fe\u7247\u3002<\/p>\n<\/p>\n<p><h3>\u4e94\u3001\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>\u901a\u8fc7\u4ee5\u4e0a\u51e0\u4e2a\u6b65\u9aa4\uff0c\u6211\u4eec\u6210\u529f\u5730\u5b9e\u73b0\u4e86\u4f7f\u7528Python\u6293\u53d6\u5f7c\u5cb8\u684c\u9762\u56fe\u7247\u7684\u8fc7\u7a0b\u3002\u9996\u5148\uff0c\u6211\u4eec\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\uff0c\u7136\u540e\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u5e76\u63d0\u53d6\u56fe\u7247\u94fe\u63a5\uff0c\u6700\u540e\u4f7f\u7528requests\u5e93\u4e0b\u8f7d\u56fe\u7247\u5e76\u4fdd\u5b58\u5230\u672c\u5730\u3002\u8fd9\u662f\u4e00\u79cd\u975e\u5e38\u5b9e\u7528\u7684\u7f51\u9875\u722c\u866b\u65b9\u6cd5\uff0c\u9002\u7528\u4e8e\u6293\u53d6\u9759\u6001\u7f51\u9875\u4e2d\u7684\u56fe\u7247\u3002<\/p>\n<\/p>\n<p><h3>\u516d\u3001\u6269\u5c55\u9605\u8bfb<\/h3>\n<\/p>\n<p><p>\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u4f60\u53ef\u80fd\u8fd8\u4f1a\u9047\u5230\u4e00\u4e9b\u5176\u4ed6\u60c5\u51b5\uff0c\u6bd4\u5982\u5904\u7406\u5206\u9875\u3001\u5904\u7406\u52a8\u6001\u52a0\u8f7d\u7684\u5185\u5bb9\u3001\u5904\u7406\u53cd\u722c\u866b\u673a\u5236\u7b49\u3002\u9488\u5bf9\u8fd9\u4e9b\u60c5\u51b5\uff0c\u53ef\u4ee5\u4f7f\u7528\u4e00\u4e9b\u66f4\u9ad8\u7ea7\u7684\u6280\u672f\u548c\u5de5\u5177\uff0c\u6bd4\u5982\u4f7f\u7528Selenium\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u3001\u4f7f\u7528\u4ee3\u7406IP\u6765\u7ed5\u8fc7\u53cd\u722c\u866b\u673a\u5236\u7b49\u3002<\/p>\n<\/p>\n<p><p>\u4ee5\u4e0b\u662f\u4e00\u4e9b\u6269\u5c55\u9605\u8bfb\u6750\u6599\uff0c\u4f9b\u4f60\u8fdb\u4e00\u6b65\u5b66\u4e60\u548c\u7814\u7a76\uff1a<\/p>\n<\/p>\n<ol>\n<li><a href=\"https:\/\/www.selenium.dev\/documentation\/en\/\">Selenium\u6587\u6863<\/a><\/li>\n<li><a href=\"https:\/\/www.crummy.com\/software\/BeautifulSoup\/bs4\/doc\/\">BeautifulSoup\u6587\u6863<\/a><\/li>\n<li><a href=\"https:\/\/docs.python-requests.org\/en\/latest\/\">requests\u5e93\u6587\u6863<\/a><\/li>\n<li><a href=\"https:\/\/www.oreilly.com\/library\/view\/python-web-scraping\/9781782164364\/\">Python\u722c\u866b\u5b9e\u6218<\/a><\/li>\n<\/ol>\n<p><p>\u5e0c\u671b\u8fd9\u7bc7\u6587\u7ae0\u5bf9\u4f60\u6709\u6240\u5e2e\u52a9\uff0c\u795d\u4f60\u5728\u4f7f\u7528Python\u6293\u53d6\u5f7c\u5cb8\u684c\u9762\u56fe\u7247\u7684\u8fc7\u7a0b\u4e2d\u53d6\u5f97\u6210\u529f\uff01<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u83b7\u53d6\u5f7c\u5cb8\u684c\u9762\u7684\u56fe\u7247\uff1f<\/strong><br \/>\u8981\u6293\u53d6\u5f7c\u5cb8\u684c\u9762\u7684\u56fe\u7247\uff0c\u53ef\u4ee5\u4f7f\u7528Python\u7684\u56fe\u50cf\u5904\u7406\u5e93\uff0c\u5982PIL\uff08Pillow\uff09\u6216OpenCV\uff0c\u5e76\u7ed3\u5408\u7f51\u7edc\u8bf7\u6c42\u5e93\u5982Requests\u3002\u9996\u5148\uff0c\u786e\u5b9a\u5f7c\u5cb8\u684c\u9762\u56fe\u7247\u7684URL\uff0c\u7136\u540e\u4f7f\u7528Requests\u5e93\u4e0b\u8f7d\u8be5\u56fe\u7247\uff0c\u5e76\u901a\u8fc7PIL\u6216OpenCV\u8fdb\u884c\u5904\u7406\u548c\u4fdd\u5b58\u3002\u786e\u4fdd\u5728\u6293\u53d6\u65f6\u9075\u5faa\u7f51\u7ad9\u7684\u4f7f\u7528\u6761\u6b3e\uff0c\u5c0a\u91cd\u7248\u6743\u3002<\/p>\n<p><strong>\u6293\u53d6\u5f7c\u5cb8\u684c\u9762\u56fe\u7247\u9700\u8981\u54ea\u4e9bPython\u5e93\uff1f<\/strong><br \/>\u5728\u8fdb\u884c\u56fe\u7247\u6293\u53d6\u65f6\uff0c\u901a\u5e38\u9700\u8981\u4f7f\u7528Requests\u5e93\u8fdb\u884cHTTP\u8bf7\u6c42\uff0cPIL\uff08Pillow\uff09\u5e93\u7528\u4e8e\u56fe\u50cf\u5904\u7406\uff0c\u53ef\u80fd\u8fd8\u9700\u8981BeautifulSoup\u5e93\u6765\u89e3\u6790HTML\u3002\u5982\u679c\u9700\u8981\u5904\u7406\u52a8\u6001\u5185\u5bb9\uff0c\u53ef\u4ee5\u8003\u8651\u4f7f\u7528Selenium\u5e93\u3002\u8fd9\u4e9b\u5e93\u7684\u7ec4\u5408\u5c06\u5e2e\u52a9\u4f60\u9ad8\u6548\u5730\u6293\u53d6\u548c\u5904\u7406\u56fe\u7247\u3002<\/p>\n<p><strong>\u6293\u53d6\u7684\u5f7c\u5cb8\u684c\u9762\u56fe\u7247\u5982\u4f55\u4fdd\u5b58\u5230\u672c\u5730\uff1f<\/strong><br \/>\u6293\u53d6\u5230\u7684\u5f7c\u5cb8\u684c\u9762\u56fe\u7247\u53ef\u4ee5\u901a\u8fc7PIL\u5e93\u4e2d\u7684Image\u7c7b\u8f7b\u677e\u4fdd\u5b58\u3002\u4e0b\u8f7d\u56fe\u7247\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528<code>Image.save()<\/code>\u65b9\u6cd5\u5c06\u5176\u4fdd\u5b58\u5230\u6307\u5b9a\u8def\u5f84\u3002\u786e\u4fdd\u6587\u4ef6\u540d\u548c\u683c\u5f0f\u6b63\u786e\uff0c\u4ee5\u907f\u514d\u4fdd\u5b58\u5931\u8d25\u6216\u6587\u4ef6\u635f\u574f\u7684\u60c5\u51b5\u3002\u4fdd\u5b58\u540e\u7684\u6587\u4ef6\u53ef\u4ee5\u5728\u672c\u5730\u6587\u4ef6\u7cfb\u7edf\u4e2d\u67e5\u770b\u548c\u4f7f\u7528\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u6293\u53d6\u5f7c\u5cb8\u684c\u9762\u56fe\u7247\u7684\u65b9\u6cd5\u5305\u62ec\uff1a\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u4f7f\u7528BeautifulSoup [&hellip;]","protected":false},"author":3,"featured_media":1089305,"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\/1089294"}],"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=1089294"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1089294\/revisions"}],"predecessor-version":[{"id":1089307,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1089294\/revisions\/1089307"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1089305"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1089294"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1089294"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1089294"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}