{"id":979172,"date":"2024-12-27T06:44:11","date_gmt":"2024-12-26T22:44:11","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/979172.html"},"modified":"2024-12-27T06:44:13","modified_gmt":"2024-12-26T22:44:13","slug":"python%e5%a6%82%e4%bd%95%e7%88%ac%e7%bd%91%e7%ab%99%e5%9b%be%e7%89%87","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/979172.html","title":{"rendered":"python\u5982\u4f55\u722c\u7f51\u7ad9\u56fe\u7247"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/24205128\/23b8f29e-ef26-4198-b77f-6771673005c6.webp\" alt=\"python\u5982\u4f55\u722c\u7f51\u7ad9\u56fe\u7247\" \/><\/p>\n<p><p> <strong>Python\u722c\u53d6\u7f51\u7ad9\u56fe\u7247\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528requests\u5e93\u3001BeautifulSoup\u5e93\u3001os\u5e93\u4ee5\u53caPIL\u5e93\u5b9e\u73b0\uff0c\u5173\u952e\u6b65\u9aa4\u5305\u62ec\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u89e3\u6790HTML\u83b7\u53d6\u56fe\u7247URL\u3001\u4e0b\u8f7d\u56fe\u7247\u5e76\u4fdd\u5b58\u5230\u672c\u5730\u3002<\/strong>\u5728\u5177\u4f53\u5b9e\u73b0\u8fc7\u7a0b\u4e2d\uff0c\u9996\u5148\u9700\u8981\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u7136\u540e\u5229\u7528BeautifulSoup\u5e93\u89e3\u6790HTML\u6587\u6863\uff0c\u63d0\u53d6\u51fa\u6240\u6709\u56fe\u7247\u7684URL\u3002\u63a5\u4e0b\u6765\uff0c\u901a\u8fc7requests\u5e93\u4e0b\u8f7d\u56fe\u7247\uff0c\u5e76\u5229\u7528os\u5e93\u521b\u5efa\u6587\u4ef6\u5939\u5e76\u4fdd\u5b58\u56fe\u7247\u5230\u672c\u5730\u3002\u6700\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528PIL\u5e93\u5bf9\u56fe\u7247\u8fdb\u884c\u7b80\u5355\u5904\u7406\uff0c\u5982\u8c03\u6574\u5927\u5c0f\u3001\u683c\u5f0f\u8f6c\u6362\u7b49\u3002<\/p>\n<\/p>\n<p><p>\u4e00\u3001\u4f7f\u7528REQUESTS\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9  <\/p>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u4f7f\u7528requests\u5e93\u5411\u76ee\u6807\u7f51\u7ad9\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u4ee5\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\u3002requests\u5e93\u662f\u4e00\u4e2a\u7b80\u5355\u6613\u7528\u7684HTTP\u5e93\uff0c\u9002\u7528\u4e8e\u5404\u79cdHTTP\u8bf7\u6c42\u64cd\u4f5c\u3002<\/p>\n<\/p>\n<p><p>requests\u5e93\u7684\u57fa\u672c\u7528\u6cd5\u5982\u4e0b\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<h2><strong>\u68c0\u67e5\u8bf7\u6c42\u662f\u5426\u6210\u529f<\/strong><\/h2>\n<p>if response.status_code == 200:<\/p>\n<p>    html_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\u6790HTML\u6587\u6863\u63d0\u53d6\u56fe\u7247URL  <\/p>\n<\/p>\n<p><p>\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u540e\uff0c\u6211\u4eec\u9700\u8981\u89e3\u6790HTML\u6587\u6863\u4ee5\u63d0\u53d6\u51fa\u6240\u6709\u56fe\u7247\u7684URL\u3002\u8fd9\u91cc\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u5e93\uff0c\u5b83\u662f\u4e00\u4e2a\u5f3a\u5927\u7684HTML\u89e3\u6790\u5e93\uff0c\u80fd\u591f\u65b9\u4fbf\u5730\u4eceHTML\u6587\u6863\u4e2d\u63d0\u53d6\u6570\u636e\u3002<\/p>\n<\/p>\n<p><p>BeautifulSoup\u7684\u57fa\u672c\u7528\u6cd5\u5982\u4e0b\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<h2><strong>\u627e\u5230\u6240\u6709\u7684img\u6807\u7b7e<\/strong><\/h2>\n<p>img_tags = soup.find_all(&#39;img&#39;)<\/p>\n<h2><strong>\u63d0\u53d6\u6bcf\u4e2aimg\u6807\u7b7e\u7684src\u5c5e\u6027<\/strong><\/h2>\n<p>img_urls = [img[&#39;src&#39;] for img in img_tags if &#39;src&#39; in img.attrs]<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e09\u3001\u4e0b\u8f7d\u56fe\u7247\u5e76\u4fdd\u5b58\u5230\u672c\u5730  <\/p>\n<\/p>\n<p><p>\u5728\u83b7\u53d6\u5230\u56fe\u7247\u7684URL\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7requests\u5e93\u4e0b\u8f7d\u8fd9\u4e9b\u56fe\u7247\uff0c\u5e76\u4f7f\u7528os\u5e93\u5c06\u5b83\u4eec\u4fdd\u5b58\u5230\u672c\u5730\u3002<\/p>\n<\/p>\n<p><p>\u5b9e\u73b0\u56fe\u7247\u4e0b\u8f7d\u4e0e\u4fdd\u5b58\u7684\u4ee3\u7801\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import os<\/p>\n<h2><strong>\u521b\u5efa\u4fdd\u5b58\u56fe\u7247\u7684\u6587\u4ef6\u5939<\/strong><\/h2>\n<p>os.makedirs(&#39;images&#39;, exist_ok=True)<\/p>\n<p>for img_url in img_urls:<\/p>\n<p>    # \u83b7\u53d6\u56fe\u7247\u540d\u79f0<\/p>\n<p>    img_name = os.path.basename(img_url)<\/p>\n<p>    img_path = os.path.join(&#39;images&#39;, img_name)<\/p>\n<p>    # \u4e0b\u8f7d\u56fe\u7247<\/p>\n<p>    img_response = requests.get(img_url)<\/p>\n<p>    # \u4fdd\u5b58\u56fe\u7247\u5230\u672c\u5730<\/p>\n<p>    with open(img_path, &#39;wb&#39;) as f:<\/p>\n<p>        f.write(img_response.content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u56db\u3001\u4f7f\u7528PIL\u5e93\u5bf9\u56fe\u7247\u8fdb\u884c\u5904\u7406  <\/p>\n<\/p>\n<p><p>\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u56fe\u7247\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528PIL\u5e93\u5bf9\u56fe\u7247\u8fdb\u884c\u7b80\u5355\u7684\u5904\u7406\uff0c\u5982\u8c03\u6574\u5927\u5c0f\u3001\u683c\u5f0f\u8f6c\u6362\u7b49\u3002PIL\u5e93\u662fPython Imaging Library\u7684\u7b80\u79f0\uff0c\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u56fe\u50cf\u5904\u7406\u5e93\u3002<\/p>\n<\/p>\n<p><p>PIL\u5e93\u7684\u57fa\u672c\u7528\u6cd5\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from PIL import Image<\/p>\n<h2><strong>\u6253\u5f00\u56fe\u7247<\/strong><\/h2>\n<p>with Image.open(&#39;images\/example.jpg&#39;) as img:<\/p>\n<p>    # \u663e\u793a\u56fe\u7247<\/p>\n<p>    img.show()<\/p>\n<p>    # \u8c03\u6574\u56fe\u7247\u5927\u5c0f<\/p>\n<p>    img_resized = img.resize((100, 100))<\/p>\n<p>    img_resized.show()<\/p>\n<p>    # \u8f6c\u6362\u56fe\u7247\u683c\u5f0f<\/p>\n<p>    img_resized.save(&#39;images\/example_resized.png&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e94\u3001\u5904\u7406\u5e38\u89c1\u95ee\u9898\u4e0e\u6ce8\u610f\u4e8b\u9879  <\/p>\n<\/p>\n<p><p>\u5728\u722c\u53d6\u7f51\u7ad9\u56fe\u7247\u65f6\uff0c\u6709\u51e0\u4e2a\u5e38\u89c1\u95ee\u9898\u548c\u6ce8\u610f\u4e8b\u9879\u9700\u8981\u8003\u8651\uff1a<\/p>\n<\/p>\n<ol>\n<li>\n<p><strong>\u53cd\u722c\u63aa\u65bd<\/strong>\uff1a\u4e00\u4e9b\u7f51\u7ad9\u53ef\u80fd\u4f1a\u6709\u53cd\u722c\u866b\u63aa\u65bd\uff0c\u5982\u8bf7\u6c42\u9891\u7387\u9650\u5236\u3001IP\u5c01\u7981\u7b49\u3002\u53ef\u4ee5\u901a\u8fc7\u589e\u52a0\u8bf7\u6c42\u95f4\u9694\u3001\u4f7f\u7528\u4ee3\u7406IP\u7b49\u65b9\u5f0f\u8fdb\u884c\u5e94\u5bf9\u3002<\/p>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u56fe\u7247URL\u7684\u5b8c\u6574\u6027<\/strong>\uff1a\u6709\u65f6\u63d0\u53d6\u5230\u7684\u56fe\u7247URL\u53ef\u80fd\u662f\u4e0d\u5b8c\u6574\u7684\uff08\u5982\u76f8\u5bf9\u8def\u5f84\uff09\u3002\u9700\u8981\u6839\u636e\u7f51\u7ad9\u7684\u7ed3\u6784\u5c06\u5176\u8865\u5168\u4e3a\u5b8c\u6574\u7684URL\u3002<\/p>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u5408\u6cd5\u6027\u548c\u7248\u6743<\/strong>\uff1a\u5728\u722c\u53d6\u548c\u4f7f\u7528\u56fe\u7247\u65f6\uff0c\u52a1\u5fc5\u9075\u5b88\u76f8\u5173\u6cd5\u5f8b\u6cd5\u89c4\uff0c\u5c0a\u91cd\u4ed6\u4eba\u7248\u6743\uff0c\u786e\u4fdd\u4f7f\u7528\u7684\u5408\u6cd5\u6027\u3002<\/p>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u5f02\u5e38\u5904\u7406<\/strong>\uff1a\u5728\u8bf7\u6c42\u548c\u4e0b\u8f7d\u8fc7\u7a0b\u4e2d\u53ef\u80fd\u4f1a\u51fa\u73b0\u5f02\u5e38\uff0c\u5982\u8bf7\u6c42\u8d85\u65f6\u3001\u7f51\u7edc\u4e0d\u7a33\u5b9a\u7b49\u3002\u9700\u8981\u589e\u52a0\u5f02\u5e38\u5904\u7406\u673a\u5236\u4ee5\u63d0\u9ad8\u7a0b\u5e8f\u7684\u5065\u58ee\u6027\u3002<\/p>\n<\/p>\n<\/li>\n<\/ol>\n<p><p>\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\u548c\u6ce8\u610f\u4e8b\u9879\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u9ad8\u6548\u5730\u722c\u53d6\u7f51\u7ad9\u56fe\u7247\uff0c\u5e76\u5bf9\u56fe\u7247\u8fdb\u884c\u5904\u7406\u3002\u5e0c\u671b\u8fd9\u7bc7\u6587\u7ae0\u80fd\u5e2e\u52a9\u5230\u4f60\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\u66f4\u597d\u5730\u5b9e\u73b0\u56fe\u7247\u722c\u53d6\u4e0e\u5904\u7406\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u722c\u53d6\u7279\u5b9a\u7f51\u7ad9\u4e0a\u7684\u56fe\u7247\uff1f<\/strong><br \/>\u8981\u722c\u53d6\u7279\u5b9a\u7f51\u7ad9\u4e0a\u7684\u56fe\u7247\uff0c\u9996\u5148\u9700\u8981\u9009\u62e9\u5408\u9002\u7684\u5e93\uff0c\u5982Requests\u548cBeautifulSoup\u3002\u4f7f\u7528Requests\u5e93\u53ef\u4ee5\u8f7b\u677e\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\uff0c\u800cBeautifulSoup\u5219\u7528\u4e8e\u89e3\u6790\u8fd9\u4e9b\u5185\u5bb9\u3002\u901a\u8fc7\u5206\u6790\u7f51\u9875\u7ed3\u6784\uff0c\u627e\u5230\u56fe\u7247\u7684URL\uff0c\u4e4b\u540e\u53ef\u4ee5\u4f7f\u7528Requests\u5e93\u5c06\u8fd9\u4e9b\u56fe\u7247\u4e0b\u8f7d\u5230\u672c\u5730\u3002<\/p>\n<p><strong>\u5728\u722c\u53d6\u7f51\u7ad9\u56fe\u7247\u65f6\u9700\u8981\u6ce8\u610f\u54ea\u4e9b\u6cd5\u5f8b\u548c\u9053\u5fb7\u95ee\u9898\uff1f<\/strong><br \/>\u5728\u8fdb\u884c\u7f51\u9875\u722c\u866b\u65f6\uff0c\u52a1\u5fc5\u9075\u5b88\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6\u548c\u76f8\u5173\u6cd5\u5f8b\u6cd5\u89c4\u3002\u786e\u4fdd\u4f60\u6709\u6743\u8bbf\u95ee\u548c\u4f7f\u7528\u6240\u722c\u53d6\u7684\u56fe\u7247\uff0c\u7279\u522b\u662f\u90a3\u4e9b\u53d7\u7248\u6743\u4fdd\u62a4\u7684\u5185\u5bb9\u3002\u6b64\u5916\uff0c\u5c3d\u91cf\u907f\u514d\u5bf9\u7f51\u7ad9\u9020\u6210\u8d1f\u62c5\uff0c\u5408\u7406\u8bbe\u7f6e\u722c\u53d6\u9891\u7387\u3002<\/p>\n<p><strong>\u662f\u5426\u6709\u73b0\u6210\u7684Python\u5e93\u53ef\u4ee5\u7b80\u5316\u56fe\u7247\u722c\u53d6\u7684\u8fc7\u7a0b\uff1f<\/strong><br \/>\u662f\u7684\uff0cPython\u4e2d\u6709\u4e00\u4e9b\u73b0\u6210\u7684\u5e93\u53ef\u4ee5\u7b80\u5316\u56fe\u7247\u722c\u53d6\u7684\u8fc7\u7a0b\uff0c\u4f8b\u5982Scrapy\u548cPillow\u3002Scrapy\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u722c\u866b\u6846\u67b6\uff0c\u652f\u6301\u5f02\u6b65\u5904\u7406\u548c\u6570\u636e\u5b58\u50a8\uff0c\u800cPillow\u5219\u53ef\u4ee5\u5e2e\u52a9\u4f60\u5904\u7406\u4e0b\u8f7d\u540e\u7684\u56fe\u7247\uff0c\u5982\u8c03\u6574\u5927\u5c0f\u6216\u683c\u5f0f\u8f6c\u6362\u3002\u8fd9\u4e9b\u5e93\u53ef\u4ee5\u663e\u8457\u63d0\u9ad8\u4f60\u7684\u5f00\u53d1\u6548\u7387\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u722c\u53d6\u7f51\u7ad9\u56fe\u7247\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528requests\u5e93\u3001BeautifulSoup\u5e93\u3001os\u5e93\u4ee5\u53caPIL\u5e93\u5b9e\u73b0\uff0c [&hellip;]","protected":false},"author":3,"featured_media":979178,"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\/979172"}],"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=979172"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/979172\/revisions"}],"predecessor-version":[{"id":979181,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/979172\/revisions\/979181"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/979178"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=979172"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=979172"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=979172"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}