{"id":176358,"date":"2024-05-08T19:09:32","date_gmt":"2024-05-08T11:09:32","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/176358.html"},"modified":"2024-05-08T19:09:40","modified_gmt":"2024-05-08T11:09:40","slug":"python%e7%88%ac%e8%99%ab%e6%80%8e%e4%b9%88%e5%ae%9e%e7%8e%b0%e7%88%ac%e5%8f%96%e7%bd%91%e7%ab%99%e5%9b%be%e7%89%87","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/176358.html","title":{"rendered":"python\u722c\u866b\u600e\u4e48\u5b9e\u73b0\u722c\u53d6\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\/27060050\/00891eb1-a14f-434f-8b9a-6eb60c6e1b6f.webp\" alt=\"python\u722c\u866b\u600e\u4e48\u5b9e\u73b0\u722c\u53d6\u7f51\u7ad9\u56fe\u7247\" \/><\/p>\n<p><p><strong>Python\u722c\u866b\u5b9e\u73b0\u722c\u53d6\u7f51\u7ad9\u56fe\u7247<\/strong>\u4e3b\u8981\u5305\u62ec\u4ee5\u4e0b\u51e0\u4e2a\u6b65\u9aa4\uff1a<strong>\u9009\u62e9\u5408\u9002\u7684\u5e93\u3001\u53d1\u9001\u8bf7\u6c42\u3001\u89e3\u6790\u5185\u5bb9\u3001\u83b7\u53d6\u56fe\u7247\u94fe\u63a5\u3001\u4e0b\u8f7d\u56fe\u7247\u3001\u4fdd\u5b58\u56fe\u7247<\/strong>\u3002\u8fd9\u4e2a\u8fc7\u7a0b\u901a\u5e38\u4f9d\u8d56\u591a\u4e2aPython\u7b2c\u4e09\u65b9\u5e93\uff0c\u4f8b\u5982requests\u5e93\u7528\u4e8e\u53d1\u9001\u7f51\u7edc\u8bf7\u6c42\u3001BeautifulSoup\u7528\u4e8e\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u3001lxml\u7528\u4e8e\u5904\u7406xml\u548chtml\uff0c\u5728\u5904\u7406\u8f83\u5927\u89c4\u6a21\u7684\u6570\u636e\u65f6\u6027\u80fd\u66f4\u597d\u3002<\/p>\n<\/p>\n<p><p>\u5728\u8be6\u7ec6\u63cf\u8ff0<strong>\u53d1\u9001\u8bf7\u6c42<\/strong>\u6b65\u9aa4\u4e4b\u524d\uff0c\u6211\u4eec\u9700\u8981\u5f04\u6e05\u695a\u7f51\u9875\u7684\u8bf7\u6c42\u7c7b\u578b\u3002\u7f51\u7ad9\u7684\u56fe\u7247\u52a0\u8f7d\u53ef\u80fd\u662f\u5728\u521d\u6b21\u9875\u9762\u52a0\u8f7d\u65f6\u5b8c\u6210\u7684\uff0c\u4e5f\u53ef\u80fd\u662f\u901a\u8fc7JavaScript\u52a8\u6001\u52a0\u8f7d\u7684\u3002\u5982\u679c\u662f\u540e\u4e00\u79cd\u60c5\u51b5\uff0c\u53ef\u80fd\u9700\u8981\u4f7f\u7528selenium\u914d\u5408webdriver\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u9009\u62e9\u5408\u9002\u7684\u5e93<\/h3>\n<\/p>\n<p><p>Python\u63d0\u4f9b\u4e86\u591a\u79cd\u7528\u4e8e\u7f51\u7edc\u722c\u866b\u7684\u5e93\uff0c<strong>requests<\/strong>\u662f\u6700\u5e38\u7528\u7684HTTP\u5ba2\u6237\u7aef\u5e93\uff0c\u56e0\u4e3a\u5b83\u7b80\u5355\u6613\u7528\u3002\u7528\u4e8e\u89e3\u6790\u7f51\u9875\u7684\u5e93\u6709<strong>BeautifulSoup<\/strong>\u548c<strong>lxml<\/strong>\uff0cBeautifulSoup\u7b80\u5355\u6613\u61c2\uff0c\u800clxml\u5904\u7406\u901f\u5ea6\u5feb\u3002\u7528\u4e8e\u6a21\u62df\u6d4f\u89c8\u5668\u7684\u5e93<strong>selenium<\/strong>\u53ef\u4ee5\u6267\u884cJavaScript\uff0c\u975e\u5e38\u9002\u5408\u722c\u53d6\u52a8\u6001\u7f51\u7ad9\u3002<\/p>\n<\/p>\n<p><h3>\u4e8c\u3001\u53d1\u9001\u8bf7\u6c42<\/h3>\n<\/p>\n<p><p>\u4f7f\u7528\u8bf7\u6c42\u5e93\uff0c\u5982<strong>requests<\/strong>\uff0c\u901a\u8fc7GET\u65b9\u6cd5\u83b7\u53d6\u76ee\u6807\u7f51\u7ad9\u7684\u5185\u5bb9\u3002\u9996\u5148\u5bfc\u5165\u5e93\u5e76\u53d1\u9001\u8bf7\u6c42\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#039;\u76ee\u6807\u7f51\u7ad9URL&#039;<\/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()  # \u786e\u4fdd\u8bf7\u6c42\u6210\u529f<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u89e3\u6790\u5185\u5bb9<\/h3>\n<\/p>\n<p><p>\u4f7f\u7528<strong>BeautifulSoup<\/strong>\u6765\u89e3\u6790response\u4e2d\u7684HTML\u5185\u5bb9\uff0c\u627e\u5230\u56fe\u7247\u7684\u6807\u7b7e\u548c\u5c5e\u6027\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>soup = BeautifulSoup(response.text, &#039;html.parser&#039;)<\/p>\n<p>images = soup.find_all(&#039;img&#039;)  # \u627e\u5230\u6240\u6709\u56fe\u7247\u6807\u7b7e<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u56db\u3001\u83b7\u53d6\u56fe\u7247\u94fe\u63a5<\/h3>\n<\/p>\n<p><p>\u4ece\u89e3\u6790\u540e\u7684\u5185\u5bb9\u4e2d\u63d0\u53d6\u6240\u6709\u56fe\u7247\u7684URL\u94fe\u63a5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">img_urls = [img[&#039;src&#039;] for img in images if &#039;src&#039; in img.attrs]<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e94\u3001\u4e0b\u8f7d\u56fe\u7247<\/h3>\n<\/p>\n<p><p>\u904d\u5386img_urls\u5217\u8868\uff0c\u5bf9\u6bcf\u4e00\u4e2a\u56fe\u7247\u94fe\u63a5\u53d1\u9001\u8bf7\u6c42\u5e76\u83b7\u53d6\u56fe\u7247\u6570\u636e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">for img_url in img_urls:<\/p>\n<p>    img_data = requests.get(img_url).content<\/p>\n<p>    # \u4e0b\u4e00\u6b65\u8fdb\u884c\u56fe\u7247\u7684\u4fdd\u5b58<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u516d\u3001\u4fdd\u5b58\u56fe\u7247<\/h3>\n<\/p>\n<p><p>\u5c06\u83b7\u53d6\u5230\u7684\u56fe\u7247\u6570\u636e\u5b58\u50a8\u5230\u6587\u4ef6\u4e2d\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">    with open(&#039;\u56fe\u7247\u4fdd\u5b58\u8def\u5f84&#039;, &#039;wb&#039;) as file:<\/p>\n<p>        file.write(img_data)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u5c31\u53ef\u4ee5\u5b8c\u6210\u56fe\u7247\u7684\u722c\u53d6\u548c\u4fdd\u5b58\u3002\u9700\u8981\u6ce8\u610f\u7684\u662f\uff0c\u8fdb\u884c\u7f51\u7edc\u722c\u866b\u65f6\uff0c\u5e94\u5f53\u9075\u5b88robots.txt\u534f\u8bae\uff0c\u5c0a\u91cd\u7f51\u7ad9\u6240\u6709\u8005\u7684\u610f\u613f\uff0c\u5e76\u4e14\u4e0d\u5e94\u8be5\u5bf9\u7f51\u7ad9\u4ea7\u751f\u592a\u5927\u8d1f\u8f7d\uff0c\u4ee5\u514d\u5f71\u54cd\u6b63\u5e38\u670d\u52a1\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p><strong>Q: \u600e\u6837\u4f7f\u7528Python\u7f16\u5199\u722c\u866b\u6765\u83b7\u53d6\u7f51\u7ad9\u4e0a\u7684\u56fe\u7247\uff1f<\/strong><\/p>\n<p>A: \u8981\u7528Python\u7f16\u5199\u722c\u866b\u6765\u83b7\u53d6\u7f51\u7ad9\u4e0a\u7684\u56fe\u7247\uff0c\u53ef\u4ee5\u6309\u7167\u4ee5\u4e0b\u6b65\u9aa4\u64cd\u4f5c\uff1a<\/p>\n<ol>\n<li>\u5bfc\u5165\u6240\u9700\u5e93\u548c\u6a21\u5757\uff0c\u5982<code>requests<\/code>\uff0c<code>beautifulsoup<\/code>\u7b49\u3002<\/li>\n<li>\u4f7f\u7528<code>requests<\/code>\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\u3002<\/li>\n<li>\u4f7f\u7528<code>beautifulsoup<\/code>\u7b49HTML\u89e3\u6790\u5e93\u89e3\u6790\u7f51\u9875\u5185\u5bb9\uff0c\u627e\u51fa\u6240\u6709\u56fe\u7247\u7684\u6807\u7b7e\u548cURL\u3002<\/li>\n<li>\u904d\u5386\u56fe\u7247\u6807\u7b7e\uff0c\u63d0\u53d6\u56fe\u7247URL\u5e76\u4e0b\u8f7d\u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6\u5939\u3002<\/li>\n<li>\u53ef\u9009\uff1a\u8bbe\u7f6e\u5408\u9002\u7684\u8bf7\u6c42\u5934\u3001\u4ee3\u7406\u4ee5\u53ca\u5904\u7406\u53cd\u722c\u673a\u5236\u7b49\u3002<\/li>\n<\/ol>\n<p><strong>Q: \u6709\u6ca1\u6709\u6bd4\u8f83\u5e38\u7528\u7684Python\u722c\u866b\u6846\u67b6\u7528\u4e8e\u83b7\u53d6\u7f51\u7ad9\u4e0a\u7684\u56fe\u7247\uff1f<\/strong><\/p>\n<p>A: \u662f\u7684\uff0cPython\u6709\u4e00\u4e9b\u5e38\u7528\u7684\u722c\u866b\u6846\u67b6\u53ef\u4ee5\u7528\u4e8e\u83b7\u53d6\u7f51\u7ad9\u4e0a\u7684\u56fe\u7247\u3002\u5176\u4e2d\u4e00\u4e9b\u6d41\u884c\u7684\u6846\u67b6\u5305\u62ec\uff1a<\/p>\n<ol>\n<li>Scrapy\uff1a\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684Python\u722c\u866b\u6846\u67b6\uff0c\u53ef\u7528\u4e8e\u9ad8\u6548\u7684\u7f51\u9875\u722c\u53d6\u548c\u6570\u636e\u63d0\u53d6\u3002<\/li>\n<li>Requests-HTML\uff1a\u4e00\u4e2a\u57fa\u4e8eRequests\u5e93\u7684\u7b80\u5355\u6613\u7528\u7684\u7f51\u9875\u722c\u53d6\u5de5\u5177\uff0c\u652f\u6301\u5bf9\u7f51\u9875\u8fdb\u884c\u89e3\u6790\u548c\u63d0\u53d6\u6570\u636e\u3002<\/li>\n<li>Selenium\uff1a\u4e00\u4e2a\u7528\u4e8e\u81ea\u52a8\u5316\u6d4b\u8bd5\u548c\u7f51\u9875\u722c\u53d6\u7684\u6846\u67b6\uff0c\u7279\u522b\u9002\u7528\u4e8e\u52a8\u6001\u7f51\u9875\u7684\u722c\u53d6\u3002<\/li>\n<li>Beautiful Soup\uff1a\u4e00\u4e2aPython\u5e93\uff0c\u7528\u4e8e\u4eceHTML\u548cXML\u6587\u4ef6\u4e2d\u63d0\u53d6\u6570\u636e\uff0c\u53ef\u7528\u4e8e\u7f51\u9875\u89e3\u6790\u548c\u63d0\u53d6\u56fe\u7247\u7b49\u5185\u5bb9\u3002<\/li>\n<li>PyQuery\uff1a\u4e00\u4e2a\u7c7b\u4f3c\u4e8ejQuery\u7684\u5e93\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u5bf9HTML\u8fdb\u884c\u89e3\u6790\u548c\u63d0\u53d6\u6570\u636e\u3002<\/li>\n<\/ol>\n<p><strong>Q: \u722c\u53d6\u7f51\u7ad9\u56fe\u7247\u65f6\u6709\u6ca1\u6709\u4ec0\u4e48\u8981\u6ce8\u610f\u7684\u4e8b\u9879\uff1f<\/strong><\/p>\n<p>A: \u5728\u722c\u53d6\u7f51\u7ad9\u56fe\u7247\u65f6\uff0c\u6709\u4e00\u4e9b\u8981\u6ce8\u610f\u7684\u4e8b\u9879\uff1a<\/p>\n<ol>\n<li>\u7f51\u7ad9\u7684\u7248\u6743\u95ee\u9898\uff1a\u786e\u4fdd\u5408\u6cd5\u4f7f\u7528\u3001\u4e0b\u8f7d\u548c\u5206\u4eab\u56fe\u7247\u3002<\/li>\n<li>Robots.txt\u6587\u4ef6\uff1a\u8bf7\u5c0a\u91cd\u7f51\u7ad9\u7684Robots\u534f\u8bae\uff0c\u9075\u5faa\u5176\u4e2d\u7684\u89c4\u5b9a\uff0c\u907f\u514d\u8bbf\u95ee\u88ab\u7981\u6b62\u7684\u9875\u9762\u3002<\/li>\n<li>\u9891\u7387\u9650\u5236\uff1a\u722c\u53d6\u65f6\u8bf7\u9002\u5ea6\u8c03\u6574\u8bf7\u6c42\u9891\u7387\uff0c\u4ee5\u514d\u5bf9\u7f51\u7ad9\u670d\u52a1\u5668\u9020\u6210\u8fc7\u5927\u7684\u8d1f\u8377\u3002<\/li>\n<li>\u53cd\u722c\u673a\u5236\uff1a\u6709\u4e9b\u7f51\u7ad9\u4f1a\u91c7\u53d6\u4e00\u4e9b\u53cd\u722c\u866b\u7684\u6280\u672f\u624b\u6bb5\uff0c\u4f8b\u5982\u9a8c\u8bc1\u7801\u3001IP\u5c01\u9501\u7b49\uff0c\u9700\u8981\u76f8\u5e94\u7684\u5904\u7406\u65b9\u5f0f\u3002<\/li>\n<li>\u6587\u4ef6\u547d\u540d\u548c\u7ba1\u7406\uff1a\u5bf9\u4e0b\u8f7d\u7684\u56fe\u7247\u8fdb\u884c\u9002\u5f53\u7684\u547d\u540d\u548c\u7ba1\u7406\uff0c\u907f\u514d\u6df7\u4e71\u548c\u91cd\u590d\u4e0b\u8f7d\u3002<\/li>\n<\/ol>\n<p>\u8bf7\u6ce8\u610f\u9075\u5b88\u6cd5\u5f8b\u6cd5\u89c4\u548c\u7f51\u7ad9\u7684\u89c4\u5b9a\uff0c\u4ee5\u53ca\u5c0a\u91cd\u4ed6\u4eba\u7684\u7248\u6743\u548c\u9690\u79c1\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u722c\u866b\u5b9e\u73b0\u722c\u53d6\u7f51\u7ad9\u56fe\u7247\u4e3b\u8981\u5305\u62ec\u4ee5\u4e0b\u51e0\u4e2a\u6b65\u9aa4\uff1a\u9009\u62e9\u5408\u9002\u7684\u5e93\u3001\u53d1\u9001\u8bf7\u6c42\u3001\u89e3\u6790\u5185\u5bb9\u3001\u83b7\u53d6\u56fe\u7247\u94fe\u63a5\u3001\u4e0b\u8f7d\u56fe\u7247 [&hellip;]","protected":false},"author":3,"featured_media":176377,"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\/176358"}],"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=176358"}],"version-history":[{"count":0,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/176358\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/176377"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=176358"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=176358"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=176358"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}