{"id":960276,"date":"2024-12-27T03:48:21","date_gmt":"2024-12-26T19:48:21","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/960276.html"},"modified":"2024-12-27T03:48:23","modified_gmt":"2024-12-26T19:48:23","slug":"python%e4%b8%ad%e5%a6%82%e4%bd%95%e7%88%ac%e8%99%ab%e5%9b%be%e7%89%87","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/960276.html","title":{"rendered":"python\u4e2d\u5982\u4f55\u722c\u866b\u56fe\u7247"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25102826\/d4754d5d-f90a-4ae9-bbf5-1814a9bb972c.webp\" alt=\"python\u4e2d\u5982\u4f55\u722c\u866b\u56fe\u7247\" \/><\/p>\n<p><p> \u5728Python\u4e2d\u8fdb\u884c\u56fe\u7247\u722c\u866b\uff0c\u4e3b\u8981\u6b65\u9aa4\u5305\u62ec\uff1a<strong>\u9009\u62e9\u5408\u9002\u7684\u722c\u866b\u5e93\u3001\u89e3\u6790\u7f51\u9875\u83b7\u53d6\u56fe\u7247\u94fe\u63a5\u3001\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u56fe\u7247<\/strong>\u3002\u4e0b\u9762\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u8fd9\u4e9b\u6b65\u9aa4\u4e2d\u7684\u6bcf\u4e00\u70b9\u3002<\/p>\n<\/p>\n<p><p>\u9996\u5148\uff0c<strong>\u9009\u62e9\u5408\u9002\u7684\u722c\u866b\u5e93<\/strong>\u662f\u8fdb\u884c\u56fe\u7247\u722c\u866b\u7684\u7b2c\u4e00\u6b65\u3002Python\u63d0\u4f9b\u4e86\u8bb8\u591a\u5f3a\u5927\u7684\u722c\u866b\u5e93\uff0c\u5982<code>requests<\/code>\u3001<code>BeautifulSoup<\/code>\u3001<code>Scrapy<\/code>\u3001<code>Selenium<\/code>\u7b49\u3002\u5176\u4e2d\uff0c<code>requests<\/code>\u548c<code>BeautifulSoup<\/code>\u9002\u5408\u7528\u4e8e\u7b80\u5355\u7684\u722c\u866b\u4efb\u52a1\uff0c\u800c<code>Scrapy<\/code>\u548c<code>Selenium<\/code>\u5219\u9002\u5408\u66f4\u590d\u6742\u7684\u9879\u76ee\u3002<\/p>\n<\/p>\n<p><p>\u63a5\u4e0b\u6765\uff0c<strong>\u89e3\u6790\u7f51\u9875\u83b7\u53d6\u56fe\u7247\u94fe\u63a5<\/strong>\u662f\u722c\u866b\u7684\u6838\u5fc3\u4efb\u52a1\u4e4b\u4e00\u3002\u901a\u8fc7<code>requests<\/code>\u5e93\u8bf7\u6c42\u7f51\u9875\u540e\uff0c\u4f7f\u7528<code>BeautifulSoup<\/code>\u89e3\u6790HTML\u6587\u6863\uff0c\u63d0\u53d6\u51fa\u5305\u542b\u56fe\u7247\u7684\u6807\u7b7e\uff08\u5982<code>&lt;img&gt;<\/code>\u6807\u7b7e\uff09\uff0c\u5e76\u83b7\u53d6\u5176<code>src<\/code>\u5c5e\u6027\u503c\uff0c\u8fd9\u5c31\u662f\u56fe\u7247\u7684URL\u3002<\/p>\n<\/p>\n<p><p>\u6700\u540e\uff0c<strong>\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u56fe\u7247<\/strong>\u9700\u8981\u901a\u8fc7\u56fe\u7247\u7684URL\u53d1\u9001\u8bf7\u6c42\uff0c\u83b7\u53d6\u56fe\u7247\u7684\u4e8c\u8fdb\u5236\u6570\u636e\uff0c\u7136\u540e\u5c06\u5176\u5199\u5165\u6587\u4ef6\u4fdd\u5b58\u5230\u672c\u5730\u3002\u53ef\u4ee5\u4f7f\u7528<code>requests.get()<\/code>\u65b9\u6cd5\u83b7\u53d6\u56fe\u7247\u5185\u5bb9\uff0c\u5e76\u7528Python\u7684\u6587\u4ef6\u64cd\u4f5c\u65b9\u6cd5\u5c06\u56fe\u7247\u4fdd\u5b58\u5230\u6307\u5b9a\u76ee\u5f55\u3002<\/p>\n<\/p>\n<hr>\n<p><p>\u4e00\u3001\u9009\u62e9\u5408\u9002\u7684\u722c\u866b\u5e93<\/p>\n<\/p>\n<p><p>\u5728\u8fdb\u884c\u56fe\u7247\u722c\u866b\u4e4b\u524d\uff0c\u9009\u62e9\u4e00\u4e2a\u5408\u9002\u7684\u722c\u866b\u5e93\u662f\u5fc5\u4e0d\u53ef\u5c11\u7684\u3002\u4e0d\u540c\u7684\u722c\u866b\u4efb\u52a1\u53ef\u80fd\u9700\u8981\u4f7f\u7528\u4e0d\u540c\u7684\u5e93\u6765\u5b9e\u73b0\u3002<\/p>\n<\/p>\n<ol>\n<li>\n<p><strong>Requests\u548cBeautifulSoup<\/strong><\/p>\n<\/p>\n<p><p><code>requests<\/code>\u662f\u4e00\u4e2a\u7b80\u5355\u800c\u5f3a\u5927\u7684HTTP\u5e93\uff0c\u9002\u5408\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3002\u4f7f\u7528<code>requests<\/code>\u53ef\u4ee5\u8f7b\u677e\u5730\u53d1\u9001GET\u3001POST\u7b49\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u7684HTML\u6587\u6863\u3002<\/p>\n<\/p>\n<p><p><code>BeautifulSoup<\/code>\u662f\u4e00\u4e2a\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\u7684\u5e93\u3002\u5b83\u63d0\u4f9b\u7b80\u5355\u7684API\uff0c\u53ef\u4ee5\u4eceHTML\u4e2d\u5feb\u901f\u63d0\u53d6\u6570\u636e\u3002\u4e0e<code>requests<\/code>\u7ed3\u5408\u4f7f\u7528\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u89e3\u6790\u548c\u5904\u7406\u7f51\u9875\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><p>\u8fd9\u4e24\u4e2a\u5e93\u975e\u5e38\u9002\u5408\u7528\u4e8e\u7b80\u5355\u7684\u56fe\u7247\u722c\u866b\u4efb\u52a1\u3002\u901a\u8fc7<code>requests<\/code>\u83b7\u53d6\u7f51\u9875HTML\u5185\u5bb9\u540e\uff0c\u4f7f\u7528<code>BeautifulSoup<\/code>\u63d0\u53d6\u51fa\u56fe\u7247\u94fe\u63a5\u3002<\/p>\n<\/p>\n<\/li>\n<li>\n<p><strong>Scrapy<\/strong><\/p>\n<\/p>\n<p><p><code>Scrapy<\/code>\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u722c\u866b\u6846\u67b6\uff0c\u9002\u5408\u4e8e\u6784\u5efa\u590d\u6742\u7684\u722c\u866b\u9879\u76ee\u3002\u4e0e<code>requests<\/code>\u548c<code>BeautifulSoup<\/code>\u76f8\u6bd4\uff0c<code>Scrapy<\/code>\u63d0\u4f9b\u4e86\u66f4\u4e3a\u5168\u9762\u7684\u529f\u80fd\uff0c\u5982\u5f02\u6b65\u8bf7\u6c42\u3001\u6570\u636e\u7ba1\u9053\u3001\u722c\u866b\u7ba1\u7406\u7b49\u3002<\/p>\n<\/p>\n<p><p><code>Scrapy<\/code>\u7684\u5b66\u4e60\u66f2\u7ebf\u76f8\u5bf9\u8f83\u9661\uff0c\u4f46\u4e00\u65e6\u638c\u63e1\uff0c\u80fd\u591f\u6781\u5927\u5730\u63d0\u9ad8\u722c\u866b\u7684\u6548\u7387\u548c\u53ef\u7ef4\u62a4\u6027\u3002\u5728\u9700\u8981\u722c\u53d6\u5927\u91cf\u6570\u636e\u6216\u8fdb\u884c\u590d\u6742\u7684\u6570\u636e\u5904\u7406\u65f6\uff0c<code>Scrapy<\/code>\u662f\u4e00\u4e2a\u4e0d\u9519\u7684\u9009\u62e9\u3002<\/p>\n<\/p>\n<\/li>\n<li>\n<p><strong>Selenium<\/strong><\/p>\n<\/p>\n<p><p><code>Selenium<\/code>\u662f\u4e00\u4e2a\u7528\u4e8e\u81ea\u52a8\u5316\u7f51\u9875\u64cd\u4f5c\u7684\u5de5\u5177\uff0c\u5e38\u7528\u4e8e\u6d4b\u8bd5Web\u5e94\u7528\u7a0b\u5e8f\u3002\u5b83\u53ef\u4ee5\u6a21\u62df\u7528\u6237\u64cd\u4f5c\uff0c\u5982\u70b9\u51fb\u3001\u8f93\u5165\u7b49\uff0c\u5e76\u83b7\u53d6\u52a8\u6001\u52a0\u8f7d\u7684\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><p>\u5728\u5904\u7406\u9700\u8981JavaScript\u6e32\u67d3\u7684\u7f51\u7ad9\u65f6\uff0c<code>Selenium<\/code>\u975e\u5e38\u6709\u7528\u3002\u867d\u7136\u6027\u80fd\u4e0d\u5982<code>Scrapy<\/code>\uff0c\u4f46\u5bf9\u4e8e\u7279\u5b9a\u573a\u666f\uff0c<code>Selenium<\/code>\u53ef\u4ee5\u66f4\u597d\u5730\u5e94\u5bf9\u52a8\u6001\u5185\u5bb9\u3002<\/p>\n<\/p>\n<\/li>\n<\/ol>\n<p><p>\u4e8c\u3001\u89e3\u6790\u7f51\u9875\u83b7\u53d6\u56fe\u7247\u94fe\u63a5<\/p>\n<\/p>\n<p><p>\u5728\u9009\u62e9\u4e86\u5408\u9002\u7684\u5e93\u540e\uff0c\u89e3\u6790\u7f51\u9875\u83b7\u53d6\u56fe\u7247\u94fe\u63a5\u662f\u4e0b\u4e00\u6b65\u9700\u8981\u5b8c\u6210\u7684\u4efb\u52a1\u3002<\/p>\n<\/p>\n<ol>\n<li>\n<p><strong>\u53d1\u9001HTTP\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/strong><\/p>\n<\/p>\n<p><p>\u4f7f\u7528<code>requests<\/code>\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u662f\u89e3\u6790\u7684\u7b2c\u4e00\u6b65\u3002\u53ef\u4ee5\u4f7f\u7528<code>requests.get(url)<\/code>\u65b9\u6cd5\u8bf7\u6c42\u7f51\u9875\uff0c\u5e76\u901a\u8fc7<code>.text<\/code>\u5c5e\u6027\u83b7\u53d6HTML\u6587\u6863\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &quot;https:\/\/example.com&quot;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>html_content = response.text<\/p>\n<p><\/code><\/pre>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML<\/strong><\/p>\n<\/p>\n<p><p><code>BeautifulSoup<\/code>\u63d0\u4f9b\u4e86\u591a\u79cd\u65b9\u6cd5\u6765\u89e3\u6790HTML\u6587\u6863\uff0c\u63d0\u53d6\u6240\u9700\u6570\u636e\u3002\u9996\u5148\uff0c\u9700\u8981\u521b\u5efa\u4e00\u4e2a<code>BeautifulSoup<\/code>\u5bf9\u8c61\uff0c\u4f20\u5165HTML\u5185\u5bb9\u548c\u89e3\u6790\u5668\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>\u7136\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528<code>soup.find_all()<\/code>\u65b9\u6cd5\u627e\u5230\u6240\u6709\u7684<code>&lt;img&gt;<\/code>\u6807\u7b7e\uff0c\u5e76\u83b7\u53d6\u5176<code>src<\/code>\u5c5e\u6027\u503c\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">img_tags = soup.find_all(&#39;img&#39;)<\/p>\n<p>img_urls = [img[&#39;src&#39;] for img in img_tags]<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u6bb5\u4ee3\u7801\u5c06\u63d0\u53d6\u51fa\u9875\u9762\u4e2d\u6240\u6709\u56fe\u7247\u7684\u94fe\u63a5\u3002<\/p>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u5904\u7406\u76f8\u5bf9\u8def\u5f84\u548c\u7edd\u5bf9\u8def\u5f84<\/strong><\/p>\n<\/p>\n<p><p>\u5728\u63d0\u53d6\u56fe\u7247\u94fe\u63a5\u65f6\uff0c\u9700\u8981\u6ce8\u610f\u94fe\u63a5\u662f\u76f8\u5bf9\u8def\u5f84\u8fd8\u662f\u7edd\u5bf9\u8def\u5f84\u3002\u5982\u679c\u662f\u76f8\u5bf9\u8def\u5f84\uff0c\u9700\u8981\u5c06\u5176\u8f6c\u6362\u4e3a\u7edd\u5bf9\u8def\u5f84\u624d\u80fd\u6b63\u786e\u4e0b\u8f7d\u56fe\u7247\u3002<\/p>\n<\/p>\n<p><p>\u53ef\u4ee5\u4f7f\u7528<code>urljoin<\/code>\u51fd\u6570\u6765\u5904\u7406\u8def\u5f84\u95ee\u9898\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from urllib.parse import urljoin<\/p>\n<p>base_url = &quot;https:\/\/example.com&quot;<\/p>\n<p>img_urls = [urljoin(base_url, img_url) for img_url in img_urls]<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u53ef\u4ee5\u786e\u4fdd\u6240\u6709\u56fe\u7247\u94fe\u63a5\u90fd\u662f\u5b8c\u6574\u7684URL\u3002<\/p>\n<\/p>\n<\/li>\n<\/ol>\n<p><p>\u4e09\u3001\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u56fe\u7247<\/p>\n<\/p>\n<p><p>\u83b7\u53d6\u56fe\u7247\u94fe\u63a5\u540e\uff0c\u4e0b\u4e00\u6b65\u662f\u4e0b\u8f7d\u56fe\u7247\u5e76\u5c06\u5176\u4fdd\u5b58\u5230\u672c\u5730\u3002<\/p>\n<\/p>\n<ol>\n<li>\n<p><strong>\u53d1\u9001\u8bf7\u6c42\u83b7\u53d6\u56fe\u7247\u5185\u5bb9<\/strong><\/p>\n<\/p>\n<p><p>\u4f7f\u7528<code>requests.get()<\/code>\u65b9\u6cd5\u53d1\u9001\u8bf7\u6c42\uff0c\u83b7\u53d6\u56fe\u7247\u7684\u4e8c\u8fdb\u5236\u6570\u636e\u3002\u9700\u8981\u6ce8\u610f\u7684\u662f\uff0c\u83b7\u53d6\u56fe\u7247\u5185\u5bb9\u65f6\uff0c\u5e94\u4f7f\u7528<code>.content<\/code>\u5c5e\u6027\u800c\u4e0d\u662f<code>.text<\/code>\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">img_url = img_urls[0]<\/p>\n<p>img_response = requests.get(img_url)<\/p>\n<p>img_data = img_response.content<\/p>\n<p><\/code><\/pre>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u4fdd\u5b58\u56fe\u7247\u5230\u672c\u5730<\/strong><\/p>\n<\/p>\n<p><p>\u4f7f\u7528Python\u7684\u6587\u4ef6\u64cd\u4f5c\u65b9\u6cd5\uff0c\u5c06\u83b7\u53d6\u7684\u4e8c\u8fdb\u5236\u6570\u636e\u5199\u5165\u6587\u4ef6\uff0c\u4fdd\u5b58\u56fe\u7247\u5230\u6307\u5b9a\u76ee\u5f55\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">img_filename = &quot;image.jpg&quot;<\/p>\n<p>with open(img_filename, &#39;wb&#39;) as img_file:<\/p>\n<p>    img_file.write(img_data)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u6bb5\u4ee3\u7801\u5c06\u56fe\u7247\u4fdd\u5b58\u4e3a<code>image.jpg<\/code>\u6587\u4ef6\u3002<\/p>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u6279\u91cf\u4e0b\u8f7d\u5e76\u4fdd\u5b58<\/strong><\/p>\n<\/p>\n<p><p>\u5982\u679c\u9700\u8981\u4e0b\u8f7d\u591a\u4e2a\u56fe\u7247\uff0c\u53ef\u4ee5\u4f7f\u7528\u5faa\u73af\u904d\u5386\u56fe\u7247URL\u5217\u8868\uff0c\u4f9d\u6b21\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">for i, img_url in enumerate(img_urls):<\/p>\n<p>    img_response = requests.get(img_url)<\/p>\n<p>    img_data = img_response.content<\/p>\n<p>    img_filename = f&quot;image_{i}.jpg&quot;<\/p>\n<p>    with open(img_filename, &#39;wb&#39;) as img_file:<\/p>\n<p>        img_file.write(img_data)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u5c06\u6240\u6709\u56fe\u7247\u4fdd\u5b58\u4e3a<code>image_0.jpg<\/code>, <code>image_1.jpg<\/code>, \u7b49\u7b49\u3002<\/p>\n<\/p>\n<\/li>\n<\/ol>\n<p><p>\u56db\u3001\u6ce8\u610f\u4e8b\u9879\u548c\u6700\u4f73\u5b9e\u8df5<\/p>\n<\/p>\n<p><p>\u5728\u8fdb\u884c\u56fe\u7247\u722c\u866b\u65f6\uff0c\u6709\u4e00\u4e9b\u6ce8\u610f\u4e8b\u9879\u548c\u6700\u4f73\u5b9e\u8df5\u9700\u8981\u8003\u8651\uff0c\u4ee5\u786e\u4fdd\u722c\u866b\u7684\u7a33\u5b9a\u6027\u548c\u6548\u7387\u3002<\/p>\n<\/p>\n<ol>\n<li>\n<p><strong>\u5c0a\u91cd\u7f51\u7ad9\u7684robots.txt<\/strong><\/p>\n<\/p>\n<p><p>\u5728\u5f00\u59cb\u722c\u866b\u4e4b\u524d\uff0c\u5e94\u68c0\u67e5\u76ee\u6807\u7f51\u7ad9\u7684<code>robots.txt<\/code>\u6587\u4ef6\uff0c\u786e\u4fdd\u9075\u5faa\u5176\u722c\u866b\u89c4\u5219\u3002<code>robots.txt<\/code>\u6587\u4ef6\u901a\u5e38\u4f4d\u4e8e\u7f51\u7ad9\u7684\u6839\u76ee\u5f55\u4e2d\uff0c\u7528\u4e8e\u544a\u8bc9\u722c\u866b\u54ea\u4e9b\u9875\u9762\u53ef\u4ee5\u6293\u53d6\uff0c\u54ea\u4e9b\u4e0d\u53ef\u4ee5\u3002<\/p>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u8bbe\u7f6e\u9002\u5f53\u7684\u8bf7\u6c42\u5934<\/strong><\/p>\n<\/p>\n<p><p>\u4e3a\u4e86\u907f\u514d\u88ab\u76ee\u6807\u7f51\u7ad9\u8bc6\u522b\u4e3a\u722c\u866b\uff0c\u5e94\u8be5\u5728\u8bf7\u6c42\u4e2d\u8bbe\u7f6e\u9002\u5f53\u7684\u8bf7\u6c42\u5934\uff0c\u5982User-Agent\u3002\u53ef\u4ee5\u4f7f\u7528<code>requests<\/code>\u5e93\u7684<code>headers<\/code>\u53c2\u6570\u8bbe\u7f6e\u8bf7\u6c42\u5934\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">headers = {&#39;User-Agent&#39;: &#39;Mozilla\/5.0&#39;}<\/p>\n<p>response = requests.get(url, headers=headers)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u5b9e\u73b0\u5ef6\u8fdf\u548c\u91cd\u8bd5\u673a\u5236<\/strong><\/p>\n<\/p>\n<p><p>\u5728\u8bf7\u6c42\u9891\u7387\u8fc7\u9ad8\u65f6\uff0c\u53ef\u80fd\u4f1a\u5bfc\u81f4IP\u88ab\u5c01\u7981\u3002\u4e3a\u4e86\u907f\u514d\u8fd9\u79cd\u60c5\u51b5\uff0c\u53ef\u4ee5\u5728\u8bf7\u6c42\u4e4b\u95f4\u6dfb\u52a0\u5ef6\u8fdf\uff0c\u5e76\u5b9e\u73b0\u91cd\u8bd5\u673a\u5236\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import time<\/p>\n<p>for img_url in img_urls:<\/p>\n<p>    try:<\/p>\n<p>        img_response = requests.get(img_url)<\/p>\n<p>        img_data = img_response.content<\/p>\n<p>        # \u4fdd\u5b58\u56fe\u7247\u4ee3\u7801<\/p>\n<p>        time.sleep(1)  # \u5ef6\u8fdf1\u79d2<\/p>\n<p>    except requests.exceptions.RequestException as e:<\/p>\n<p>        print(f&quot;F<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>led to download {img_url}: {e}&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u5904\u7406\u52a8\u6001\u5185\u5bb9<\/strong><\/p>\n<\/p>\n<p><p>\u5bf9\u4e8e\u9700\u8981JavaScript\u6e32\u67d3\u7684\u7f51\u7ad9\uff0c\u53ef\u4ee5\u4f7f\u7528<code>Selenium<\/code>\u6765\u83b7\u53d6\u52a8\u6001\u52a0\u8f7d\u7684\u5185\u5bb9\u3002<code>Selenium<\/code>\u80fd\u591f\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u83b7\u53d6\u5b8c\u6574\u7684\u7f51\u9875\u5185\u5bb9\u3002<\/p>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u4f18\u5316\u4ee3\u7801\u548c\u63d0\u9ad8\u6548\u7387<\/strong><\/p>\n<\/p>\n<p><p>\u5728\u5904\u7406\u5927\u91cf\u56fe\u7247\u65f6\uff0c\u53ef\u4ee5\u4f7f\u7528\u591a\u7ebf\u7a0b\u6216\u5f02\u6b65IO\u6765\u63d0\u9ad8\u4e0b\u8f7d\u6548\u7387\u3002Python\u7684<code>concurrent.futures<\/code>\u548c<code>asyncio<\/code>\u5e93\u63d0\u4f9b\u4e86\u7b80\u4fbf\u7684\u5e76\u53d1\u5904\u7406\u65b9\u6cd5\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from concurrent.futures import ThreadPoolExecutor<\/p>\n<p>def download_image(img_url):<\/p>\n<p>    img_response = requests.get(img_url)<\/p>\n<p>    img_data = img_response.content<\/p>\n<p>    # \u4fdd\u5b58\u56fe\u7247\u4ee3\u7801<\/p>\n<p>with ThreadPoolExecutor(max_workers=5) as executor:<\/p>\n<p>    executor.map(download_image, img_urls)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<\/li>\n<\/ol>\n<p><p>\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\u548c\u6ce8\u610f\u4e8b\u9879\uff0c\u60a8\u53ef\u4ee5\u5728Python\u4e2d\u6709\u6548\u5730\u8fdb\u884c\u56fe\u7247\u722c\u866b\u3002\u9009\u62e9\u5408\u9002\u7684\u5de5\u5177\u548c\u65b9\u6cd5\uff0c\u80fd\u591f\u5e2e\u52a9\u60a8\u5feb\u901f\u3001\u7a33\u5b9a\u5730\u83b7\u53d6\u6240\u9700\u7684\u56fe\u7247\u6570\u636e\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u722c\u53d6\u7f51\u9875\u4e0a\u7684\u56fe\u7247\uff1f<\/strong><br \/>\u8981\u4f7f\u7528Python\u722c\u53d6\u7f51\u9875\u4e0a\u7684\u56fe\u7247\uff0c\u60a8\u53ef\u4ee5\u5229\u7528\u5e93\u5982Requests\u548cBeautifulSoup\u3002\u9996\u5148\uff0c\u4f7f\u7528Requests\u5e93\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\uff0c\u7136\u540e\u7528BeautifulSoup\u89e3\u6790\u8be5\u5185\u5bb9\uff0c\u627e\u5230\u6240\u6709\u56fe\u7247\u7684URL\u3002\u63a5\u4e0b\u6765\uff0c\u60a8\u53ef\u4ee5\u5faa\u73af\u904d\u5386\u8fd9\u4e9bURL\uff0c\u5e76\u4f7f\u7528Requests\u5e93\u4e0b\u8f7d\u56fe\u7247\u3002\u4e3a\u4e86\u63d0\u9ad8\u6548\u7387\uff0c\u8003\u8651\u4f7f\u7528\u591a\u7ebf\u7a0b\u6216\u5f02\u6b65\u8bf7\u6c42\u3002<\/p>\n<p><strong>\u722c\u53d6\u56fe\u7247\u65f6\u5982\u4f55\u5904\u7406\u53cd\u722c\u866b\u673a\u5236\uff1f<\/strong><br \/>\u8bb8\u591a\u7f51\u7ad9\u4f1a\u5b9e\u65bd\u53cd\u722c\u866b\u673a\u5236\u6765\u4fdd\u62a4\u5176\u5185\u5bb9\u3002\u4e3a\u4e86\u6709\u6548\u5e94\u5bf9\u8fd9\u4e9b\u673a\u5236\uff0c\u53ef\u4ee5\u91c7\u7528\u66f4\u6539\u8bf7\u6c42\u5934\u3001\u8bbe\u7f6e\u5408\u9002\u7684\u8bf7\u6c42\u95f4\u9694\u3001\u4f7f\u7528\u4ee3\u7406IP\u7b49\u7b56\u7565\u3002\u6b64\u5916\uff0c\u6a21\u62df\u7528\u6237\u884c\u4e3a\uff0c\u6bd4\u5982\u968f\u673a\u5ef6\u8fdf\u548c\u9875\u9762\u6eda\u52a8\uff0c\u4e5f\u80fd\u5e2e\u52a9\u964d\u4f4e\u88ab\u8bc6\u522b\u4e3a\u722c\u866b\u7684\u98ce\u9669\u3002<\/p>\n<p><strong>\u4e0b\u8f7d\u7684\u56fe\u7247\u5982\u4f55\u8fdb\u884c\u5b58\u50a8\u548c\u7ba1\u7406\uff1f<\/strong><br \/>\u5728\u4e0b\u8f7d\u56fe\u7247\u65f6\uff0c\u60a8\u53ef\u4ee5\u9009\u62e9\u5c06\u5176\u4fdd\u5b58\u5728\u672c\u5730\u6587\u4ef6\u7cfb\u7edf\u7684\u7279\u5b9a\u76ee\u5f55\u4e2d\uff0c\u4f7f\u7528\u56fe\u7247\u7684\u539f\u59cb\u540d\u79f0\u6216\u6839\u636e\u65f6\u95f4\u6233\u91cd\u547d\u540d\u6587\u4ef6\u3002\u6b64\u5916\uff0c\u53ef\u4ee5\u521b\u5efa\u4e00\u4e2a\u6587\u4ef6\u5939\u7ed3\u6784\u6765\u5206\u7c7b\u5b58\u50a8\u4e0d\u540c\u6765\u6e90\u6216\u4e3b\u9898\u7684\u56fe\u7247\uff0c\u786e\u4fdd\u5728\u7ba1\u7406\u5927\u91cf\u56fe\u7247\u65f6\u80fd\u591f\u8fc5\u901f\u627e\u5230\u6240\u9700\u5185\u5bb9\u3002\u4f7f\u7528Python\u7684os\u5e93\u53ef\u4ee5\u65b9\u4fbf\u5730\u5904\u7406\u6587\u4ef6\u548c\u76ee\u5f55\u7684\u64cd\u4f5c\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728Python\u4e2d\u8fdb\u884c\u56fe\u7247\u722c\u866b\uff0c\u4e3b\u8981\u6b65\u9aa4\u5305\u62ec\uff1a\u9009\u62e9\u5408\u9002\u7684\u722c\u866b\u5e93\u3001\u89e3\u6790\u7f51\u9875\u83b7\u53d6\u56fe\u7247\u94fe\u63a5\u3001\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u56fe\u7247\u3002\u4e0b\u9762\u5c06\u8be6\u7ec6 [&hellip;]","protected":false},"author":3,"featured_media":960283,"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\/960276"}],"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=960276"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/960276\/revisions"}],"predecessor-version":[{"id":960284,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/960276\/revisions\/960284"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/960283"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=960276"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=960276"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=960276"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}