{"id":932402,"date":"2024-12-26T17:57:27","date_gmt":"2024-12-26T09:57:27","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/932402.html"},"modified":"2024-12-26T17:57:29","modified_gmt":"2024-12-26T09:57:29","slug":"python%e5%a6%82%e4%bd%95%e7%88%ac%e5%9b%be%e7%89%87","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/932402.html","title":{"rendered":"python\u5982\u4f55\u722c\u56fe\u7247"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25070252\/f355f022-2aef-48b7-bec2-19541448bc5e.webp\" alt=\"python\u5982\u4f55\u722c\u56fe\u7247\" \/><\/p>\n<p><p> <strong>\u4f7f\u7528Python\u722c\u53d6\u56fe\u7247\u7684\u6b65\u9aa4\u5305\u62ec\uff1a\u9009\u62e9\u5408\u9002\u7684\u722c\u866b\u5e93\u3001\u89e3\u6790\u7f51\u9875\u83b7\u53d6\u56fe\u7247URL\u3001\u4e0b\u8f7d\u56fe\u7247\u5230\u672c\u5730\u3001\u5904\u7406\u5f02\u5e38\u60c5\u51b5\u3002\u4e00\u4e2a\u5e38\u7528\u7684\u5e93\u662fBeautifulSoup\uff0c\u5b83\u53ef\u4ee5\u5e2e\u52a9\u89e3\u6790HTML\u6587\u6863\u3002\u4e3a\u4e86\u4e0b\u8f7d\u56fe\u7247\uff0crequests\u5e93\u662f\u4e00\u4e2a\u4e0d\u9519\u7684\u9009\u62e9\uff0c\u56e0\u4e3a\u5b83\u7b80\u5355\u6613\u7528\u4e14\u529f\u80fd\u5f3a\u5927\u3002<\/strong><\/p>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u4e86\u89e3\u5982\u4f55\u4f7f\u7528Python\u5e93\u6765\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u3002BeautifulSoup\u662f\u4e00\u4e2a\u975e\u5e38\u53d7\u6b22\u8fce\u7684\u5e93\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u8f7b\u677e\u5730\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u6570\u636e\u3002\u5b83\u4e0erequests\u5e93\u7ed3\u5408\u4f7f\u7528\uff0c\u53ef\u4ee5\u5feb\u901f\u6293\u53d6\u7f51\u9875\u5185\u5bb9\u5e76\u89e3\u6790\u51fa\u6211\u4eec\u9700\u8981\u7684\u56fe\u7247URL\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u9009\u62e9\u5408\u9002\u7684\u722c\u866b\u5e93<\/h3>\n<\/p>\n<p><p>Python\u6709\u8bb8\u591a\u5e93\u53ef\u4ee5\u7528\u4e8e\u7f51\u9875\u6293\u53d6\uff0c\u5982BeautifulSoup\u3001Scrapy\u3001Selenium\u7b49\u3002\u5bf9\u4e8e\u521d\u5b66\u8005\u6216\u5c0f\u578b\u9879\u76ee\uff0cBeautifulSoup\u662f\u4e00\u4e2a\u4e0d\u9519\u7684\u9009\u62e9\uff0c\u56e0\u4e3a\u5b83\u7b80\u5355\u4e14\u529f\u80fd\u8db3\u591f\u5f3a\u5927\u3002Scrapy\u9002\u7528\u4e8e\u66f4\u590d\u6742\u7684\u9879\u76ee\uff0c\u800cSelenium\u5219\u53ef\u4ee5\u5904\u7406\u52a8\u6001\u7f51\u9875\u3002<\/p>\n<\/p>\n<ol>\n<li>\n<p><strong>BeautifulSoup<\/strong>\uff1a\u8fd9\u662f\u4e00\u4e2a\u7528\u4e8e\u4eceHTML\u548cXML\u6587\u4ef6\u4e2d\u63d0\u53d6\u6570\u636e\u7684\u5e93\uff0c\u8bed\u6cd5\u7b80\u5355\uff0c\u975e\u5e38\u9002\u5408\u521d\u5b66\u8005\u4f7f\u7528\u3002\u5176\u6838\u5fc3\u529f\u80fd\u662f\u89e3\u6790\u7f51\u9875\u5e76\u63d0\u53d6\u6570\u636e\u3002<\/p>\n<\/p>\n<\/li>\n<li>\n<p><strong>Requests<\/strong>\uff1a\u8fd9\u4e2a\u5e93\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\u3002\u5b83\u53ef\u4ee5\u8f7b\u677e\u83b7\u53d6\u7f51\u9875\u7684HTML\u4ee3\u7801\uff0c\u4e0eBeautifulSoup\u914d\u5408\u4f7f\u7528\u6548\u679c\u6781\u4f73\u3002<\/p>\n<\/p>\n<\/li>\n<li>\n<p><strong>Scrapy<\/strong>\uff1a\u8fd9\u662f\u4e00\u4e2a\u66f4\u9ad8\u7ea7\u7684\u722c\u866b\u6846\u67b6\uff0c\u9002\u5408\u7528\u4e8e\u5927\u89c4\u6a21\u6293\u53d6\u548c\u5904\u7406\u590d\u6742\u7684\u7f51\u9875\u7ed3\u6784\u3002\u5176\u529f\u80fd\u5f3a\u5927\u4f46\u5b66\u4e60\u66f2\u7ebf\u8f83\u9661\u3002<\/p>\n<\/p>\n<\/li>\n<\/ol>\n<p><h3>\u4e8c\u3001\u89e3\u6790\u7f51\u9875\u83b7\u53d6\u56fe\u7247URL<\/h3>\n<\/p>\n<p><p>\u89e3\u6790\u7f51\u9875\u7684\u6838\u5fc3\u5728\u4e8e\u627e\u5230\u76ee\u6807\u56fe\u7247\u7684URL\u3002\u5728\u5927\u591a\u6570\u60c5\u51b5\u4e0b\uff0c\u56fe\u7247\u7684URL\u662f\u5d4c\u5165\u5728HTML\u7684<code>&lt;img&gt;<\/code>\u6807\u7b7e\u4e2d\u7684\u3002\u56e0\u6b64\uff0c\u6211\u4eec\u9700\u8981\u89e3\u6790HTML\uff0c\u63d0\u53d6\u8fd9\u4e9b\u6807\u7b7e\u5e76\u83b7\u53d6\u5176\u4e2d\u7684<code>src<\/code>\u5c5e\u6027\u3002<\/p>\n<\/p>\n<ol>\n<li>\n<p><strong>\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML<\/strong>\uff1a\u9996\u5148\uff0c\u6211\u4eec\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\uff0c\u7136\u540e\u4f7f\u7528BeautifulSoup\u89e3\u6790\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<p>url = &quot;http:\/\/example.com&quot;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>soup = BeautifulSoup(response.text, &#39;html.parser&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u63d0\u53d6\u56fe\u7247URL<\/strong>\uff1a\u4e00\u65e6\u89e3\u6790\u5b8c\u6210\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u7684\u5404\u79cd\u67e5\u627e\u529f\u80fd\u6765\u63d0\u53d6\u56fe\u7247\u7684URL\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">images = soup.find_all(&#39;img&#39;)<\/p>\n<p>img_urls = [img[&#39;src&#39;] for img in images if &#39;src&#39; in img.attrs]<\/p>\n<p><\/code><\/pre>\n<\/p>\n<\/li>\n<\/ol>\n<p><h3>\u4e09\u3001\u4e0b\u8f7d\u56fe\u7247\u5230\u672c\u5730<\/h3>\n<\/p>\n<p><p>\u83b7\u53d6\u5230\u56fe\u7247\u7684URL\u540e\uff0c\u4e0b\u4e00\u6b65\u5c31\u662f\u5c06\u8fd9\u4e9b\u56fe\u7247\u4e0b\u8f7d\u5230\u672c\u5730\u3002\u6211\u4eec\u53ef\u4ee5\u518d\u6b21\u4f7f\u7528requests\u5e93\u6765\u5b8c\u6210\u8fd9\u9879\u4efb\u52a1\u3002<\/p>\n<\/p>\n<ol>\n<li>\n<p><strong>\u4e0b\u8f7d\u56fe\u7247<\/strong>\uff1a\u5bf9\u4e8e\u6bcf\u4e00\u4e2a\u56fe\u7247URL\uff0c\u6211\u4eec\u53ef\u4ee5\u53d1\u9001\u4e00\u4e2a\u8bf7\u6c42\u5e76\u5c06\u54cd\u5e94\u7684\u5185\u5bb9\u4fdd\u5b58\u4e3a\u6587\u4ef6\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import os<\/p>\n<p>for i, img_url in enumerate(img_urls):<\/p>\n<p>    img_data = requests.get(img_url).content<\/p>\n<p>    with open(f&#39;image_{i}.jpg&#39;, &#39;wb&#39;) as handler:<\/p>\n<p>        handler.write(img_data)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u521b\u5efa\u76ee\u5f55<\/strong>\uff1a\u4e3a\u4e86\u65b9\u4fbf\u7ba1\u7406\uff0c\u6211\u4eec\u53ef\u4ee5\u5728\u4e0b\u8f7d\u56fe\u7247\u4e4b\u524d\u521b\u5efa\u4e00\u4e2a\u76ee\u5f55\u6765\u5b58\u653e\u8fd9\u4e9b\u56fe\u7247\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">os.makedirs(&#39;images&#39;, exist_ok=True)<\/p>\n<p>for i, img_url in enumerate(img_urls):<\/p>\n<p>    img_data = requests.get(img_url).content<\/p>\n<p>    with open(f&#39;images\/image_{i}.jpg&#39;, &#39;wb&#39;) as handler:<\/p>\n<p>        handler.write(img_data)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<\/li>\n<\/ol>\n<p><h3>\u56db\u3001\u5904\u7406\u5f02\u5e38\u60c5\u51b5<\/h3>\n<\/p>\n<p><p>\u5728\u5b9e\u9645\u64cd\u4f5c\u4e2d\uff0c\u722c\u866b\u7a0b\u5e8f\u53ef\u80fd\u4f1a\u9047\u5230\u5404\u79cd\u5f02\u5e38\u60c5\u51b5\uff0c\u5982\u8bf7\u6c42\u5931\u8d25\u3001\u56fe\u7247URL\u65e0\u6548\u3001\u7f51\u7edc\u4e2d\u65ad\u7b49\u3002\u56e0\u6b64\uff0c\u6211\u4eec\u9700\u8981\u6dfb\u52a0\u4e00\u4e9b\u5f02\u5e38\u5904\u7406\u673a\u5236\u4ee5\u63d0\u9ad8\u7a0b\u5e8f\u7684\u7a33\u5b9a\u6027\u3002<\/p>\n<\/p>\n<ol>\n<li>\n<p><strong>\u5f02\u5e38\u5904\u7406<\/strong>\uff1a\u4f7f\u7528try-except\u5757\u6765\u6355\u83b7\u548c\u5904\u7406\u5f02\u5e38\u3002\u4f8b\u5982\uff0c\u5728\u4e0b\u8f7d\u56fe\u7247\u65f6\uff0c\u6211\u4eec\u53ef\u80fd\u4f1a\u9047\u5230\u8bf7\u6c42\u5931\u8d25\u7684\u60c5\u51b5\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">try:<\/p>\n<p>    response = requests.get(img_url)<\/p>\n<p>    response.r<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>se_for_status()  # \u68c0\u67e5\u8bf7\u6c42\u662f\u5426\u6210\u529f<\/p>\n<p>except requests.exceptions.RequestException as e:<\/p>\n<p>    print(f&quot;Error downloading {img_url}: {e}&quot;)<\/p>\n<p>    continue<\/p>\n<p><\/code><\/pre>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u65e5\u5fd7\u8bb0\u5f55<\/strong>\uff1a\u4e3a\u65b9\u4fbf\u8c03\u8bd5\u548c\u7ef4\u62a4\uff0c\u53ef\u4ee5\u4f7f\u7528Python\u7684logging\u6a21\u5757\u8bb0\u5f55\u7a0b\u5e8f\u7684\u8fd0\u884c\u4fe1\u606f\u548c\u9519\u8bef\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import logging<\/p>\n<p>logging.basicConfig(filename=&#39;image_scraper.log&#39;, level=logging.INFO)<\/p>\n<p>logging.info(f&quot;Downloaded {img_url}&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<\/li>\n<\/ol>\n<p><h3>\u4e94\u3001\u4f18\u5316\u548c\u63d0\u5347\u6027\u80fd<\/h3>\n<\/p>\n<p><p>\u5728\u5904\u7406\u5927\u91cf\u56fe\u7247\u6216\u590d\u6742\u7f51\u9875\u65f6\uff0c\u53ef\u80fd\u9700\u8981\u4f18\u5316\u548c\u63d0\u5347\u7a0b\u5e8f\u6027\u80fd\u3002\u53ef\u4ee5\u8003\u8651\u4ee5\u4e0b\u51e0\u4e2a\u65b9\u9762\uff1a<\/p>\n<\/p>\n<ol>\n<li>\n<p><strong>\u4f7f\u7528\u591a\u7ebf\u7a0b\u6216\u5f02\u6b65IO<\/strong>\uff1aPython\u7684\u591a\u7ebf\u7a0b\u548c\u5f02\u6b65IO\u53ef\u4ee5\u52a0\u901f\u722c\u866b\u7a0b\u5e8f\uff0c\u5c24\u5176\u662f\u5728I\/O\u5bc6\u96c6\u578b\u4efb\u52a1\u4e2d\u3002\u53ef\u4ee5\u4f7f\u7528<code>concurrent.futures<\/code>\u6a21\u5757\u6216<code>asyncio<\/code>\u5e93\u3002<\/p>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u9650\u5236\u8bf7\u6c42\u9891\u7387<\/strong>\uff1a\u4e3a\u4e86\u907f\u514d\u5bf9\u76ee\u6807\u7f51\u7ad9\u9020\u6210\u8fc7\u5927\u538b\u529b\uff0c\u53ef\u4ee5\u5728\u8bf7\u6c42\u4e4b\u95f4\u52a0\u5165\u5ef6\u65f6\u3002<\/p>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u7f13\u5b58\u673a\u5236<\/strong>\uff1a\u5982\u679c\u9700\u8981\u591a\u6b21\u4e0b\u8f7d\u76f8\u540c\u7684\u56fe\u7247\uff0c\u53ef\u4ee5\u5f15\u5165\u7f13\u5b58\u673a\u5236\uff0c\u907f\u514d\u91cd\u590d\u4e0b\u8f7d\u3002<\/p>\n<\/p>\n<\/li>\n<\/ol>\n<p><p>\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u4f60\u53ef\u4ee5\u4f7f\u7528Python\u6709\u6548\u5730\u722c\u53d6\u56fe\u7247\u3002\u8bb0\u4f4f\u5728\u722c\u53d6\u8fc7\u7a0b\u4e2d\u8981\u9075\u5faa\u76f8\u5173\u6cd5\u5f8b\u6cd5\u89c4\u548c\u7f51\u7ad9\u7684robots.txt\u534f\u8bae\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u6293\u53d6\u7f51\u9875\u4e0a\u7684\u56fe\u7247\uff1f<\/strong><br \/>\u4f7f\u7528Python\u6293\u53d6\u56fe\u7247\u7684\u57fa\u672c\u6b65\u9aa4\u5305\u62ec\u9009\u62e9\u5408\u9002\u7684\u5e93\uff0c\u5982requests\u548cBeautifulSoup\u3002\u9996\u5148\uff0c\u901a\u8fc7requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u7136\u540e\u5229\u7528BeautifulSoup\u89e3\u6790HTML\uff0c\u627e\u5230\u56fe\u7247\u7684URL\u3002\u63a5\u4e0b\u6765\uff0c\u53ef\u4ee5\u4f7f\u7528requests\u5e93\u4e0b\u8f7d\u8fd9\u4e9b\u56fe\u7247\uff0c\u5e76\u4fdd\u5b58\u5230\u672c\u5730\u3002\u786e\u4fdd\u5728\u6293\u53d6\u65f6\u9075\u5faa\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6\u548c\u7248\u6743\u89c4\u5b9a\u3002<\/p>\n<p><strong>\u5728\u6293\u53d6\u56fe\u7247\u65f6\uff0c\u5982\u4f55\u5904\u7406\u53cd\u722c\u866b\u673a\u5236\uff1f<\/strong><br \/>\u8bb8\u591a\u7f51\u7ad9\u4f1a\u4f7f\u7528\u53cd\u722c\u866b\u673a\u5236\u6765\u963b\u6b62\u81ea\u52a8\u5316\u6293\u53d6\u3002\u53ef\u4ee5\u901a\u8fc7\u8bbe\u7f6e\u8bf7\u6c42\u5934\uff08\u5982User-Agent\uff09\u6765\u4f2a\u88c5\u6210\u666e\u901a\u7528\u6237\u8bf7\u6c42\u3002\u6b64\u5916\uff0c\u4f7f\u7528\u968f\u673a\u65f6\u95f4\u95f4\u9694\u8fdb\u884c\u8bf7\u6c42\u3001\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u6216\u8005\u4f7f\u7528\u4ee3\u7406IP\u7b49\u65b9\u6cd5\u90fd\u6709\u52a9\u4e8e\u7ed5\u8fc7\u53cd\u722c\u866b\u673a\u5236\u3002\u52a1\u5fc5\u6ce8\u610f\uff0c\u9075\u5faa\u6cd5\u5f8b\u6cd5\u89c4\u548c\u7f51\u7ad9\u7684\u4f7f\u7528\u6761\u6b3e\u662f\u975e\u5e38\u91cd\u8981\u7684\u3002<\/p>\n<p><strong>\u6293\u53d6\u7279\u5b9a\u7c7b\u578b\u7684\u56fe\u7247\uff08\u5982JPEG\u6216PNG\uff09\u65f6\uff0c\u6709\u54ea\u4e9b\u6ce8\u610f\u4e8b\u9879\uff1f<\/strong><br \/>\u5728\u6293\u53d6\u7279\u5b9a\u7c7b\u578b\u7684\u56fe\u7247\u65f6\uff0c\u53ef\u4ee5\u5728\u89e3\u6790HTML\u65f6\u6dfb\u52a0\u6761\u4ef6\u7b5b\u9009\uff0c\u4f8b\u5982\u53ea\u9009\u62e9\u4ee5\u7279\u5b9a\u540e\u7f00\u7ed3\u5c3e\u7684\u56fe\u7247\u94fe\u63a5\u3002\u6b64\u5916\uff0c\u786e\u4fdd\u5904\u7406\u56fe\u7247\u7684\u4e0b\u8f7d\u8def\u5f84\u548c\u6587\u4ef6\u547d\u540d\uff0c\u4ee5\u907f\u514d\u6587\u4ef6\u8986\u76d6\u6216\u6df7\u6dc6\u3002\u5efa\u8bae\u68c0\u67e5\u56fe\u7247\u7684\u5927\u5c0f\u548c\u683c\u5f0f\uff0c\u4ee5\u786e\u4fdd\u4e0b\u8f7d\u7684\u6587\u4ef6\u7b26\u5408\u9884\u671f\u7684\u6807\u51c6\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u4f7f\u7528Python\u722c\u53d6\u56fe\u7247\u7684\u6b65\u9aa4\u5305\u62ec\uff1a\u9009\u62e9\u5408\u9002\u7684\u722c\u866b\u5e93\u3001\u89e3\u6790\u7f51\u9875\u83b7\u53d6\u56fe\u7247URL\u3001\u4e0b\u8f7d\u56fe\u7247\u5230\u672c\u5730\u3001\u5904\u7406\u5f02\u5e38\u60c5\u51b5\u3002\u4e00 [&hellip;]","protected":false},"author":3,"featured_media":932407,"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\/932402"}],"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=932402"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/932402\/revisions"}],"predecessor-version":[{"id":932409,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/932402\/revisions\/932409"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/932407"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=932402"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=932402"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=932402"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}