{"id":1027117,"date":"2024-12-31T10:48:21","date_gmt":"2024-12-31T02:48:21","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1027117.html"},"modified":"2024-12-31T10:48:23","modified_gmt":"2024-12-31T02:48:23","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e7%88%ac%e8%99%ab%e6%98%8e%e6%98%9f%e5%9b%be%e7%89%87","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1027117.html","title":{"rendered":"\u5982\u4f55\u7528python\u722c\u866b\u660e\u661f\u56fe\u7247"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-docs.pingcode.com\/wp-content\/uploads\/2024\/12\/48d0ee92-0462-46ad-9483-d63e81e638dd.webp?x-oss-process=image\/auto-orient,1\/format,webp\" alt=\"\u5982\u4f55\u7528python\u722c\u866b\u660e\u661f\u56fe\u7247\" \/><\/p>\n<p><p> <strong>\u7528Python\u722c\u53d6\u660e\u661f\u56fe\u7247\u7684\u6b65\u9aa4\u4e3b\u8981\u5305\u62ec\uff1a\u9009\u62e9\u76ee\u6807\u7f51\u7ad9\u3001\u89e3\u6790HTML\u83b7\u53d6\u56fe\u7247\u94fe\u63a5\u3001\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u56fe\u7247\u3001\u5904\u7406\u53cd\u722c\u673a\u5236\u3002\u9996\u5148\uff0c\u9009\u62e9\u4e00\u4e2a\u5305\u542b\u660e\u661f\u56fe\u7247\u7684\u7f51\u7ad9\uff0c\u89e3\u6790\u5176HTML\uff0c\u83b7\u53d6\u6240\u6709\u56fe\u7247\u94fe\u63a5\uff0c\u7136\u540e\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u8fd9\u4e9b\u56fe\u7247\u3002\u6700\u540e\uff0c\u8003\u8651\u7f51\u7ad9\u7684\u53cd\u722c\u673a\u5236\uff0c\u907f\u514d\u88ab\u5c01\u7981\u3002<\/strong><\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u9009\u62e9\u76ee\u6807\u7f51\u7ad9<\/h3>\n<\/p>\n<p><p>\u9009\u62e9\u4e00\u4e2a\u5305\u542b\u660e\u661f\u56fe\u7247\u7684\u7f51\u7ad9\u662f\u722c\u866b\u7684\u7b2c\u4e00\u6b65\u3002\u5e38\u89c1\u7684\u7f51\u7ad9\u5305\u62ec\u767e\u5ea6\u56fe\u7247\u3001\u8c37\u6b4c\u56fe\u7247\u3001\u793e\u4ea4\u5a92\u4f53\u5e73\u53f0\u7b49\u3002\u6ce8\u610f\u9009\u62e9\u90a3\u4e9b\u5141\u8bb8\u722c\u866b\u8bbf\u95ee\u7684\u7f51\u7ad9\uff0c\u907f\u514d\u6cd5\u5f8b\u98ce\u9669\u3002<\/p>\n<\/p>\n<p><h3>\u4e8c\u3001\u89e3\u6790HTML\u83b7\u53d6\u56fe\u7247\u94fe\u63a5<\/h3>\n<\/p>\n<p><p>\u4e00\u65e6\u9009\u62e9\u4e86\u76ee\u6807\u7f51\u7ad9\uff0c\u63a5\u4e0b\u6765\u5c31\u662f\u89e3\u6790HTML\u4ee5\u83b7\u53d6\u56fe\u7247\u94fe\u63a5\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u7684<code>requests<\/code>\u5e93\u6765\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u518d\u7528<code>BeautifulSoup<\/code>\u6765\u89e3\u6790HTML\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<h2><strong>\u76ee\u6807\u7f51\u5740<\/strong><\/h2>\n<p>url = &#39;https:\/\/www.example.com&#39;<\/p>\n<h2><strong>\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/strong><\/h2>\n<p>response = requests.get(url)<\/p>\n<p>html_content = response.content<\/p>\n<h2><strong>\u89e3\u6790HTML<\/strong><\/h2>\n<p>soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<h2><strong>\u67e5\u627e\u6240\u6709\u56fe\u7247\u6807\u7b7e<\/strong><\/h2>\n<p>images = soup.find_all(&#39;img&#39;)<\/p>\n<h2><strong>\u83b7\u53d6\u56fe\u7247\u94fe\u63a5<\/strong><\/h2>\n<p>image_urls = [img[&#39;src&#39;] for img in images]<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u56fe\u7247<\/h3>\n<\/p>\n<p><p>\u83b7\u53d6\u56fe\u7247\u94fe\u63a5\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528<code>requests<\/code>\u5e93\u4e0b\u8f7d\u56fe\u7247\u5e76\u4fdd\u5b58\u5230\u672c\u5730\u3002<\/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>if not os.path.exists(&#39;images&#39;):<\/p>\n<p>    os.makedirs(&#39;images&#39;)<\/p>\n<h2><strong>\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u56fe\u7247<\/strong><\/h2>\n<p>for i, image_url in enumerate(image_urls):<\/p>\n<p>    response = requests.get(image_url)<\/p>\n<p>    with open(f&#39;images\/image_{i}.jpg&#39;, &#39;wb&#39;) as file:<\/p>\n<p>        file.write(response.content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u56db\u3001\u5904\u7406\u53cd\u722c\u673a\u5236<\/h3>\n<\/p>\n<p><p>\u8bb8\u591a\u7f51\u7ad9\u4f1a\u6709\u53cd\u722c\u673a\u5236\u6765\u9632\u6b62\u5927\u91cf\u7684\u81ea\u52a8\u5316\u8bf7\u6c42\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u65b9\u6cd5\u6765\u5904\u7406\u8fd9\u4e9b\u95ee\u9898\uff1a<\/p>\n<\/p>\n<ol>\n<li><strong>\u8bbe\u7f6e\u8bf7\u6c42\u5934<\/strong>\uff1a\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u907f\u514d\u88ab\u8bc6\u522b\u4e3a\u722c\u866b\u3002<\/li>\n<li><strong>\u4f7f\u7528\u4ee3\u7406<\/strong>\uff1a\u901a\u8fc7\u4ee3\u7406\u670d\u52a1\u5668\u53d1\u9001\u8bf7\u6c42\uff0c\u907f\u514dIP\u88ab\u5c01\u7981\u3002<\/li>\n<li><strong>\u8bbe\u7f6e\u5ef6\u65f6<\/strong>\uff1a\u5728\u8bf7\u6c42\u4e4b\u95f4\u8bbe\u7f6e\u968f\u673a\u5ef6\u65f6\uff0c\u907f\u514d\u9891\u7e41\u8bf7\u6c42\u3002<\/li>\n<\/ol>\n<p><pre><code class=\"language-python\">import time<\/p>\n<p>import random<\/p>\n<p>headers = {<\/p>\n<p>    &#39;User-Agent&#39;: &#39;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/58.0.3029.110 Safari\/537.36&#39;<\/p>\n<p>}<\/p>\n<p>for i, image_url in enumerate(image_urls):<\/p>\n<p>    # \u8bbe\u7f6e\u5ef6\u65f6<\/p>\n<p>    time.sleep(random.uniform(1, 3))<\/p>\n<p>    response = requests.get(image_url, headers=headers)<\/p>\n<p>    with open(f&#39;images\/image_{i}.jpg&#39;, &#39;wb&#39;) as file:<\/p>\n<p>        file.write(response.content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e94\u3001\u5904\u7406\u56fe\u7247\u94fe\u63a5\u4e2d\u7684\u76f8\u5bf9\u8def\u5f84<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u7ad9\u7684\u56fe\u7247\u94fe\u63a5\u662f\u76f8\u5bf9\u8def\u5f84\uff0c\u8fd9\u79cd\u60c5\u51b5\u4e0b\u9700\u8981\u5c06\u5176\u8f6c\u6362\u4e3a\u7edd\u5bf9\u8def\u5f84\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from urllib.parse import urljoin<\/p>\n<p>base_url = &#39;https:\/\/www.example.com&#39;<\/p>\n<p>image_urls = [urljoin(base_url, img[&#39;src&#39;]) for img in images]<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u516d\u3001\u5904\u7406\u56fe\u7247\u683c\u5f0f\u548c\u8d28\u91cf<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u56fe\u7247\u53ef\u80fd\u662f\u5176\u4ed6\u683c\u5f0f\uff08\u5982PNG\u3001GIF\u7b49\uff09\uff0c\u6216\u8005\u8d28\u91cf\u8f83\u5dee\u3002\u53ef\u4ee5\u4f7f\u7528<code>Pillow<\/code>\u5e93\u6765\u5904\u7406\u8fd9\u4e9b\u95ee\u9898\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from PIL import Image<\/p>\n<p>from io import BytesIO<\/p>\n<p>for i, image_url in enumerate(image_urls):<\/p>\n<p>    response = requests.get(image_url, headers=headers)<\/p>\n<p>    image = Image.open(BytesIO(response.content))<\/p>\n<p>    # \u8f6c\u6362\u4e3aJPEG\u683c\u5f0f<\/p>\n<p>    if image.format != &#39;JPEG&#39;:<\/p>\n<p>        image = image.convert(&#39;RGB&#39;)<\/p>\n<p>    # \u4fdd\u5b58\u56fe\u7247<\/p>\n<p>    image.save(f&#39;images\/image_{i}.jpg&#39;, &#39;JPEG&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e03\u3001\u603b\u7ed3\u4e0e\u4f18\u5316<\/h3>\n<\/p>\n<p><p>\u901a\u8fc7\u4e0a\u8ff0\u6b65\u9aa4\uff0c\u6211\u4eec\u53ef\u4ee5\u6210\u529f\u722c\u53d6\u5e76\u4fdd\u5b58\u660e\u661f\u56fe\u7247\u3002\u7136\u800c\uff0c\u5b9e\u9645\u4f7f\u7528\u4e2d\u53ef\u80fd\u8fd8\u4f1a\u9047\u5230\u5404\u79cd\u95ee\u9898\uff0c\u5982\u9a8c\u8bc1\u7801\u9a8c\u8bc1\u3001\u52a8\u6001\u52a0\u8f7d\u7b49\u3002\u5bf9\u4e8e\u8fd9\u4e9b\u95ee\u9898\uff0c\u53ef\u4ee5\u5c1d\u8bd5\u4f7f\u7528Selenium\u8fdb\u884c\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\uff0c\u6216\u901a\u8fc7\u5206\u6790\u7f51\u7ad9\u7684API\u6765\u76f4\u63a5\u83b7\u53d6\u6570\u636e\u3002<\/p>\n<\/p>\n<p><p>\u603b\u4e4b\uff0c\u7528Python\u722c\u53d6\u660e\u661f\u56fe\u7247\u7684\u6d41\u7a0b\u5305\u62ec\u9009\u62e9\u76ee\u6807\u7f51\u7ad9\u3001\u89e3\u6790HTML\u83b7\u53d6\u56fe\u7247\u94fe\u63a5\u3001\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u56fe\u7247\u3001\u5904\u7406\u53cd\u722c\u673a\u5236\u3002\u5728\u5b9e\u9645\u64cd\u4f5c\u4e2d\uff0c\u9700\u6839\u636e\u5177\u4f53\u60c5\u51b5\u8c03\u6574\u4ee3\u7801\uff0c\u63d0\u9ad8\u722c\u866b\u7684\u6548\u7387\u548c\u7a33\u5b9a\u6027\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u9009\u62e9\u5408\u9002\u7684\u5e93\u6765\u5b9e\u73b0\u660e\u661f\u56fe\u7247\u7684\u722c\u53d6\uff1f<\/strong><br \/>\u5728\u4f7f\u7528Python\u8fdb\u884c\u722c\u866b\u65f6\uff0c\u6709\u51e0\u4e2a\u6d41\u884c\u7684\u5e93\u53ef\u4ee5\u9009\u62e9\uff0c\u5982Requests\u3001BeautifulSoup\u548cScrapy\u3002Requests\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff1bBeautifulSoup\u7528\u4e8e\u89e3\u6790HTML\u6587\u6863\uff0c\u63d0\u53d6\u6240\u9700\u7684\u4fe1\u606f\uff1bScrapy\u5219\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u6846\u67b6\uff0c\u9002\u5408\u5904\u7406\u66f4\u590d\u6742\u7684\u722c\u866b\u4efb\u52a1\u3002\u6839\u636e\u9879\u76ee\u7684\u9700\u6c42\uff0c\u9009\u62e9\u5408\u9002\u7684\u5de5\u5177\u53ef\u4ee5\u63d0\u9ad8\u6548\u7387\u548c\u7075\u6d3b\u6027\u3002<\/p>\n<p><strong>\u4f7f\u7528\u722c\u866b\u65f6\u9700\u8981\u6ce8\u610f\u54ea\u4e9b\u6cd5\u5f8b\u548c\u9053\u5fb7\u95ee\u9898\uff1f<\/strong><br \/>\u5728\u722c\u53d6\u660e\u661f\u56fe\u7247\u65f6\uff0c\u9075\u5faa\u6cd5\u5f8b\u548c\u9053\u5fb7\u89c4\u8303\u975e\u5e38\u91cd\u8981\u3002\u9996\u5148\uff0c\u786e\u4fdd\u9075\u5b88\u7f51\u7ad9\u7684Robots.txt\u6587\u4ef6\u4e2d\u7684\u722c\u866b\u89c4\u5219\u3002\u5176\u6b21\uff0c\u907f\u514d\u9891\u7e41\u8bf7\u6c42\u540c\u4e00\u9875\u9762\uff0c\u4ee5\u514d\u5bf9\u76ee\u6807\u7f51\u7ad9\u9020\u6210\u8d1f\u62c5\u3002\u6b64\u5916\uff0c\u5c0a\u91cd\u7248\u6743\uff0c\u786e\u4fdd\u4f7f\u7528\u7684\u56fe\u7247\u4e0d\u4fb5\u72af\u4ed6\u4eba\u7684\u77e5\u8bc6\u4ea7\u6743\uff0c\u5fc5\u8981\u65f6\u83b7\u53d6\u6388\u6743\u3002\u5408\u7406\u4f7f\u7528\u722c\u866b\u6280\u672f\u53ef\u4ee5\u907f\u514d\u6f5c\u5728\u7684\u6cd5\u5f8b\u98ce\u9669\u3002<\/p>\n<p><strong>\u5982\u4f55\u5904\u7406\u722c\u53d6\u7684\u56fe\u7247\u6570\u636e\uff1f<\/strong><br \/>\u722c\u53d6\u5230\u7684\u660e\u661f\u56fe\u7247\u901a\u5e38\u9700\u8981\u8fdb\u884c\u4e00\u5b9a\u7684\u5904\u7406\u3002\u53ef\u4ee5\u4f7f\u7528Python\u7684PIL\uff08Pillow\uff09\u5e93\u8fdb\u884c\u56fe\u7247\u683c\u5f0f\u8f6c\u6362\u3001\u538b\u7f29\u6216\u8c03\u6574\u5927\u5c0f\u7b49\u64cd\u4f5c\u3002\u6b64\u5916\uff0c\u5efa\u8bae\u5c06\u56fe\u7247\u4fdd\u5b58\u5230\u672c\u5730\u65f6\u4f7f\u7528\u5408\u9002\u7684\u547d\u540d\u89c4\u5219\uff0c\u4ee5\u4fbf\u540e\u7eed\u7ba1\u7406\u3002\u5bf9\u4e8e\u9700\u8981\u5927\u91cf\u5b58\u50a8\u7684\u60c5\u51b5\uff0c\u53ef\u4ee5\u8003\u8651\u5c06\u56fe\u7247\u4e0a\u4f20\u5230\u4e91\u5b58\u50a8\u670d\u52a1\uff0c\u4fbf\u4e8e\u8bbf\u95ee\u548c\u5206\u4eab\u3002\u901a\u8fc7\u6709\u6548\u7684\u6570\u636e\u5904\u7406\uff0c\u53ef\u4ee5\u63d0\u5347\u9879\u76ee\u7684\u6574\u4f53\u8d28\u91cf\u548c\u7528\u6237\u4f53\u9a8c\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u7528Python\u722c\u53d6\u660e\u661f\u56fe\u7247\u7684\u6b65\u9aa4\u4e3b\u8981\u5305\u62ec\uff1a\u9009\u62e9\u76ee\u6807\u7f51\u7ad9\u3001\u89e3\u6790HTML\u83b7\u53d6\u56fe\u7247\u94fe\u63a5\u3001\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u56fe\u7247\u3001\u5904\u7406\u53cd\u722c\u673a\u5236 [&hellip;]","protected":false},"author":3,"featured_media":1027125,"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\/1027117"}],"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=1027117"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1027117\/revisions"}],"predecessor-version":[{"id":1027127,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1027117\/revisions\/1027127"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1027125"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1027117"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1027117"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1027117"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}