{"id":1015721,"date":"2024-12-27T12:10:33","date_gmt":"2024-12-27T04:10:33","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1015721.html"},"modified":"2024-12-27T12:10:35","modified_gmt":"2024-12-27T04:10:35","slug":"python%e7%88%ac%e8%99%ab%e5%a6%82%e4%bd%95%e4%b8%8b%e8%bd%bdpdf","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1015721.html","title":{"rendered":"python\u722c\u866b\u5982\u4f55\u4e0b\u8f7dpdf"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25095508\/fdab35fd-c086-4029-bacd-55db61e35752.webp\" alt=\"python\u722c\u866b\u5982\u4f55\u4e0b\u8f7dpdf\" \/><\/p>\n<p><p> <strong>Python\u722c\u866b\u4e0b\u8f7dPDF\u7684\u5173\u952e\u6b65\u9aa4\u5305\u62ec\uff1a\u9009\u62e9\u5408\u9002\u7684\u5e93\u3001\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u3001\u5b9a\u4f4dPDF\u94fe\u63a5\u3001\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u6587\u4ef6\u3002\u5176\u4e2d\uff0c\u4f7f\u7528requests\u5e93\u8fdb\u884cHTTP\u8bf7\u6c42\u548cBeautifulSoup\u5e93\u89e3\u6790HTML\u5185\u5bb9\u662f\u5e38\u89c1\u7684\u505a\u6cd5\u3002\u901a\u8fc7\u4ed4\u7ec6\u5206\u6790\u7f51\u9875\u7ed3\u6784\uff0c\u53ef\u4ee5\u6709\u6548\u5b9a\u4f4d\u5230PDF\u6587\u4ef6\u7684URL\uff0c\u7136\u540e\u4f7f\u7528requests\u5e93\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u6587\u4ef6\u3002\u4ee5\u4e0b\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u6bcf\u4e2a\u6b65\u9aa4\u7684\u5b9e\u73b0\u3002<\/strong><\/p>\n<\/p>\n<p><p>\u4e00\u3001\u9009\u62e9\u5408\u9002\u7684\u5e93<\/p>\n<\/p>\n<p><p>\u5728\u4e0b\u8f7dPDF\u6587\u4ef6\u7684\u8fc7\u7a0b\u4e2d\uff0c\u9009\u62e9\u5408\u9002\u7684Python\u5e93\u662f\u81f3\u5173\u91cd\u8981\u7684\u3002\u4e3b\u8981\u4f7f\u7528\u7684\u5e93\u5305\u62ecrequests\u548cBeautifulSoup\u3002requests\u5e93\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u800cBeautifulSoup\u5219\u7528\u4e8e\u89e3\u6790HTML\u6587\u6863\uff0c\u65b9\u4fbf\u63d0\u53d6\u6211\u4eec\u9700\u8981\u7684\u4fe1\u606f\u3002<\/p>\n<\/p>\n<ol>\n<li><strong>requests\u5e93<\/strong><\/li>\n<\/ol>\n<p><p>requests\u5e93\u662f\u4e00\u4e2a\u7b80\u6d01\u6613\u7528\u7684HTTP\u5e93\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u8fdb\u884cGET\u3001POST\u8bf7\u6c42\u3002\u901a\u8fc7requests.get()\u65b9\u6cd5\uff0c\u6211\u4eec\u53ef\u4ee5\u8f7b\u677e\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\uff0c\u8fd9\u4e3a\u540e\u7eed\u7684\u89e3\u6790\u63d0\u4f9b\u4e86\u57fa\u7840\u3002<\/p>\n<\/p>\n<ol start=\"2\">\n<li><strong>BeautifulSoup\u5e93<\/strong><\/li>\n<\/ol>\n<p><p>BeautifulSoup\u5e93\u7528\u4e8e\u89e3\u6790\u548c\u904d\u5386HTML\u6587\u6863\u3002\u901a\u8fc7BeautifulSoup\uff0c\u6211\u4eec\u53ef\u4ee5\u6839\u636e\u6807\u7b7e\u3001\u5c5e\u6027\u7b49\u4fe1\u606f\uff0c\u5feb\u901f\u5b9a\u4f4d\u5230\u7f51\u9875\u4e2d\u7684\u7279\u5b9a\u5143\u7d20\u3002\u5bf9\u4e8ePDF\u4e0b\u8f7d\u6765\u8bf4\uff0c\u901a\u5e38\u6211\u4eec\u9700\u8981\u627e\u5230\u5305\u542bPDF\u94fe\u63a5\u7684a\u6807\u7b7e\uff0c\u8fd9\u4e00\u6b65\u9aa4\u975e\u5e38\u91cd\u8981\u3002<\/p>\n<\/p>\n<p><p>\u4e8c\u3001\u89e3\u6790\u7f51\u9875\u5185\u5bb9<\/p>\n<\/p>\n<p><p>\u5728\u83b7\u53d6\u5230\u7f51\u9875\u7684HTML\u5185\u5bb9\u540e\uff0c\u63a5\u4e0b\u6765\u9700\u8981\u89e3\u6790\u8fd9\u4e9b\u5185\u5bb9\u4ee5\u63d0\u53d6\u6211\u4eec\u6240\u9700\u7684PDF\u94fe\u63a5\u3002\u901a\u5e38\uff0c\u8fd9\u6d89\u53ca\u5230\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u6587\u6863\u3002<\/p>\n<\/p>\n<ol>\n<li><strong>\u521b\u5efaBeautifulSoup\u5bf9\u8c61<\/strong><\/li>\n<\/ol>\n<p><p>\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5c06\u7f51\u9875\u7684HTML\u5185\u5bb9\u8f6c\u5316\u4e3a\u4e00\u4e2aBeautifulSoup\u5bf9\u8c61\uff0c\u8fd9\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u4ee3\u7801\u5b9e\u73b0\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>html_content = requests.get(url).text<\/p>\n<p>soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<ol start=\"2\">\n<li><strong>\u5b9a\u4f4dPDF\u94fe\u63a5<\/strong><\/li>\n<\/ol>\n<p><p>PDF\u6587\u4ef6\u901a\u5e38\u662f\u901a\u8fc7<a>\u6807\u7b7e\u94fe\u63a5\u7684\uff0c\u56e0\u6b64\uff0c\u6211\u4eec\u9700\u8981\u67e5\u627e\u6240\u6709\u7684<a>\u6807\u7b7e\uff0c\u5e76\u7b5b\u9009\u51fa\u5176\u4e2dhref\u5c5e\u6027\u4ee5.pdf\u7ed3\u5c3e\u7684\u94fe\u63a5\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">pdf_links = [a[&#39;href&#39;] for a in soup.find_all(&#39;a&#39;, href=True) if a[&#39;href&#39;].endswith(&#39;.pdf&#39;)]<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e09\u3001\u4e0b\u8f7dPDF\u6587\u4ef6<\/p>\n<\/p>\n<p><p>\u5728\u83b7\u53d6\u5230PDF\u94fe\u63a5\u540e\uff0c\u63a5\u4e0b\u6765\u9700\u8981\u4e0b\u8f7d\u8fd9\u4e9b\u6587\u4ef6\u5e76\u4fdd\u5b58\u5230\u672c\u5730\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528requests\u5e93\u7684get\u65b9\u6cd5\u6765\u5b9e\u73b0\u8fd9\u4e00\u70b9\u3002<\/p>\n<\/p>\n<ol>\n<li><strong>\u53d1\u9001HTTP\u8bf7\u6c42\u4e0b\u8f7dPDF<\/strong><\/li>\n<\/ol>\n<p><p>\u5bf9\u4e8e\u6bcf\u4e00\u4e2aPDF\u94fe\u63a5\uff0c\u4f7f\u7528requests.get()\u65b9\u6cd5\u53d1\u9001\u8bf7\u6c42\uff0c\u5e76\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9\u3002\u7136\u540e\uff0c\u5c06\u54cd\u5e94\u5185\u5bb9\u5199\u5165\u6587\u4ef6\u5373\u53ef\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">for link in pdf_links:<\/p>\n<p>    response = requests.get(link)<\/p>\n<p>    with open(link.split(&#39;\/&#39;)[-1], &#39;wb&#39;) as f:<\/p>\n<p>        f.write(response.content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<ol start=\"2\">\n<li><strong>\u4fdd\u5b58PDF\u6587\u4ef6<\/strong><\/li>\n<\/ol>\n<p><p>\u5728\u4e0b\u8f7dPDF\u6587\u4ef6\u65f6\uff0c\u901a\u5e38\u9700\u8981\u6307\u5b9a\u4fdd\u5b58\u8def\u5f84\u3002\u53ef\u4ee5\u901a\u8fc7os\u5e93\u6765\u5b9e\u73b0\u8def\u5f84\u7684\u521b\u5efa\u548c\u68c0\u67e5\uff0c\u4ee5\u786e\u4fdd\u6587\u4ef6\u80fd\u591f\u6b63\u786e\u4fdd\u5b58\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import os<\/p>\n<p>save_path = &#39;pdf_files&#39;<\/p>\n<p>if not os.path.exists(save_path):<\/p>\n<p>    os.makedirs(save_path)<\/p>\n<p>for link in pdf_links:<\/p>\n<p>    response = requests.get(link)<\/p>\n<p>    file_name = os.path.join(save_path, link.split(&#39;\/&#39;)[-1])<\/p>\n<p>    with open(file_name, &#39;wb&#39;) as f:<\/p>\n<p>        f.write(response.content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u56db\u3001\u5904\u7406\u53cd\u722c\u866b\u673a\u5236<\/p>\n<\/p>\n<p><p>\u5728\u8fdb\u884c\u722c\u866b\u64cd\u4f5c\u65f6\uff0c\u5f88\u591a\u7f51\u7ad9\u4f1a\u6709\u53cd\u722c\u866b\u673a\u5236\uff0c\u8fd9\u53ef\u80fd\u5bfc\u81f4\u8bf7\u6c42\u88ab\u963b\u6b62\u6216IP\u88ab\u5c01\u7981\u3002\u4e3a\u6b64\uff0c\u6211\u4eec\u9700\u8981\u91c7\u53d6\u4e00\u4e9b\u63aa\u65bd\u6765\u5e94\u5bf9\u8fd9\u4e9b\u673a\u5236\u3002<\/p>\n<\/p>\n<ol>\n<li><strong>\u8bbe\u7f6e\u8bf7\u6c42\u5934<\/strong><\/li>\n<\/ol>\n<p><p>\u901a\u8fc7\u8bbe\u7f6eUser-Agent\u7b49\u8bf7\u6c42\u5934\u4fe1\u606f\uff0c\u53ef\u4ee5\u6a21\u62df\u6d4f\u89c8\u5668\u8bf7\u6c42\uff0c\u964d\u4f4e\u88ab\u7f51\u7ad9\u8bc6\u522b\u4e3a\u722c\u866b\u7684\u98ce\u9669\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">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\/91.0.4472.124 Safari\/537.36&#39;<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, headers=headers)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<ol start=\"2\">\n<li><strong>\u4f7f\u7528\u4ee3\u7406<\/strong><\/li>\n<\/ol>\n<p><p>\u4f7f\u7528\u4ee3\u7406IP\u53ef\u4ee5\u6709\u6548\u9632\u6b62IP\u88ab\u5c01\u7981\u3002\u53ef\u4ee5\u901a\u8fc7requests\u5e93\u7684proxies\u53c2\u6570\u6765\u8bbe\u7f6e\u4ee3\u7406\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">proxies = {<\/p>\n<p>    &#39;http&#39;: &#39;http:\/\/proxy_ip:proxy_port&#39;,<\/p>\n<p>    &#39;https&#39;: &#39;https:\/\/proxy_ip:proxy_port&#39;<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, headers=headers, proxies=proxies)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e94\u3001\u5904\u7406\u52a8\u6001\u7f51\u9875<\/p>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u9875\u7684\u5185\u5bb9\u662f\u901a\u8fc7JavaScript\u52a8\u6001\u52a0\u8f7d\u7684\uff0c\u76f4\u63a5\u8bf7\u6c42HTML\u9875\u9762\u53ef\u80fd\u5f97\u4e0d\u5230\u5b8c\u6574\u5185\u5bb9\u3002\u5bf9\u4e8e\u8fd9\u79cd\u60c5\u51b5\uff0c\u53ef\u4ee5\u4f7f\u7528Selenium\u5e93\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\u3002<\/p>\n<\/p>\n<ol>\n<li><strong>\u4f7f\u7528Selenium<\/strong><\/li>\n<\/ol>\n<p><p>Selenium\u662f\u4e00\u4e2a\u81ea\u52a8\u5316\u6d4b\u8bd5\u5de5\u5177\uff0c\u53ef\u4ee5\u7528\u4e8e\u63a7\u5236\u6d4f\u89c8\u5668\u8bbf\u95ee\u7f51\u9875\uff0c\u9002\u5408\u5904\u7406\u52a8\u6001\u7f51\u9875\u5185\u5bb9\u7684\u722c\u53d6\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>driver = webdriver.Chrome()<\/p>\n<p>driver.get(url)<\/p>\n<p>html_content = driver.page_source<\/p>\n<p><\/code><\/pre>\n<\/p>\n<ol start=\"2\">\n<li><strong>\u7ed3\u5408BeautifulSoup\u89e3\u6790\u5185\u5bb9<\/strong><\/li>\n<\/ol>\n<p><p>\u5728\u83b7\u53d6\u5230\u52a8\u6001\u52a0\u8f7d\u540e\u7684\u7f51\u9875\u5185\u5bb9\u540e\uff0c\u53ef\u4ee5\u7ee7\u7eed\u4f7f\u7528BeautifulSoup\u8fdb\u884c\u89e3\u6790\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<p>pdf_links = [a[&#39;href&#39;] for a in soup.find_all(&#39;a&#39;, href=True) if a[&#39;href&#39;].endswith(&#39;.pdf&#39;)]<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u6211\u4eec\u53ef\u4ee5\u6709\u6548\u5730\u4f7f\u7528Python\u722c\u866b\u4e0b\u8f7dPDF\u6587\u4ef6\u3002\u9700\u8981\u6ce8\u610f\u7684\u662f\uff0c\u5728\u8fdb\u884c\u722c\u866b\u64cd\u4f5c\u65f6\uff0c\u5e94\u9075\u5faa\u7f51\u7ad9\u7684robots.txt\u534f\u8bae\uff0c\u5c0a\u91cd\u7f51\u7ad9\u7684\u8bbf\u95ee\u89c4\u5219\uff0c\u907f\u514d\u5bf9\u76ee\u6807\u7f51\u7ad9\u9020\u6210\u8fc7\u591a\u7684\u8bf7\u6c42\u538b\u529b\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u722c\u866b\u81ea\u52a8\u4e0b\u8f7dPDF\u6587\u4ef6\uff1f<\/strong><br \/>\u4f7f\u7528Python\u722c\u866b\u4e0b\u8f7dPDF\u6587\u4ef6\u901a\u5e38\u6d89\u53ca\u5230\u4f7f\u7528requests\u5e93\u6765\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u5e76\u5229\u7528BeautifulSoup\u6216lxml\u89e3\u6790HTML\u6587\u6863\uff0c\u627e\u51faPDF\u6587\u4ef6\u7684\u94fe\u63a5\u3002\u63a5\u4e0b\u6765\uff0c\u53ef\u4ee5\u518d\u6b21\u4f7f\u7528requests\u5e93\u4e0b\u8f7dPDF\u6587\u4ef6\u3002\u786e\u4fdd\u5728\u4ee3\u7801\u4e2d\u5904\u7406\u597d\u5f02\u5e38\uff0c\u4ee5\u5e94\u5bf9\u7f51\u7edc\u95ee\u9898\u6216\u94fe\u63a5\u5931\u6548\u7684\u60c5\u51b5\u3002<\/p>\n<p><strong>\u5728\u4e0b\u8f7dPDF\u65f6\u5982\u4f55\u5904\u7406\u6587\u4ef6\u540d\u51b2\u7a81\uff1f<\/strong><br \/>\u5728\u4e0b\u8f7dPDF\u6587\u4ef6\u65f6\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u6587\u4ef6\u540d\u91cd\u590d\u7684\u60c5\u51b5\u3002\u53ef\u4ee5\u901a\u8fc7\u5728\u6587\u4ef6\u540d\u540e\u6dfb\u52a0\u65f6\u95f4\u6233\u6216\u5e8f\u53f7\u6765\u907f\u514d\u51b2\u7a81\u3002\u6b64\u5916\uff0c\u68c0\u67e5\u6587\u4ef6\u662f\u5426\u5df2\u5b58\u5728\uff0c\u5982\u679c\u5b58\u5728\uff0c\u53ef\u4ee5\u9009\u62e9\u8986\u76d6\u3001\u8df3\u8fc7\u6216\u91cd\u547d\u540d\u6587\u4ef6\uff0c\u4ee5\u786e\u4fdd\u6bcf\u4e2a\u4e0b\u8f7d\u7684\u6587\u4ef6\u90fd\u662f\u552f\u4e00\u7684\u3002<\/p>\n<p><strong>Python\u722c\u866b\u4e0b\u8f7dPDF\u9700\u8981\u6ce8\u610f\u54ea\u4e9b\u6cd5\u5f8b\u95ee\u9898\uff1f<\/strong><br \/>\u5728\u4f7f\u7528Python\u722c\u866b\u4e0b\u8f7dPDF\u6587\u4ef6\u65f6\uff0c\u7528\u6237\u9700\u8981\u9075\u5faa\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6\u4e2d\u7684\u89c4\u5b9a\uff0c\u786e\u4fdd\u4e0d\u8fdd\u53cd\u7f51\u7ad9\u7684\u6293\u53d6\u653f\u7b56\u3002\u540c\u65f6\uff0c\u4e86\u89e3\u7248\u6743\u6cd5\u548c\u76f8\u5173\u6cd5\u5f8b\uff0c\u907f\u514d\u4e0b\u8f7d\u53d7\u7248\u6743\u4fdd\u62a4\u7684\u5185\u5bb9\uff0c\u4ee5\u514d\u5f15\u53d1\u6cd5\u5f8b\u7ea0\u7eb7\u3002\u5efa\u8bae\u5728\u4e0b\u8f7d\u524d\u786e\u8ba4\u5185\u5bb9\u7684\u4f7f\u7528\u6743\u9650\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u722c\u866b\u4e0b\u8f7dPDF\u7684\u5173\u952e\u6b65\u9aa4\u5305\u62ec\uff1a\u9009\u62e9\u5408\u9002\u7684\u5e93\u3001\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u3001\u5b9a\u4f4dPDF\u94fe\u63a5\u3001\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u6587\u4ef6\u3002\u5176\u4e2d\uff0c\u4f7f [&hellip;]","protected":false},"author":3,"featured_media":1015730,"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\/1015721"}],"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=1015721"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1015721\/revisions"}],"predecessor-version":[{"id":1015736,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1015721\/revisions\/1015736"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1015730"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1015721"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1015721"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1015721"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}