{"id":1102098,"date":"2025-01-08T15:56:20","date_gmt":"2025-01-08T07:56:20","guid":{"rendered":""},"modified":"2025-01-08T15:56:39","modified_gmt":"2025-01-08T07:56:39","slug":"python%e5%a6%82%e4%bd%95%e7%88%ac%e5%8f%96%e7%bd%91%e9%a1%b5%e5%88%86%e9%a1%b5%e9%9d%a2%e7%9a%84url-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1102098.html","title":{"rendered":"python\u5982\u4f55\u722c\u53d6\u7f51\u9875\u5206\u9875\u9762\u7684url"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25064536\/74ca8370-d236-4ea9-add5-d293a94736bf.webp\" alt=\"python\u5982\u4f55\u722c\u53d6\u7f51\u9875\u5206\u9875\u9762\u7684url\" \/><\/p>\n<p><p> Python\u722c\u53d6\u7f51\u9875\u5206\u9875\u9762\u7684URL\u662f\u4e00\u9879\u5e38\u89c1\u7684\u7f51\u7edc\u722c\u866b\u4efb\u52a1\uff0c<strong>\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u3001\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u94fe\u63a5<\/strong>\uff0c\u5176\u4e2d\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u662f\u4e00\u79cd\u9ad8\u6548\u4e14\u7b80\u5355\u7684\u65b9\u6cd5\u3002<strong>\u4f7f\u7528BeautifulSoup\u5e93\uff0c\u53ef\u4ee5\u8f7b\u677e\u5730\u63d0\u53d6\u7f51\u9875\u4e0a\u7684\u6240\u6709\u94fe\u63a5\uff0c\u5e76\u6839\u636e\u9700\u8981\u8fdb\u884c\u7b5b\u9009\u548c\u5904\u7406<\/strong>\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u5b89\u88c5\u6240\u9700\u5e93<\/h3>\n<\/p>\n<p><p>\u5728\u5f00\u59cb\u4e4b\u524d\uff0c\u786e\u4fdd\u4f60\u7684Python\u73af\u5883\u4e2d\u5b89\u88c5\u4e86\u6240\u9700\u7684\u5e93\u3002\u53ef\u4ee5\u4f7f\u7528pip\u5b89\u88c5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install requests<\/p>\n<p>pip install beautifulsoup4<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e8c\u3001\u53d1\u9001HTTP\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/h3>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u9700\u8981\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u6765\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3002\u53ef\u4ee5\u4f7f\u7528<code>requests.get(url)<\/code>\u6765\u53d1\u9001\u4e00\u4e2aGET\u8bf7\u6c42\u5e76\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;https:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>if response.status_code == 200:<\/p>\n<p>    html_content = response.text<\/p>\n<p>else:<\/p>\n<p>    print(f&quot;F<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>led to retrieve the webpage. Status code: {response.status_code}&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u89e3\u6790\u7f51\u9875\u5185\u5bb9<\/h3>\n<\/p>\n<p><p>\u4f7f\u7528BeautifulSoup\u5e93\u89e3\u6790\u7f51\u9875\u5185\u5bb9\uff0c\u5e76\u63d0\u53d6\u6240\u6709\u94fe\u63a5\u3002BeautifulSoup\u53ef\u4ee5\u65b9\u4fbf\u5730\u89e3\u6790HTML\u6587\u6863\uff0c\u5e76\u652f\u6301CSS\u9009\u62e9\u5668\u548cXPath\u7b49\u591a\u79cd\u9009\u62e9\u65b9\u5f0f\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><h3>\u56db\u3001\u63d0\u53d6\u9875\u9762\u4e0a\u7684\u6240\u6709\u94fe\u63a5<\/h3>\n<\/p>\n<p><p>\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u7684<code>find_all<\/code>\u65b9\u6cd5\u6765\u67e5\u627e\u6240\u6709\u7684<code>&lt;a&gt;<\/code>\u6807\u7b7e\uff0c\u5e76\u63d0\u53d6\u5176\u4e2d\u7684<code>href<\/code>\u5c5e\u6027\u503c\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">links = []<\/p>\n<p>for link in soup.find_all(&#39;a&#39;):<\/p>\n<p>    href = link.get(&#39;href&#39;)<\/p>\n<p>    if href:<\/p>\n<p>        links.append(href)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e94\u3001\u5904\u7406\u76f8\u5bf9\u94fe\u63a5\u548c\u7edd\u5bf9\u94fe\u63a5<\/h3>\n<\/p>\n<p><p>\u63d0\u53d6\u5230\u7684\u94fe\u63a5\u53ef\u80fd\u662f\u76f8\u5bf9\u94fe\u63a5\u6216\u7edd\u5bf9\u94fe\u63a5\u3002\u4e3a\u4e86\u786e\u4fdd\u6240\u6709\u94fe\u63a5\u90fd\u662f\u5b8c\u6574\u7684URL\uff0c\u53ef\u4ee5\u4f7f\u7528<code>urllib.parse.urljoin<\/code>\u51fd\u6570\u5c06\u76f8\u5bf9\u94fe\u63a5\u8f6c\u6362\u4e3a\u7edd\u5bf9\u94fe\u63a5\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from urllib.parse import urljoin<\/p>\n<p>base_url = &#39;https:\/\/example.com&#39;<\/p>\n<p>full_links = [urljoin(base_url, link) for link in links]<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u516d\u3001\u5904\u7406\u5206\u9875\u94fe\u63a5<\/h3>\n<\/p>\n<p><p>\u5f88\u591a\u7f51\u7ad9\u7684\u5206\u9875\u94fe\u63a5\u4f1a\u6709\u89c4\u5f8b\uff0c\u6bd4\u5982\u9875\u9762URL\u4e2d\u5305\u542b\u9875\u7801\u53c2\u6570\u3002\u53ef\u4ee5\u901a\u8fc7\u89e3\u6790\u5206\u9875\u94fe\u63a5\u7684\u7ed3\u6784\uff0c\u52a8\u6001\u751f\u6210\u6240\u6709\u5206\u9875\u94fe\u63a5\uff0c\u5e76\u9010\u9875\u8fdb\u884c\u722c\u53d6\u3002<\/p>\n<\/p>\n<p><p>\u5047\u8bbe\u9875\u9762URL\u4e3a<code>https:\/\/example.com\/page\/1<\/code>\uff0c\u53ef\u4ee5\u901a\u8fc7\u6539\u53d8\u9875\u7801\u53c2\u6570\u6765\u751f\u6210\u5206\u9875\u94fe\u63a5\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">def generate_pagination_urls(base_url, total_pages):<\/p>\n<p>    pagination_urls = []<\/p>\n<p>    for page in range(1, total_pages + 1):<\/p>\n<p>        pagination_urls.append(f&quot;{base_url}\/page\/{page}&quot;)<\/p>\n<p>    return pagination_urls<\/p>\n<p>pagination_urls = generate_pagination_urls(&#39;https:\/\/example.com&#39;, 10)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e03\u3001\u7efc\u5408\u793a\u4f8b<\/h3>\n<\/p>\n<p><p>\u7efc\u5408\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u5199\u4e00\u4e2a\u5b8c\u6574\u7684\u722c\u866b\u811a\u672c\uff0c\u722c\u53d6\u67d0\u4e2a\u7f51\u7ad9\u7684\u6240\u6709\u5206\u9875\u94fe\u63a5\uff0c\u5e76\u63d0\u53d6\u6bcf\u9875\u4e0a\u7684\u6240\u6709\u94fe\u63a5\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<p>from urllib.parse import urljoin<\/p>\n<p>def get_html_content(url):<\/p>\n<p>    response = requests.get(url)<\/p>\n<p>    if response.status_code == 200:<\/p>\n<p>        return response.text<\/p>\n<p>    else:<\/p>\n<p>        print(f&quot;Failed to retrieve the webpage. Status code: {response.status_code}&quot;)<\/p>\n<p>        return None<\/p>\n<p>def extract_links(html_content, base_url):<\/p>\n<p>    soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<p>    links = []<\/p>\n<p>    for link in soup.find_all(&#39;a&#39;):<\/p>\n<p>        href = link.get(&#39;href&#39;)<\/p>\n<p>        if href:<\/p>\n<p>            full_url = urljoin(base_url, href)<\/p>\n<p>            links.append(full_url)<\/p>\n<p>    return links<\/p>\n<p>def generate_pagination_urls(base_url, total_pages):<\/p>\n<p>    pagination_urls = []<\/p>\n<p>    for page in range(1, total_pages + 1):<\/p>\n<p>        pagination_urls.append(f&quot;{base_url}\/page\/{page}&quot;)<\/p>\n<p>    return pagination_urls<\/p>\n<p>def main():<\/p>\n<p>    base_url = &#39;https:\/\/example.com&#39;<\/p>\n<p>    total_pages = 10  # \u6839\u636e\u9700\u8981\u8c03\u6574\u603b\u9875\u6570<\/p>\n<p>    pagination_urls = generate_pagination_urls(base_url, total_pages)<\/p>\n<p>    all_links = []<\/p>\n<p>    for page_url in pagination_urls:<\/p>\n<p>        html_content = get_html_content(page_url)<\/p>\n<p>        if html_content:<\/p>\n<p>            page_links = extract_links(html_content, base_url)<\/p>\n<p>            all_links.extend(page_links)<\/p>\n<p>    print(f&quot;Total links extracted: {len(all_links)}&quot;)<\/p>\n<p>    for link in all_links:<\/p>\n<p>        print(link)<\/p>\n<p>if __name__ == &#39;__main__&#39;:<\/p>\n<p>    main()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u516b\u3001\u5904\u7406\u53cd\u722c\u673a\u5236<\/h3>\n<\/p>\n<p><p>\u4e00\u4e9b\u7f51\u7ad9\u53ef\u80fd\u4f1a\u6709\u53cd\u722c\u673a\u5236\uff0c\u6bd4\u5982\u4f7f\u7528CAPTCHA\u3001IP\u5c01\u7981\u3001\u7528\u6237\u4ee3\u7406\u68c0\u67e5\u7b49\u3002\u53ef\u4ee5\u901a\u8fc7\u6dfb\u52a0\u8bf7\u6c42\u5934\u3001\u4f7f\u7528\u4ee3\u7406IP\u3001\u6a21\u62df\u4eba\u7c7b\u884c\u4e3a\u7b49\u65b9\u5f0f\u6765\u7ed5\u8fc7\u8fd9\u4e9b\u673a\u5236\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<p><h3>\u4e5d\u3001\u4fdd\u5b58\u7ed3\u679c<\/h3>\n<\/p>\n<p><p>\u53ef\u4ee5\u5c06\u63d0\u53d6\u5230\u7684\u94fe\u63a5\u4fdd\u5b58\u5230\u6587\u4ef6\u4e2d\uff0c\u65b9\u4fbf\u540e\u7eed\u5904\u7406\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">with open(&#39;extracted_links.txt&#39;, &#39;w&#39;) as file:<\/p>\n<p>    for link in all_links:<\/p>\n<p>        file.write(link + &#39;\\n&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u5341\u3001\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u53ef\u4ee5\u4f7f\u7528Python\u722c\u53d6\u7f51\u9875\u7684\u6240\u6709\u5206\u9875\u94fe\u63a5\uff0c\u5e76\u63d0\u53d6\u6bcf\u9875\u4e0a\u7684\u6240\u6709\u94fe\u63a5\u3002<strong>\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u3001\u5904\u7406\u5206\u9875\u94fe\u63a5\u548c\u53cd\u722c\u673a\u5236<\/strong>\uff0c\u53ef\u4ee5\u5b9e\u73b0\u4e00\u4e2a\u529f\u80fd\u5b8c\u6574\u7684\u722c\u866b\u811a\u672c\u3002\u5e0c\u671b\u8fd9\u7bc7\u6587\u7ae0\u5bf9\u4f60\u6709\u6240\u5e2e\u52a9\uff0c\u795d\u4f60\u5728\u5b66\u4e60\u548c\u4f7f\u7528Python\u722c\u866b\u65f6\u53d6\u5f97\u66f4\u591a\u7684\u8fdb\u5c55\uff01<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u5b9e\u73b0\u7f51\u9875\u5206\u9875\u9762\u7684\u722c\u53d6\uff1f<\/strong><br \/>\u8981\u4f7f\u7528Python\u722c\u53d6\u5206\u9875\u9762\u7684URL\uff0c\u901a\u5e38\u9700\u8981\u501f\u52a9\u4e00\u4e9b\u5e93\uff0c\u5982requests\u548cBeautifulSoup\u3002\u9996\u5148\uff0c\u53d1\u9001HTTP\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u7136\u540e\u89e3\u6790HTML\u7ed3\u6784\uff0c\u63d0\u53d6\u5206\u9875\u7684URL\u3002\u53ef\u4ee5\u901a\u8fc7\u5206\u6790\u7f51\u9875\u7684DOM\u7ed3\u6784\uff0c\u627e\u51fa\u5305\u542b\u5206\u9875\u94fe\u63a5\u7684\u5143\u7d20\u3002<\/p>\n<p><strong>\u5728\u722c\u53d6\u8fc7\u7a0b\u4e2d\u5982\u4f55\u5904\u7406\u53cd\u722c\u673a\u5236\uff1f<\/strong><br \/>\u8bb8\u591a\u7f51\u7ad9\u4f1a\u5b9e\u65bd\u53cd\u722c\u673a\u5236\uff0c\u53ef\u80fd\u4f1a\u963b\u6b62\u9891\u7e41\u8bf7\u6c42\u3002\u53ef\u4ee5\u91c7\u53d6\u4e00\u4e9b\u63aa\u65bd\u6765\u5e94\u5bf9\uff0c\u6bd4\u5982\u8bbe\u7f6e\u8bf7\u6c42\u5934\u3001\u4f7f\u7528\u968f\u673a\u7684User-Agent\u3001\u52a0\u5165\u9002\u5f53\u7684\u5ef6\u65f6\u3001\u751a\u81f3\u4f7f\u7528\u4ee3\u7406IP\u3002\u6b64\u5916\uff0c\u4f7f\u7528selenium\u7b49\u5de5\u5177\u53ef\u4ee5\u6a21\u62df\u771f\u5b9e\u7528\u6237\u7684\u64cd\u4f5c\uff0c\u4ece\u800c\u51cf\u5c11\u88ab\u68c0\u6d4b\u7684\u98ce\u9669\u3002<\/p>\n<p><strong>\u5982\u4f55\u4fdd\u5b58\u722c\u53d6\u7684\u6570\u636e\u4ee5\u4fbf\u540e\u7eed\u5206\u6790\uff1f<\/strong><br \/>\u722c\u53d6\u5230\u7684\u6570\u636e\u53ef\u4ee5\u9009\u62e9\u4fdd\u5b58\u4e3a\u591a\u79cd\u683c\u5f0f\uff0c\u4f8b\u5982CSV\u3001JSON\u6216\u76f4\u63a5\u5b58\u5165\u6570\u636e\u5e93\uff08\u5982SQLite\u3001MongoDB\u7b49\uff09\u3002\u4f7f\u7528pandas\u5e93\u53ef\u4ee5\u65b9\u4fbf\u5730\u5c06\u6570\u636e\u5b58\u4e3aCSV\u6587\u4ef6\uff0c\u800cJSON\u6a21\u5757\u5219\u53ef\u4ee5\u8f7b\u677e\u5904\u7406JSON\u683c\u5f0f\u7684\u6570\u636e\u3002\u786e\u4fdd\u5728\u4fdd\u5b58\u6570\u636e\u65f6\uff0c\u683c\u5f0f\u6e05\u6670\u4e14\u6613\u4e8e\u540e\u7eed\u5206\u6790\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u722c\u53d6\u7f51\u9875\u5206\u9875\u9762\u7684URL\u662f\u4e00\u9879\u5e38\u89c1\u7684\u7f51\u7edc\u722c\u866b\u4efb\u52a1\uff0c\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u4f7f\u7528B [&hellip;]","protected":false},"author":3,"featured_media":1102132,"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\/1102098"}],"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=1102098"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1102098\/revisions"}],"predecessor-version":[{"id":1102137,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1102098\/revisions\/1102137"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1102132"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1102098"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1102098"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1102098"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}