{"id":1085321,"date":"2025-01-08T13:15:03","date_gmt":"2025-01-08T05:15:03","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1085321.html"},"modified":"2025-01-08T13:15:06","modified_gmt":"2025-01-08T05:15:06","slug":"python%e5%a6%82%e4%bd%95%e7%88%ac%e5%8f%96%e6%af%8f%e9%a1%b55%e4%b8%aa%e9%9f%b3%e9%a2%91-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1085321.html","title":{"rendered":"python\u5982\u4f55\u722c\u53d6\u6bcf\u98755\u4e2a\u97f3\u9891"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/24195253\/be056175-a9a9-4dbe-8612-34b0b54a09cd.webp\" alt=\"python\u5982\u4f55\u722c\u53d6\u6bcf\u98755\u4e2a\u97f3\u9891\" \/><\/p>\n<p><p> <strong>Python\u722c\u53d6\u6bcf\u98755\u4e2a\u97f3\u9891\u7684\u65b9\u6cd5\uff1a\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u3001\u63d0\u53d6\u97f3\u9891\u94fe\u63a5\u3001\u9010\u9875\u722c\u53d6\u5e76\u4e0b\u8f7d\u97f3\u9891\u6587\u4ef6\u3002<\/strong><\/p>\n<\/p>\n<p><p>\u5176\u4e2d\uff0c<strong>\u63d0\u53d6\u97f3\u9891\u94fe\u63a5<\/strong>\u662f\u5173\u952e\u6b65\u9aa4\u3002\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u540e\uff0c\u9700\u8981\u627e\u5230\u97f3\u9891\u6587\u4ef6\u6240\u5728\u7684\u6807\u7b7e\uff0c\u5e76\u63d0\u53d6\u5176src\u5c5e\u6027\uff0c\u8fd9\u6837\u624d\u80fd\u83b7\u53d6\u97f3\u9891\u6587\u4ef6\u7684\u94fe\u63a5\u8fdb\u884c\u4e0b\u8f7d\u3002<\/p>\n<\/p>\n<p><p>\u4e00\u3001\u8bbe\u7f6e\u4e0e\u5b89\u88c5<\/p>\n<\/p>\n<p><p>\u5728\u5f00\u59cb\u4e4b\u524d\uff0c\u9700\u8981\u5b89\u88c5\u6240\u9700\u7684Python\u5e93\u3002\u6211\u4eec\u5c06\u7528\u5230requests\u5e93\u6765\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0cBeautifulSoup\u5e93\u6765\u89e3\u6790HTML\uff0c\u4ee5\u53caos\u5e93\u6765\u5904\u7406\u6587\u4ef6\u64cd\u4f5c\u3002<\/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><p>\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u5bfc\u5165\u6240\u9700\u5e93\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<p>import os<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e8c\u3001\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/p>\n<\/p>\n<p><p>\u4f7f\u7528requests\u5e93\u6765\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3002\u6211\u4eec\u9700\u8981\u77e5\u9053\u6211\u4eec\u8981\u722c\u53d6\u7684\u76ee\u6807\u7f51\u9875\u7684URL\uff0c\u5e76\u4f7f\u7528requests.get\u65b9\u6cd5\u6765\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">url = &#39;http:\/\/example.com&#39;  # \u66ff\u6362\u4e3a\u76ee\u6807\u7f51\u7ad9\u7684URL<\/p>\n<p>response = requests.get(url)<\/p>\n<p>html_content = response.content<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e09\u3001\u89e3\u6790HTML\u5185\u5bb9<\/p>\n<\/p>\n<p><p>\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u5185\u5bb9\uff0c\u5e76\u67e5\u627e\u97f3\u9891\u6587\u4ef6\u6240\u5728\u7684\u6807\u7b7e\u3002\u5047\u8bbe\u97f3\u9891\u6587\u4ef6\u90fd\u5728<code>&lt;audio&gt;<\/code>\u6807\u7b7e\u4e2d\uff0c\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u4ee3\u7801\u83b7\u53d6\u6240\u6709\u97f3\u9891\u6807\u7b7e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<p>audio_tags = soup.find_all(&#39;audio&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u56db\u3001\u63d0\u53d6\u97f3\u9891\u94fe\u63a5<\/p>\n<\/p>\n<p><p>\u4ece\u97f3\u9891\u6807\u7b7e\u4e2d\u63d0\u53d6\u97f3\u9891\u6587\u4ef6\u7684src\u5c5e\u6027\uff0c\u8fd9\u6837\u6211\u4eec\u5c31\u53ef\u4ee5\u83b7\u53d6\u97f3\u9891\u6587\u4ef6\u7684\u94fe\u63a5\u3002\u6211\u4eec\u8fd8\u9700\u8981\u786e\u4fdd\u53ea\u63d0\u53d6\u524d5\u4e2a\u97f3\u9891\u6587\u4ef6\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">audio_urls = []<\/p>\n<p>for tag in audio_tags[:5]:  # \u53ea\u63d0\u53d6\u524d5\u4e2a\u97f3\u9891\u6587\u4ef6<\/p>\n<p>    audio_url = tag.get(&#39;src&#39;)<\/p>\n<p>    if audio_url:<\/p>\n<p>        audio_urls.append(audio_url)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e94\u3001\u4e0b\u8f7d\u97f3\u9891\u6587\u4ef6<\/p>\n<\/p>\n<p><p>\u73b0\u5728\u6211\u4eec\u6709\u4e86\u97f3\u9891\u6587\u4ef6\u7684\u94fe\u63a5\uff0c\u53ef\u4ee5\u4f7f\u7528requests\u5e93\u6765\u4e0b\u8f7d\u8fd9\u4e9b\u6587\u4ef6\u5e76\u4fdd\u5b58\u5230\u672c\u5730\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">def download_audio(url, save_path):<\/p>\n<p>    response = requests.get(url)<\/p>\n<p>    with open(save_path, &#39;wb&#39;) as file:<\/p>\n<p>        file.write(response.content)<\/p>\n<p>save_directory = &#39;downloaded_audios&#39;<\/p>\n<p>os.makedirs(save_directory, exist_ok=True)<\/p>\n<p>for i, audio_url in enumerate(audio_urls):<\/p>\n<p>    save_path = os.path.join(save_directory, f&#39;audio_{i + 1}.mp3&#39;)<\/p>\n<p>    download_audio(audio_url, save_path)<\/p>\n<p>    print(f&#39;Downloaded {save_path}&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u516d\u3001\u9010\u9875\u722c\u53d6<\/p>\n<\/p>\n<p><p>\u5982\u679c\u76ee\u6807\u7f51\u7ad9\u6709\u5206\u9875\u529f\u80fd\uff0c\u6211\u4eec\u9700\u8981\u9010\u9875\u722c\u53d6\u97f3\u9891\u6587\u4ef6\u3002\u8fd9\u901a\u5e38\u6d89\u53ca\u5230\u4fee\u6539URL\u6216\u53d1\u9001\u7279\u5b9a\u7684\u8bf7\u6c42\u53c2\u6570\u3002\u5047\u8bbe\u76ee\u6807\u7f51\u7ad9\u7684\u5206\u9875\u901a\u8fc7URL\u53c2\u6570\u63a7\u5236\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u4e00\u4e2a\u5faa\u73af\u6765\u904d\u5386\u6240\u6709\u9875\u9762\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">base_url = &#39;http:\/\/example.com\/page=&#39;  # \u66ff\u6362\u4e3a\u76ee\u6807\u7f51\u7ad9\u7684URL\u683c\u5f0f<\/p>\n<p>page_number = 1<\/p>\n<p>while True:<\/p>\n<p>    url = f&#39;{base_url}{page_number}&#39;<\/p>\n<p>    response = requests.get(url)<\/p>\n<p>    if response.status_code != 200:<\/p>\n<p>        break  # \u5982\u679c\u8bf7\u6c42\u5931\u8d25\uff0c\u505c\u6b62\u722c\u53d6<\/p>\n<p>    html_content = response.content<\/p>\n<p>    soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<p>    audio_tags = soup.find_all(&#39;audio&#39;)<\/p>\n<p>    if not audio_tags:<\/p>\n<p>        break  # \u5982\u679c\u6ca1\u6709\u627e\u5230\u97f3\u9891\u6807\u7b7e\uff0c\u505c\u6b62\u722c\u53d6<\/p>\n<p>    audio_urls = [tag.get(&#39;src&#39;) for tag in audio_tags[:5] if tag.get(&#39;src&#39;)]<\/p>\n<p>    for i, audio_url in enumerate(audio_urls):<\/p>\n<p>        save_path = os.path.join(save_directory, f&#39;page_{page_number}_audio_{i + 1}.mp3&#39;)<\/p>\n<p>        download_audio(audio_url, save_path)<\/p>\n<p>        print(f&#39;Downloaded {save_path}&#39;)<\/p>\n<p>    page_number += 1<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e03\u3001\u5904\u7406\u5f02\u5e38\u60c5\u51b5<\/p>\n<\/p>\n<p><p>\u5728\u5b9e\u9645\u64cd\u4f5c\u4e2d\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u5404\u79cd\u5f02\u5e38\u60c5\u51b5\uff0c\u6bd4\u5982\u7f51\u7edc\u95ee\u9898\u3001\u6587\u4ef6\u5199\u5165\u9519\u8bef\u7b49\u3002\u6211\u4eec\u9700\u8981\u6dfb\u52a0\u5f02\u5e38\u5904\u7406\u4ee3\u7801\u6765\u63d0\u9ad8\u7a0b\u5e8f\u7684\u5065\u58ee\u6027\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">def download_audio(url, save_path):<\/p>\n<p>    try:<\/p>\n<p>        response = requests.get(url)<\/p>\n<p>        response.r<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>se_for_status()<\/p>\n<p>        with open(save_path, &#39;wb&#39;) as file:<\/p>\n<p>            file.write(response.content)<\/p>\n<p>    except requests.RequestException as e:<\/p>\n<p>        print(f&#39;Failed to download {url}: {e}&#39;)<\/p>\n<p>    except IOError as e:<\/p>\n<p>        print(f&#39;Failed to save {save_path}: {e}&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u516b\u3001\u603b\u7ed3<\/p>\n<\/p>\n<p><p>\u901a\u8fc7\u4e0a\u8ff0\u6b65\u9aa4\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u722c\u53d6\u6bcf\u98755\u4e2a\u97f3\u9891\u6587\u4ef6\u3002<strong>\u63d0\u53d6\u97f3\u9891\u94fe\u63a5<\/strong>\u662f\u5173\u952e\u6b65\u9aa4\uff0c\u786e\u4fdd\u6211\u4eec\u80fd\u591f\u83b7\u53d6\u5230\u97f3\u9891\u6587\u4ef6\u7684URL\u3002\u6b64\u5916\uff0c\u9010\u9875\u722c\u53d6\u548c\u5904\u7406\u5f02\u5e38\u60c5\u51b5\u4e5f\u662f\u9700\u8981\u6ce8\u610f\u7684\u65b9\u9762\u3002\u901a\u8fc7\u5408\u7406\u7684\u4ee3\u7801\u7ed3\u6784\u548c\u5f02\u5e38\u5904\u7406\uff0c\u53ef\u4ee5\u63d0\u9ad8\u722c\u53d6\u7a0b\u5e8f\u7684\u5065\u58ee\u6027\u548c\u53ef\u9760\u6027\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u722c\u53d6\u7279\u5b9a\u7f51\u7ad9\u7684\u97f3\u9891\u6587\u4ef6\uff1f<\/strong><br \/>\u4e3a\u4e86\u4f7f\u7528Python\u722c\u53d6\u97f3\u9891\u6587\u4ef6\uff0c\u53ef\u4ee5\u4f7f\u7528\u5e93\u5982Requests\u548cBeautifulSoup\u6765\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3002\u9996\u5148\uff0c\u60a8\u9700\u8981\u5206\u6790\u76ee\u6807\u7f51\u7ad9\u7684\u7ed3\u6784\uff0c\u627e\u51fa\u97f3\u9891\u6587\u4ef6\u7684URL\uff0c\u7136\u540e\u7f16\u5199\u4ee3\u7801\u6765\u63d0\u53d6\u8fd9\u4e9b\u94fe\u63a5\u3002\u4f7f\u7528requests\u5e93\u53d1\u9001\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\uff0c\u63a5\u7740\u7528BeautifulSoup\u89e3\u6790HTML\uff0c\u627e\u5230\u97f3\u9891\u6587\u4ef6\u7684\u94fe\u63a5\u5e76\u4e0b\u8f7d\u3002\u786e\u4fdd\u9075\u5b88\u7f51\u7ad9\u7684\u722c\u866b\u89c4\u5219\uff0c\u907f\u514d\u5bf9\u670d\u52a1\u5668\u9020\u6210\u8fc7\u591a\u8d1f\u62c5\u3002<\/p>\n<p><strong>\u5728\u722c\u53d6\u97f3\u9891\u65f6\u5982\u4f55\u5904\u7406\u5206\u9875\uff1f<\/strong><br \/>\u5904\u7406\u5206\u9875\u65f6\uff0c\u53ef\u4ee5\u901a\u8fc7\u89c2\u5bdf\u7f51\u9875\u7684URL\u7ed3\u6784\u6216\u7f51\u7edc\u8bf7\u6c42\u6765\u627e\u5230\u4e0b\u4e00\u9875\u7684\u94fe\u63a5\u3002\u5728\u4ee3\u7801\u4e2d\u5b9e\u73b0\u5faa\u73af\uff0c\u76f4\u5230\u6ca1\u6709\u66f4\u591a\u9875\u53ef\u4ee5\u722c\u53d6\u3002\u53ef\u4ee5\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u6216BeautifulSoup\u67e5\u627e\u201c\u4e0b\u4e00\u9875\u201d\u7684\u94fe\u63a5\uff0c\u5e76\u5c06\u5176\u4f5c\u4e3a\u65b0\u7684\u8bf7\u6c42\u8fdb\u884c\u5904\u7406\u3002\u540c\u65f6\uff0c\u6ce8\u610f\u5728\u6bcf\u6b21\u8bf7\u6c42\u65f6\u9650\u5236\u8bf7\u6c42\u9891\u7387\uff0c\u4ee5\u9632\u6b62\u88ab\u7f51\u7ad9\u5c01\u7981\u3002<\/p>\n<p><strong>\u722c\u53d6\u97f3\u9891\u540e\u5982\u4f55\u4fdd\u5b58\u548c\u7ba1\u7406\u6587\u4ef6\uff1f<\/strong><br \/>\u5728\u4e0b\u8f7d\u97f3\u9891\u6587\u4ef6\u65f6\uff0c\u53ef\u4ee5\u4f7f\u7528Python\u7684os\u5e93\u521b\u5efa\u6587\u4ef6\u5939\u6765\u5b58\u50a8\u4e0b\u8f7d\u7684\u6587\u4ef6\u3002\u4e3a\u6bcf\u4e2a\u97f3\u9891\u6587\u4ef6\u547d\u540d\u65f6\uff0c\u53ef\u4ee5\u4f7f\u7528\u5176\u6807\u9898\u6216\u5176\u4ed6\u552f\u4e00\u6807\u8bc6\u7b26\uff0c\u786e\u4fdd\u6587\u4ef6\u540d\u4e0d\u91cd\u590d\u3002\u9009\u62e9\u5408\u9002\u7684\u6587\u4ef6\u683c\u5f0f\u8fdb\u884c\u4fdd\u5b58\uff0c\u786e\u4fdd\u60a8\u53ef\u4ee5\u65b9\u4fbf\u5730\u8bbf\u95ee\u548c\u64ad\u653e\u8fd9\u4e9b\u97f3\u9891\u6587\u4ef6\u3002\u5efa\u7acb\u4e00\u4e2a\u6570\u636e\u5e93\u6216\u4f7f\u7528CSV\u6587\u4ef6\u8bb0\u5f55\u4e0b\u8f7d\u7684\u97f3\u9891\u4fe1\u606f\uff0c\u53ef\u4ee5\u5e2e\u52a9\u60a8\u66f4\u597d\u5730\u7ba1\u7406\u548c\u67e5\u627e\u97f3\u9891\u5185\u5bb9\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u722c\u53d6\u6bcf\u98755\u4e2a\u97f3\u9891\u7684\u65b9\u6cd5\uff1a\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HT [&hellip;]","protected":false},"author":3,"featured_media":1085327,"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\/1085321"}],"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=1085321"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1085321\/revisions"}],"predecessor-version":[{"id":1085332,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1085321\/revisions\/1085332"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1085327"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1085321"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1085321"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1085321"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}