{"id":204071,"date":"2025-05-29T10:15:49","date_gmt":"2025-05-29T02:15:49","guid":{"rendered":"https:\/\/server.hk\/cnblog\/204071\/"},"modified":"2025-05-29T10:15:49","modified_gmt":"2025-05-29T02:15:49","slug":"%e5%a6%82%e4%bd%95%e5%88%a9%e7%94%a8-python-%e7%88%ac%e8%99%ab%e8%a7%a3%e5%86%b3%e6%8a%96%e9%9f%b3%e8%a7%86%e9%a2%91%e7%bf%bb%e9%a1%b5%e5%8a%a0%e8%bd%bd%e9%99%90%e5%88%b6%ef%bc%9f","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/204071\/","title":{"rendered":"\u5982\u4f55\u5229\u7528 Python \u722c\u866b\u89e3\u51b3\u6296\u97f3\u89c6\u9891\u7ffb\u9875\u52a0\u8f7d\u9650\u5236\uff1f"},"content":{"rendered":"<p><b><\/b>     <\/p>\n<h1>\u5982\u4f55\u5229\u7528 Python \u722c\u866b\u89e3\u51b3\u6296\u97f3\u89c6\u9891\u7ffb\u9875\u52a0\u8f7d\u9650\u5236\uff1f<\/h1>\n<p><span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\">\u6587\u7ae0<\/span>\u4e0d\u77e5\u9053\u5927\u5bb6\u662f\u5426\u719f\u6089\uff1f\u4eca\u5929\u6211\u5c06\u7ed9\u5927\u5bb6\u4ecb\u7ecd<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\">\u300a\u5982\u4f55\u5229\u7528 Python \u722c\u866b\u89e3\u51b3\u6296\u97f3\u89c6\u9891\u7ffb\u9875\u52a0\u8f7d\u9650\u5236\uff1f\u300b<\/span>\uff0c\u8fd9\u7bc7\u6587\u7ae0\u4e3b\u8981\u4f1a\u8bb2\u5230<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\"><\/span>\u7b49\u7b49\u77e5\u8bc6\u70b9\uff0c\u5982\u679c\u4f60\u5728\u770b\u5b8c\u672c\u7bc7\u6587\u7ae0\u540e\uff0c\u6709\u66f4\u597d\u7684\u5efa\u8bae\u6216\u8005\u53d1\u73b0\u54ea\u91cc\u6709\u95ee\u9898\uff0c\u5e0c\u671b\u5927\u5bb6\u90fd\u80fd\u79ef\u6781\u8bc4\u8bba\u6307\u51fa\uff0c\u8c22\u8c22\uff01\u5e0c\u671b\u6211\u4eec\u80fd\u4e00\u8d77\u52a0\u6cb9\u8fdb\u6b65\uff01<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.17golang.com\/uploads\/20241026\/1729945658671ce03ab0ea6.jpg\" class=\"aligncenter\"><\/p>\n<p><strong>\u6296\u97f3\u89c6\u9891\u722c\u53d6\u4e2d\u7ffb\u9875\u95ee\u9898<\/strong><\/p>\n<p>\u5728\u4f7f\u7528 python \u722c\u866b\u722c\u53d6\u6296\u97f3\u89c6\u9891\u65f6\uff0c\u9047\u5230\u4e86\u7ffb\u9875\u95ee\u9898\uff0c\u65e0\u6cd5\u83b7\u53d6\u6240\u6709\u89c6\u9891\u94fe\u63a5\u3002<\/p>\n<p><strong>\u95ee\u9898\u63cf\u8ff0<\/strong><\/p>\n<p>\u5728\u6296\u97f3\u4e2d\uff0c\u5f53\u60a8\u8bbf\u95ee\u535a\u4e3b\u4e3b\u9875\u65f6\uff0c\u6700\u521d\u53ea\u80fd\u770b\u5230 20 \u4e2a\u5de6\u53f3\u7684\u89c6\u9891\u53ca\u5176\u94fe\u63a5\u3002\u968f\u540e\u5f53\u60a8\u5c06\u9f20\u6807\u6ed1\u5230\u9875\u9762\u5e95\u90e8\u65f6\uff0c\u4f1a\u81ea\u52a8\u52a0\u8f7d\u540e\u7eed\u89c6\u9891\u5185\u5bb9\u3002\u4f46\u662f\uff0c\u722c\u866b\u7a0b\u5e8f\u53ea\u4f1a\u83b7\u53d6\u5230\u6700\u521d\u7684 20 \u4e2a\u89c6\u9891\u94fe\u63a5\uff0c\u65e0\u6cd5\u81ea\u52a8\u5b8c\u6210\u7ffb\u9875\u52a0\u8f7d\u65b0\u89c6\u9891\u3002<\/p>\n<p><strong>\u89e3\u51b3\u65b9\u6848<\/strong><\/p>\n<p>\u89e3\u51b3\u7ffb\u9875\u95ee\u9898\u7684\u5173\u952e\u5728\u4e8e\uff0c\u4e86\u89e3\u6296\u97f3\u662f\u57fa\u4e8e\u4ec0\u4e48\u673a\u5236\u8fdb\u884c\u7ffb\u9875\u52a0\u8f7d\u7684\u3002\u5728\u6296\u97f3\u4e2d\uff0c\u7ffb\u9875\u5b9e\u9645\u4e0a\u662f\u901a\u8fc7\u4fee\u6539 url \u4e2d\u7684 max_cursor \u53c2\u6570\u5b9e\u73b0\u7684\u3002max_cursor \u53c2\u6570\u7684\u503c\u4ee3\u8868\u4e86\u5f53\u524d\u9875\u9762\u4e2d\u6700\u540e\u4e00\u6761\u89c6\u9891\u7684 id\u3002<\/p>\n<p>\u4e3a\u4e86\u5728\u722c\u866b\u4e2d\u5b9e\u73b0\u7ffb\u9875\u529f\u80fd\uff0c\u6211\u4eec\u9700\u8981\uff1a<\/p>\n<ol>\n<li>\u83b7\u53d6\u5f53\u524d\u9875\u9762\u6700\u540e\u4e00\u4e2a\u89c6\u9891\u7684 id\uff0c\u4f5c\u4e3a max_cursor \u53c2\u6570\u7684\u503c\u3002<\/li>\n<li>\u5c06\u66f4\u65b0\u540e\u7684 max_cursor \u53c2\u6570\u6dfb\u52a0\u5230 url \u4e2d\uff0c\u5e76\u8bf7\u6c42\u65b0\u7684\u9875\u9762\u3002<\/li>\n<li>\u91cd\u590d\u6b65\u9aa4 1 \u548c 2\uff0c\u76f4\u5230\u83b7\u53d6\u5230\u6240\u6709\u89c6\u9891\u3002<\/li>\n<\/ol>\n<p><strong>\u793a\u4f8b\u4ee3\u7801<\/strong><\/p>\n<p>\u4ee5\u4e0b\u793a\u4f8b\u4ee3\u7801\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528 max_cursor \u53c2\u6570\u5b9e\u73b0\u6296\u97f3\u89c6\u9891\u7ffb\u9875\uff1a<\/p>\n<pre>import requests\nfrom bs4 import BeautifulSoup\n\nheaders = {\n    \"user-agent\": \"Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/103.0.0.0 Safari\/537.36\",\n    'cookie': 'douyin.com',\n    'sec-ch-ua': '\"Not\/A)Brand\";v=\"99\", \"Google Chrome\";v=\"103\", \"Chromium\";v=\"103\"'\n}\n\n# \u521d\u59cb URL\nurl = 'https:\/\/www.douyin.com\/user\/MS4wLjABAAAAp3rtDfotN7-mHjDIr0XR2XJ5g0C1DIVAuJYgBHJYX-xJLZgoHvfN0r0yAWTLybn7'\n\n# \u5b58\u50a8\u89c6\u9891 ID \u5217\u8868\nvideo_ids = []\n\n#max_cursor \u521d\u59cb\u5316\u4e3a0\nmax_cursor = 0\n\nwhile True:\n    # \u62fc\u63a5\u65b0\u7684 URL\n    new_url = url + f\"?max_cursor={max_cursor}\"\n\n    # \u8bf7\u6c42\u9875\u9762\n    r = requests.get(url=new_url, headers=headers)\n    html = BeautifulSoup(r.text, 'html.parser')\n\n    # \u83b7\u53d6\u89c6\u9891 ID\n    result = html.find_all('a', 'B3AsdZT9 chmb2GX8 UwG3qaZV')\n    for item in result:\n        vid = item['href'][-19:]  # \u83b7\u53d6\u89c6\u9891 ID\n        video_ids.append(vid)  # \u6dfb\u52a0\u5230\u5217\u8868\u4e2d\n\n    # \u66f4\u65b0 max_cursor\n    max_cursor = video_ids[-1]\n\n    # \u5224\u65ad\u662f\u5426\u5df2\u7ecf\u83b7\u53d6\u5230\u6240\u6709\u89c6\u9891\n    if len(result) &lt; 20:\n        break\n\n# \u6253\u5370\u51fa\u89c6\u9891 ID \u5217\u8868\nprint(video_ids)<\/pre>\n<p>\u4eca\u5929\u5e26\u5927\u5bb6\u4e86\u89e3\u4e86\u7684\u76f8\u5173\u77e5\u8bc6\uff0c\u5e0c\u671b\u5bf9\u4f60\u6709\u6240\u5e2e\u52a9\uff1b\u5173\u4e8e\u6587\u7ae0\u7684\u6280\u672f\u77e5\u8bc6\u6211\u4eec\u4f1a\u4e00\u70b9\u70b9\u6df1\u5165\u4ecb\u7ecd\uff0c\u6b22\u8fce\u5927\u5bb6\u5173\u6ce8\u516c\u4f17\u53f7\uff0c\u4e00\u8d77\u5b66\u4e60\u7f16\u7a0b~<\/p>\n<p>      \u7248\u672c\u58f0\u660e \u672c\u6587\u8f6c\u8f7d\u4e8e\uff1aphp \u5982\u6709\u4fb5\u72af\uff0c\u8bf7\u8054\u7cfb\u5220\u9664<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u5982\u4f55\u5229\u7528 Python \u722c\u866b\u89e3\u51b3&#46;&#46;&#46;<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4925],"tags":[],"class_list":["post-204071","post","type-post","status-publish","format-standard","hentry","category-4925"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/204071","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/comments?post=204071"}],"version-history":[{"count":0,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/204071\/revisions"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=204071"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=204071"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=204071"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}