{"slug":"wechat-article-ingest","title":"\u516c\u4f17\u53f7\u6587\u7ae0\u91c7\u96c6","description":"\u628a\u516c\u4f17\u53f7\u6587\u7ae0\u91c7\u96c6\u8fdb\u77e5\u8bc6\u5e93\uff0c\u8f6c\u6210\u7ed3\u6784\u5316 Markdown\u3002","category":"\u7d20\u6750\u4e0e\u6548\u7387","tags":["\u516c\u4f17\u53f7","\u91c7\u96c6","\u7d20\u6750"],"author":"Chubby","source_url":"https://github.com/chubbyguan/chubbyskills/blob/main/wechat-article-ingest/SKILL.md","license":"MIT","status":"published","verification":"source_reviewed","verification_notes":"\u6765\u6e90 chubbyguan/chubbyskills\uff08wechat-article-ingest/SKILL.md\uff09\uff0c\u672c\u5730\u6253\u5305\u4e0a\u4f20\uff1b\u672a\u6267\u884c\u5305\u5185\u811a\u672c\u3002","revision":"91b4384f15264b298d5723bfc39b9bb8","created_at":"2026-10-28T08:54:30+00:00","updated_at":"2026-10-28T08:54:50+00:00","source_repo":"","source_path":"","source_commit":"","source_updated_at":"","stars":0,"proxy_score":null,"score":null,"grade":null,"dimensions":{},"evaluation":{},"installs":0,"platforms":[],"formats":[],"category_slug":"workflow","category_name":"\u7d20\u6750\u4e0e\u6548\u7387","usage_guide":{},"read_url":"https://shiliuai.cn/api/v2/skills/wechat-article-ingest","skill_url":"https://shiliuai.cn/api/v2/skills/wechat-article-ingest/files/SKILL.md","download_url":"https://shiliuai.cn/api/v2/skills/wechat-article-ingest/download","install_url":"https://shiliuai.cn/api/v2/skills/wechat-article-ingest/install","files":[{"path":"SKILL.md","bytes":3652,"url":"https://shiliuai.cn/api/v2/skills/wechat-article-ingest/files/SKILL.md"},{"path":"requirements.txt","bytes":57,"url":"https://shiliuai.cn/api/v2/skills/wechat-article-ingest/files/requirements.txt"},{"path":"scripts/extract.py","bytes":5132,"url":"https://shiliuai.cn/api/v2/skills/wechat-article-ingest/files/scripts/extract.py"},{"path":"scripts/fetch_article.py","bytes":8901,"url":"https://shiliuai.cn/api/v2/skills/wechat-article-ingest/files/scripts/fetch_article.py"}],"content":"---\nname: wechat-article-ingest\ndescription: >\n  \u5fae\u4fe1\u516c\u4f17\u53f7\u6587\u7ae0 \u2192 Markdown \u63d0\u53d6 + A\u5c42\u89c2\u70b9\u63d0\u53d6 + B\u5c42\u95ee\u9898\u94fe\u751f\u6210\u3002\n  \u652f\u6301\u76f4\u63a5\u94fe\u63a5\u6293\u53d6\u548c PDF \u63d0\u53d6\u4e24\u79cd\u65b9\u5f0f\u3002\nmetadata:\n  category: \"productivity\"\n  triggers: \"[\\\"\u5904\u7406\u516c\u4f17\u53f7\u6587\u7ae0\\\", \\\"\u516c\u4f17\u53f7\u5165\u5e93\\\", \\\"\u63d0\u53d6\u89c2\u70b9\\\", \\\"A+B \u5904\u7406\\\", \\\"\u628a\u8fd9\u7bc7\u6587\u7ae0\u8f6c\u6210 markdown\\\", \\\"\u6293\u53d6\u516c\u4f17\u53f7\u6587\u7ae0\\\"]\"\n  version: \"1.0.0\"\n  tags: \"[\\\"productivity\\\", \\\"wechat\\\", \\\"article-ingest\\\", \\\"knowledge-management\\\"]\"\n---\n\n# \u5fae\u4fe1\u516c\u4f17\u53f7\u6587\u7ae0\u5904\u7406 Skill\n\n\u5c06\u5fae\u4fe1\u516c\u4f17\u53f7\u6587\u7ae0\u8f6c\u6362\u4e3a Markdown\uff0c\u751f\u6210 A \u5c42\u89c2\u70b9\u63d0\u53d6 + B \u5c42\u95ee\u9898\u94fe\uff0c\u5b58\u5165\u77e5\u8bc6\u5e93\u3002\n\n## \u4e24\u79cd\u6a21\u5f0f\n\n### \u6a21\u5f0f 1\uff1a\u76f4\u63a5\u94fe\u63a5\u6293\u53d6\uff08\u63a8\u8350\uff09\n\n```bash\npython scripts/fetch_article.py \"https://mp.weixin.qq.com/s/xxxxx\"\n```\n\n\u516c\u4f17\u53f7\u6587\u7ae0 URL \u662f\u516c\u5f00\u7684\uff0c\u4e0d\u9700\u8981\u767b\u5f55\uff0c\u76f4\u63a5\u6293\u53d6\u5373\u53ef\u3002\n\n### \u6a21\u5f0f 2\uff1aPDF \u63d0\u53d6\n\n```bash\npython scripts/extract.py \"path/to/article.pdf\"\n```\n\n\u9002\u7528\u4e8e\u901a\u8fc7\u300c\u7b14\u8bb0\u540c\u6b65\u52a9\u624b\u300d\u7b49\u5de5\u5177\u5bfc\u51fa\u7684 PDF\u3002\n\n## \u73af\u5883\u8981\u6c42\n\n```bash\n# Python 3.10+\npip install beautifulsoup4 markitdown pymupdf\n\n# \u6216\u8005\u7528 uv\nuv pip install beautifulsoup4 markitdown pymupdf\n```\n\n## \u4f7f\u7528\u65b9\u6cd5\n\n### \u5355\u7bc7\u5904\u7406\uff08\u94fe\u63a5\uff09\n\n```bash\npython scripts/fetch_article.py \"https://mp.weixin.qq.com/s/xxxxx\" --output ./output\n```\n\n\u94fe\u63a5\u6a21\u5f0f\u4f1a\u5c3d\u91cf\u4fdd\u7559\uff1a\n\n- \u6807\u9898\u5c42\u7ea7\uff1a`h1`/`h2`/`h3` \u4f1a\u8f6c\u6210 Markdown \u6807\u9898\n- \u56fe\u7247\uff1a`data-src` / `src` \u4f1a\u8f6c\u6210 Markdown \u56fe\u7247\u5f15\u7528\n- \u94fe\u63a5\uff1a\u6b63\u6587\u91cc\u7684 `<a>` \u4f1a\u8f6c\u6210 Markdown \u94fe\u63a5\n\n### \u5355\u7bc7\u5904\u7406\uff08PDF\uff09\n\n```bash\npython scripts/extract.py \"path/to/article.pdf\" --output ./output\n```\n\n### A+B \u5904\u7406\uff08\u9700\u8981 Agent\uff09\n\n```\n\u5e2e\u6211\u5904\u7406\u8fd9\u7bc7\u6587\u7ae0\uff1ahttps://mp.weixin.qq.com/s/xxxxx\n\u63d0\u53d6\u89c2\u70b9 + \u95ee\u9898\u94fe\n```\n\n## \u6838\u5fc3\u6d41\u7a0b\n\n```\n\u516c\u4f17\u53f7\u94fe\u63a5/PDF \u2192 \u63d0\u53d6\u5185\u5bb9 \u2192 A\u5c42\u89c2\u70b9\u63d0\u53d6 + B\u5c42\u95ee\u9898\u94fe \u2192 \u5b58\u5165\u77e5\u8bc6\u5e93\n```\n\n## A\u5c42\uff1a\u89c2\u70b9\u63d0\u53d6\n\n\u751f\u6210 `\u89c2\u70b9\u63d0\u53d6-{\u4f5c\u8005}-{\u4e3b\u9898}.md`\uff1a\n\n- \ud83d\udd34 \u652f\u67f1\u89c2\u70b9\uff08P1-P6\uff09\uff1a\u6587\u7ae0\u6700\u6838\u5fc3\u7684\u8bba\u70b9\n- \ud83d\udfe1 \u652f\u6491\u89c2\u70b9\uff08S1-S8\uff09\uff1a\u652f\u6491\u652f\u67f1\u7684\u8bba\u636e\n- \ud83d\udfe2 \u5ef6\u4f38\u89c2\u70b9\uff08E1-E4\uff09\uff1a\u53ef\u4ee5\u5ef6\u4f38\u601d\u8003\u7684\u65b9\u5411\n- Takeaway\uff1a\u6bcf\u6761\u542b\u6838\u5fc3\u89c2\u70b9 + \u884c\u52a8\u6307\u5411\n\n## B\u5c42\uff1a\u95ee\u9898\u94fe\n\n\u751f\u6210 `\u95ee\u9898\u94fe-{\u4f5c\u8005}-{\u4e3b\u9898}.md`\uff1a\n\n- 3-5 \u6761\u95ee\u9898\u94fe\uff0c\u6bcf\u6761\u5bf9\u5e94\u4e00\u4e2a\u6838\u5fc3\u4e3b\u9898\n- \u6bcf\u6761\u94fe\u5206 L1\uff08\u5b89\u5168\u533a\uff09\u2192 L2\uff08\u8fb9\u7f18\u533a\uff09\u2192 L3\uff08\u6838\u5fc3\u533a\uff09\n- \u6bcf\u6761\u94fe 6 \u9053\u95ee\u9898\n- \u7ec8\u5c40\u79cd\u5b50\uff1a\u4e00\u4e2a\u5e26\u56de\u5bb6\u7684\u95ee\u9898\n\n## \u77e5\u8bc6\u5e93\u76ee\u5f55\u7ed3\u6784\n\n```\n\u77e5\u8bc6\u5e93/\n\u251c\u2500\u2500 \u7d20\u6750\u5e93/\n\u2502   \u2514\u2500\u2500 \u516c\u4f17\u53f7\u6587\u7ae0/\n\u2502       \u2514\u2500\u2500 {\u516c\u4f17\u53f7\u540d}/\n\u2502           \u2514\u2500\u2500 article.md\n\u2514\u2500\u2500 wiki/\n    \u2514\u2500\u2500 \u5916\u90e8\u8f93\u5165/\n        \u2514\u2500\u2500 \u516c\u4f17\u53f7/\n            \u2514\u2500\u2500 {\u516c\u4f17\u53f7\u540d}/\n                \u2514\u2500\u2500 {\u4e3b\u9898}/\n                    \u251c\u2500\u2500 \u89c2\u70b9\u63d0\u53d6.md\n                    \u2514\u2500\u2500 \u95ee\u9898\u94fe.md\n```\n\n## \u5df2\u77e5\u9650\u5236\n\n- \u90e8\u5206\u516c\u4f17\u53f7\u6587\u7ae0\u6709\u9632\u76d7\u94fe\uff0c\u53ef\u80fd\u6293\u53d6\u5931\u8d25\n- \u7eaf\u56fe\u7247\u6587\u7ae0\u65e0\u6cd5\u63d0\u53d6\u6587\u5b57\n- MarkItDown \u9700\u8981 Python \u2265 3.10\n- PDF \u63d0\u53d6\u8d28\u91cf\u53d6\u51b3\u4e8e\u539f\u6587\u6392\u7248\uff1b\u94fe\u63a5\u6a21\u5f0f\u6bd4 PDF \u6a21\u5f0f\u66f4\u80fd\u4fdd\u7559\u56fe\u7247\u548c\u94fe\u63a5\n- \u957f\u6587\u6863\u62c6\u5206\u9700\u8981 Agent \u5224\u65ad\n\n## \u53c2\u8003\u9879\u76ee\n\n- [microsoft/markitdown](https://github.com/microsoft/markitdown) - PDF/\u6587\u6863\u8f6c Markdown\n- [pymupdf/PyMuPDF](https://github.com/pymupdf/PyMuPDF) - PDF \u5904\u7406\u5e93\n- [beautifulsoup4](https://www.crummy.com/software/BeautifulSoup/) - HTML \u89e3\u6790\n\n## \u2696\ufe0f \u5408\u89c4\u58f0\u660e\n\n\u4ec5\u4f9b**\u4e2a\u4eba\u5b66\u4e60\u4e0e\u7814\u7a76**\u4f7f\u7528\u3002\u8bf7\u9075\u5b88\u76ee\u6807\u5e73\u53f0\u7684\u670d\u52a1\u6761\u6b3e\uff08ToS\uff09\u4e0e robots \u89c4\u5219\uff0c\u63a7\u5236\u8bf7\u6c42\u9891\u7387\uff0c\u4e0d\u8981\u7528\u4e8e\u6279\u91cf\u6293\u53d6\u3001\u5546\u7528\u722c\u53d6\u6216\u4fb5\u72af\u4ed6\u4eba\u6743\u76ca\u7684\u573a\u666f\u3002\u4e0b\u8f7d\u5185\u5bb9\u7684\u7248\u6743\u5f52\u539f\u4f5c\u8005\u6240\u6709\u3002\n","usage":"\u8bfb\u53d6 SKILL.md\uff0c\u5e76\u6309\u9700\u8bfb\u53d6\u914d\u5957\u6587\u4ef6\uff1b\u4e0b\u8f7d ZIP \u83b7\u53d6\u5b8c\u6574\u5305\u3002\u6280\u80fd\u662f\u4efb\u52a1\u65b9\u6cd5\uff0c\u4e0d\u6388\u4e88\u65b0\u589e\u8d26\u6237\u3001\u4ed8\u8d39\u6216\u7cfb\u7edf\u6743\u9650\u3002"}
