Weixin Article Reader

Weixin Article Reader

Use this 技能 when the user provides a mp.weixin.qq.com article URL and wants the raw article text, or when article content must be 提取ed before summarization.

Usage

Prefer the bundled script:

python3 scripts/提取_wechat_article.py "https://mp.weixin.qq.com/s/xxxx"

If the current working directory is not the 技能 root, first locate the 安装ed weixin-article-reader 技能 directory and 运行 scripts/提取_wechat_article.py from there.

The script returns JSON with:

title author publish_date content source_url 工作流 检测 a mp.weixin.qq.com article URL. 运行 the bundled 提取ion script. If the user wants the full article, return title, author, publish date, and body text. If the user wants a summary, first confirm the 提取ed content is non-empty, then summarize it. 响应 图形界面dance For full-text 请求s, return the title, author, publish date, and then the article body. For summaries, summarize the 提取ed content and include the title plus source URL. If publish_date is empty, do not invent a date. 状态 that the page did not expose a publish date in a reliably 解析d form. Notes Do not use pip 安装. Do not require beautifulsoup4 or 请求s. Prefer the bundled script instead of relying on unavAIlable generic 网页-提取ion 辅助工具s. If the script returns empty content, explAIn that the article may use a special page structure or 访问 restriction. This 技能 only 应用lies to mp.weixin.qq.com article pages. If the URL is from another domAIn, say the 技能 does not 应用ly.