Back to Details

read-gzh

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

读取公众号文章

Read WeChat Official Account Articles

给 cc 一个微信公众号链接，自动抓取文章内容（包括配图），生成结构化总结。
Provide cc with a WeChat Official Account link, and it will automatically capture the article content (including images) and generate a structured summary.

触发词

Trigger Words

  • /read-gzh <链接>
  • /read-gzh <链接1> <链接2> ...
    （批量处理）
  • "帮我读一下这篇公众号"
  • "总结一下这篇文章"
  • /read-gzh <link>
  • /read-gzh <link1> <link2> ...
    (Batch processing)
  • "Help me read this official account article"
  • "Summarize this article"

功能

Features

  1. 抓取文章 — 标题、作者、正文、配图
  2. 图片识别 — 下载配图，提取图中文字/信息
  3. 结构化总结 — 核心观点、关键信息、金句提取
  4. 批量处理 — 支持多链接一次处理
  1. Article Capture — Title, author, main text, images
  2. Image Recognition — Download images, extract text/information from images
  3. Structured Summary — Core viewpoints, key information, golden sentences extraction
  4. Batch Processing — Support processing multiple links at once

执行流程

Execution Process

Step 1: 抓取文章

Step 1: Capture Article

使用 
scripts/fetch_wechat_article.py
脚本抓取：
  • 标题、作者
  • 完整正文（图文文章）或摘要（视频号）
  • 所有配图链接
bash
python3 .claude/skills/read-gzh/scripts/fetch_wechat_article.py "<公众号链接>"
Use the 
scripts/fetch_wechat_article.py
script to capture:
  • Title, author
  • Full text (graphic article) or abstract (Video Account)
  • All image links
bash
python3 .claude/skills/read-gzh/scripts/fetch_wechat_article.py "<WeChat Official Account link>"

Step 2: 下载并识别配图

Step 2: Download and Recognize Images

对于每篇文章：
  1. 创建临时目录存放图片
  2. 下载所有配图
  3. 读取每张图片，提取其中的文字或关键信息
  4. 将图片内容纳入总结
bash
undefined
For each article:
  1. Create a temporary directory to store images
  2. Download all images
  3. Read each image and extract text or key information from it
  4. Incorporate image content into the summary
bash
undefined

下载图片

Download image

curl -o /tmp/article_img_1.jpg "<图片链接>"
undefined
curl -o /tmp/article_img_1.jpg "<image link>"
undefined

Step 3: 生成总结

Step 3: Generate Summary

输出格式：
markdown
undefined
Output format:
markdown
undefined

📄 文章总结

📄 Article Summary

基本信息

Basic Information

  • 标题：xxx
  • 作者：xxx
  • 类型：图文文章 / 视频号
  • 配图：x 张
  • Title: xxx
  • Author: xxx
  • Type: Graphic Article / Video Account
  • Images: x pieces

核心观点

Core Viewpoints

  1. xxx
  2. xxx
  3. xxx
  1. xxx
  2. xxx
  3. xxx

关键信息

Key Information

  • xxx
  • xxx
  • xxx
  • xxx

金句摘录

Golden Sentences Excerpt

"xxx" "xxx"
"xxx" "xxx"

图片内容

Image Content

  • 图1：xxx
  • 图2：xxx
  • Image 1: xxx
  • Image 2: xxx

思考/迭代点

Reflections/Iteration Points

  • 对我有什么启发？
  • 有什么可以借鉴的？

---
  • What insights does this give me?
  • What can be learned from this?

---

批量处理

Batch Processing

当提供多个链接时，逐个处理并汇总：
markdown
undefined
When multiple links are provided, process them one by one and summarize:
markdown
undefined

📚 批量文章总结

📚 Batch Article Summary

文章 1: xxx

Article 1: xxx

[总结内容]
[Summary content]

文章 2: xxx

Article 2: xxx

[总结内容]
[Summary content]

汇总洞察

Summary Insights

  • 共同主题：xxx
  • 差异点：xxx

---
  • Common Theme: xxx
  • Differences: xxx

---

注意事项

Notes

  1. 视频号文章：只能获取简介，无法获取视频内容
  2. 图片类文章：重点识别图片中的文字
  3. 需要登录的内容：无法获取
创建：2026-01-22
  1. Video Account Articles: Only the introduction can be obtained, video content cannot be accessed
  2. Image-only Articles: Focus on recognizing text in images
  3. Content requiring login: Cannot be accessed
Created: 2026-01-22