SuperAPI AI Directory

wechat-article-fetcher

Writing & research

View repository

Updated 10-16 01:34

About this skill

WeChat Official Account Article Scraping Assistant

This skill is specifically designed to bypass access restrictions on WeChat Official Account articles, convert them into well-structured Markdown files, and automatically handle the localization of image resources.

Use Cases

  • When the user provides a link starting with https://mp.weixin.qq.com/s/ .
  • When the Official Account content needs to be saved as a local Markdown document.
  • When a long Official Account article needs to be structurally summarized or its image resources extracted.

Core Features

  1. Full-text scraping: Automatically handles standard article streams and the special "image page" format.
  2. Mixed text and image layout: Preserves the original positional relationship between paragraphs and images.
  3. Image localization: Automatically downloads remote images to the images/ directory and updates the Markdown reference paths.
  4. Structured output: Automatically recognizes heading levels (H1-H6) and generates an easy-to-read document.
  5. Summary generation: Automatically extracts the article's core viewpoints, key insights, and author information.
  6. flomo integration: Supports pushing the generated article summary to the flomo note-taking platform.

Directory Structure Description

  • bin/main.py: Main execution script, supports an optional flomo API URL parameter.
  • utils/downloader.py: Responsible for HTML and image downloads.
  • utils/parser.py: Responsible for content parsing, cleaning, and structuring.
  • utils/flomo.py: Responsible for sending POST requests to flomo.
  • images/: (Generated after running) Stores localized image resources.

Usage Examples

  1. Local scraping only: Provide the Official Account link directly.
  2. Push to flomo: While providing the link, also provide the flomo secret key (API URL), and the script will automatically complete the push.