wechat-article-aggregator_skill

This skill aggregates WeChat official account articles by fetching from mptext.top and converts content to Markdown, HTML, or text for quick reading.

Python

122

GitHub Stars

2

Bundled Files

2 months ago

Catalog Refreshed

3 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill wwwzhouhui/skills_collection --skill wechat-article-aggregator

README.md10.3 KB
SKILL.md8.3 KB

Overview

This skill aggregates WeChat public account (公众号) articles using the mptext.top API and converts them into Markdown, HTML, plain text, or JSON. It supports fetching by fakeid or account name, bulk retrieval across multiple accounts, and includes eight popular AI-focused accounts preconfigured. Outputs are saved to a structured output folder with a summary.json metadata file.

How this skill works

The tool calls mptext.top endpoints to list recent articles for each fakeid and to download full article HTML. It extracts the article body from the div with id="js_content", strips scripts/styles, and converts content to the chosen format using optional html2text/BeautifulSoup or a built-in HTML parser. It can be run as a CLI script or imported as a Python module for programmatic use.

When to use it

Collect latest posts from a specific WeChat public account
Batch-aggregate posts from multiple authors for research or newsletters
Create an offline archive of articles in Markdown or HTML
Automate technical news collection for AI/ML topics
Populate a static site or knowledge base with curated WeChat content

Best practices

Store the mptext.top API key in environment variables or secure secrets, never hard-code it
Start with a small --limit and a 1s --interval; increase interval if you hit rate limits (429)
Use --accounts-file to manage and extend the built-in account list safely
Enable html2text and beautifulsoup4 for higher-quality Markdown conversion; the script falls back to a built-in parser if absent
Sanitize and short-truncate filenames to avoid OS issues; the tool truncates titles to 80 characters automatically

Example use cases

Fetch the latest 2 posts from one AI-focused account and save as Markdown for newsletter drafts
Bulk-download 3 latest posts from 10 authors nightly to feed a research database
Resolve account names to fakeids and run a one-shot aggregation: python scripts/fetch_articles.py --fakeids all --limit 2
Integrate the library in a Python pipeline to fetch, parse, and index articles for full-text search
Export article collections as JSON summary to track fetch success/failure across accounts

FAQ

Obtain an API key from mptext.top and pass it via --api-key or set it as an environment variable; the script sends it in X-Auth-Key header.

What if html2text or BeautifulSoup are not installed?

The script falls back to a built-in HTMLParser to extract plain text. Installing beautifulsoup4 and html2text improves Markdown and formatting conversion.