Skip to content
TakoAPI
Back to skills

wechat-article-extractor-skill

by freestylefly

Coding Agents & IDEs
1.1kDownloads reported by clawskills.sh
4Stars
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Extract metadata and content from WeChat Official Account articles.

Description

What This Skill Does

Extracts metadata and content from WeChat Official Account articles given a mp.weixin.qq.com URL. Returns structured data including title, author, publish time, cover image, account info, and HTML content. Handles deleted, expired, rate-limited, and migrated content with specific error codes.

WeChat's closed ecosystem makes article data inaccessible via standard APIs, so this skill handles the page parsing and anti-scraping quirks directly.

When to Use It

  • Archiving WeChat articles before they get deleted
  • Converting WeChat posts to structured data for a CMS
  • Monitoring a brand's WeChat official account output
  • Extracting article metadata for content aggregation pipelines
  • Pulling WeChat article content into a translation workflow

Example Workflow

INPUT

User asks: Extract the title, author, and publish time from https://mp.weixin.qq.com/s?__biz=ABC123

AGENT
  1. 1

    Calls extract() with the provided mp.weixin.qq.com URL

  2. 2

    Receives success response with code 0

  3. 3

    Reads msg_title, msg_author, and msg_publish_time_str from the data object

  4. 4

    Formats the extracted fields into a readable summary

OUTPUT

Title: '示例标题', Author: '张三', Published: '2024/01/15 10:30:00'

Installation

clawhub install freestylefly/wechat-article-extractor-skill

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links