skills.rest
sungaoxiang-backend
sungaoxiang-backendCOMMUNITY
Explore all skills by this author →
GitHub

read-wechat-article

Extract clean text from WeChat public account articles via Playwright.

Updated Jul 20, 2025
Search Tags:#Playwright#text extraction#article extraction#web-scraping#WeChat#content-processing
One-click install
npx skills add https://github.com/sungaoxiang-backend/intelligent-evidence-platform --skill read-wechat-article
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: read-wechat-article
Source: https://github.com/sungaoxiang-backend/intelligent-evidence-platform/tree/main/app/agentic/skills/read-wechat-article
Command: npx skills add https://github.com/sungaoxiang-backend/intelligent-evidence-platform --skill read-wechat-article

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, and includes scripts (resource) components.

What problem does it solve?

Extract clean text from WeChat public account articles.

Core Features & Use Cases

  • Text extraction: Retrieve the full article text from a given WeChat URL (mp.weixin.qq.com) for downstream processing like summarization or data extraction.
  • Content cleaning: Removes non-content elements such as scripts and styles to produce clean text suitable for analysis.
  • Use Case: When you receive a WeChat article URL, run this skill to obtain the article body for AI-based summarization or archival storage.

Quick Start

Run the fetch script with a WeChat article URL to extract its text: python3 scripts/fetch_wechat.py "https://mp.weixin.qq.com/s/xxxxx"

Frequently Asked Questions about read-wechat-article

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract clean text from a WeChat public account article URL?▼

To extract clean text from a WeChat article, run a Playwright-based headless browser workflow that locates the article content in the #js_content element, strips non-content elements like scripts, and returns plain text suitable for analysis.

Can I use Playwright for web scraping WeChat articles to get plain text?▼

Yes, you can use Playwright for web scraping WeChat articles by executing a headless browser script that navigates to the mp.weixin.qq.com URL, isolates the #js_content section, and removes scripts and styles to retrieve plain text.

What is the best way to get WeChat article content for AI summarization?▼

The best way to get WeChat article content for AI summarization is running a Python script that fetches the URL via Playwright, cleans the HTML by stripping non-content elements, and outputs plain text ready for downstream AI processing.

Do I need to install Playwright to extract WeChat article text?▼

Yes, you need to install Playwright as it is the required dependency for the headless browser workflow that dynamically renders the WeChat article page and extracts the text from the DOM element.

Does WeChat article text extraction remove scripts and styles from the output?▼

Yes, WeChat article text extraction removes scripts and styles from the output by cleaning non-content elements within the #js_content container, ensuring the returned text is suitable for analysis and archival processing.

Related Skills

Explore More Content & Communication Skills→
majunbaomajunbao

playwright

Run Playwright CLI commands to capture screenshots and render web pages.

Community
Basic
Leeky1017Leeky1017
1

Summarize

Summarize long-form text into concise digests with key points.

Community
Basic
Prorise-coolProrise-cool
24

scraping-specialist

Scrape websites and extract structured data into CSV or JSON.

Community
Advanced
HuuBarHuuBar

scrapling-skill

Diagnose Scrapling CLI installs and guide static or browser-backed web extraction.

Community
Intermediate