wechat-reader

Extract WeChat Official Account article text and metadata from mp.weixin.qq.com pages.

2|Updated Mar 7, 2026

Search Tags:#wechat #web-scraping #metadata-extraction #content-extraction #weixin #article-summarization

Ready to run

npx skills add https://github.com/enkira-ai/claude-plugins --skill wechat-reader

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: wechat-reader
Source: https://github.com/enkira-ai/claude-plugins/tree/main/plugins/wechat-reader/skills/wechat-reader
Command: npx skills add https://github.com/enkira-ai/claude-plugins --skill wechat-reader

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the extraction of content from WeChat Official Account articles (mp.weixin.qq.com), handling anti-scraping protection by spoofing the MicroMessenger User-Agent to retrieve full text and metadata for downstream processing.

Core Features & Use Cases

Metadata extraction: title, author, account name, publish time, and full article text.
JSON output: optional structured data suitable for integration with downstream workflows.
After extraction: summarize or analyze the article content; note when images cannot be extracted due to hotlink protection.

Quick Start

Run the extraction script with a WeChat article URL to retrieve the article's title, author, account name, publish time, and full content.

Frequently Asked Questions about wechat-reader

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

FAQPage Schema

How do I extract WeChat article content from an mp.weixin.qq.com link?▼

To extract WeChat article content, you can run an extraction script against the mp.weixin.qq.com URL. It spoofs the MicroMessenger User-Agent to bypass anti-scraping protections and parses the text from the js_content div.

What metadata is extracted from WeChat Official Account articles?▼

WeChat Official Account article metadata extraction retrieves the title, author, account name, and publish time. It also fetches the full article text for downstream reading and analysis.

Why does web scraping fail on WeChat article links and how is it bypassed?▼

Web scraping fails on WeChat links due to anti-scraping protections. This is bypassed by spoofing the MicroMessenger User-Agent in the request header, allowing the extraction script to retrieve the article content successfully.

Can I get structured JSON output from WeChat article extraction?▼

Yes, you can get structured JSON output from WeChat article extraction. This optional format includes the article's title, author, account name, publish time, and full content, making it suitable for integration with downstream workflows.

Does WeChat article extraction support downloading images from the post?▼

No, WeChat article extraction does not support downloading images. Due to hotlink protection, images cannot be extracted, and the script focuses solely on retrieving the full text and metadata.

How do I summarize a WeChat article after sharing the link?▼

To summarize a WeChat article, first extract the content using the article link. Once the text is parsed from the js_content div, you can process the extracted metadata and full text for downstream summarization.