Extract metadata and content from WeChat Official Account articles. Use when user needs to parse WeChat article URLs (mp.weixin.qq.com), extract article info (title, author, content, publish time, cover image), or convert WeChat articles to structured data. Supports various article types including posts, videos, images, voice messages, and reposts.
The WeChat Article Extractor skill is designed to efficiently retrieve and structure content from WeChat Official Account articles. It addresses the challenge of parsing and extracting detailed information from WeChat URLs, which often contain a mix of text, media, and metadata that is difficult to access directly. By automating the extraction process, this skill enables users to obtain essential article data such as title, author, content, publication time, and cover images, transforming unstructured web content into a structured format ready for analysis or integration into other systems.
This skill provides comprehensive capabilities for handling different types of WeChat content, including standard posts, videos, images, voice messages, and reposts. It can parse URLs, extract both article-specific and account-specific metadata, and return the full HTML content when required. The extractor supports additional options such as following migrated account links, extracting embedded WeChat links, capturing article tags, and retrieving repost metadata. It also incorporates error handling for scenarios like deleted content, expired links, rate limiting, or blocked accounts, ensuring robust performance across diverse WeChat pages and structures.
WeChat Article Extractor is particularly useful for developers, content analysts, researchers, or businesses that need to monitor or archive WeChat content systematically. Typical use cases include aggregating articles for content analysis, converting WeChat posts into structured datasets for reporting, and integrating article information into applications or databases. Its flexible extraction options make it suitable for both real-time retrieval from URLs and offline parsing from saved HTML content, offering a practical tool for anyone working with WeChat content at scale.
You can use the extract function with the article URL as input. The skill will return structured metadata and content including title, author, publish time, and HTML content.
Yes, it supports multiple types including posts, videos, images, voice messages, text-only articles, and reposts.
Yes, you can pass HTML content along with the source URL to the extractor, allowing offline or pre-fetched content to be processed.
The skill requires npm packages: cheerio for HTML parsing, dayjs for date formatting, request-promise for HTTP requests, qs for query parsing, and lodash.unescape for HTML entities.
The skill includes error handling and will return specific error codes indicating if the content is deleted, blocked, expired, or if there are access limitations.
Quick Setup:
.claude/skills/