Extract Weibo post text and images into Markdown notes.
npx skills add https://github.com/Wanger-SJTU/claw_skills --skill weibo-note
Please help me install this Agent Skill. Skill: weibo-note Source: https://github.com/Wanger-SJTU/claw_skills/tree/main/weibo-note Command: npx skills add https://github.com/Wanger-SJTU/claw_skills --skill weibo-note
It automates the collection of Weibo posts by extracting text and images from a given post and saving them as Markdown notes for offline reference, archiving, or sharing.
Run the weibo_fetch.py script with a Weibo post URL and an optional output directory to generate a Markdown note.
High-intent search queries and answers about installing and using this skill.
To extract Weibo posts into Markdown notes, run the weibo_fetch.py script with a post URL and an output directory. This fetches text and embeds large images using direct URLs for high fidelity.
Automating Weibo content archiving is done by passing standard or mobile post URLs to the extraction script, which pulls text and images to save as clean Markdown files for offline reference.
Yes, scraping Weibo posts requires Python 3 and a cookies file located at ~/cookies-weibo.json. The script uses these credentials to access and extract content from the specified URLs.
Yes, the Weibo extraction tool supports both standard and mobile post URLs. It processes single-post links to pull text and images, formatting them into a Markdown note saved to your specified directory.
When converting Weibo posts to Markdown, images are handled by embedding large images using direct URLs. This ensures high fidelity visual content is preserved within the generated text note.
A limitation of automated Weibo content extraction is that it supports single-post extraction only. It requires a pre-configured cookies file and does not handle batch or multi-post collection workflows.
jongwonySplit PDF documents into individual chapter files using bookmarks or text boundaries.
zzafergokConvert Markdown documents to HTML using marked.js, pandoc, gomarkdown, or static site generators.
solar-lunaConvert WeChat HTML content into Xiaohongshu posts and publish via MCP.
limzivectorExtract text, tables, and images from web pages via browser automation.
