Extract Xiaohongshu post content and save it as a Markdown note.
npx skills add https://github.com/Wanger-SJTU/claw_skills --skill xhs-note
Please help me install this Agent Skill. Skill: xhs-note Source: https://github.com/Wanger-SJTU/claw_skills/tree/main/xhs-note Command: npx skills add https://github.com/Wanger-SJTU/claw_skills --skill xhs-note
Automates capturing Xiaohongshu post content (text and images) and saving it as a clean Markdown file, reducing manual copy-paste and post-formatting work.
Run the script with a Xiaohongshu post URL and an optional output directory to generate a Markdown note locally.
High-intent search queries and answers about installing and using this skill.
To save a Xiaohongshu post as a Markdown note, provide the post URL and an output directory to the script. It extracts text, images, author, date, and engagement metrics, saving them locally in a structured Markdown file.
Yes, you need cookies to scrape Xiaohongshu post content. The script requires a ~/cookies.json file for authentication to successfully access and parse the post's __INITIAL_STATE__ data.
Supported Xiaohongshu URL formats for web scraping include explore, discovery, search_result, and short links. The script can automatically resolve redirects from these formats to extract the target post data.
Xiaohongshu note generation requires Python 3 installed in your environment. Along with the Python 3 runtime, you need to ensure the ~/cookies.json authentication file is configured correctly before running the script.
When converting Xiaohongshu posts to Markdown, the extracted metadata includes the post title, author, publication date, images, and engagement metrics. This data is parsed directly from the page's __INITIAL_STATE__ object.
Extracted Xiaohongshu Markdown notes are organized locally by saving them in a user-specified output directory. The script automatically generates a date-based filename for each note to ensure easy chronological organization.
buda-aiConfigure cookie-based authentication for YouTube, Bilibili, Instagram, and Xiaohongshu workflows.
ComwrapUkReplyScrape webpages to extract content, metadata, and images for migration workflows.
ericdahl-devAutomate structured data extraction from web pages using defined criteria.
MimicHunterZExtracts web content from Xiaohongshu and Zhihu via headless browsers for AI analysis.
