Extract logged-in Xiaohongshu posts into markdown files with OCR.
npx skills add https://github.com/eatbreads/.agents --skill xhs-web-note-capture
Please help me install this Agent Skill. Skill: xhs-web-note-capture Source: https://github.com/eatbreads/.agents/tree/main/skills/xhs-web-note-capture Command: npx skills add https://github.com/eatbreads/.agents --skill xhs-web-note-capture
Capture complete Xiaohongshu (小红书) note content that is only available from a real logged-in browser session, including hidden or image-heavy posts, and convert them into local markdown files with metadata and OCRed text so the full post can be archived, searched, or edited offline.
Save the logged-in note page HTML with cookies, then run the extractor to convert the saved HTML into a markdown file in your chosen output directory.
High-intent search queries and answers about installing and using this skill.
To extract logged-in Xiaohongshu posts into markdown, you save the authenticated note page HTML with cookies, then run the extractor to parse window.__INITIAL_STATE__ and generate one markdown file per post with metadata and images.
Yes, you can capture hidden or image-heavy Xiaohongshu notes requiring xsec_token by navigating from an authenticated author or search page to obtain durable pc_user URLs, saving the full HTML with cookies for the extractor to parse.
Yes, Xiaohongshu note extraction supports image OCR on macOS by utilizing a bundled macOS Vision OCR binary to transcribe downloaded images from the note's imageList, including the raw OCR output alongside original image links in the final markdown file.
Parsing window.__INITIAL_STATE__ for Xiaohongshu web scraping works by extracting structured note data directly from the saved HTML to reliably read the title, body, tags, imageList, and interactInfo without triggering anti-bot blocks.
Yes, you need to save cookies to extract Xiaohongshu posts to local files because the extractor relies on saved HTML from an authenticated browser session to access restricted content and preserve metadata for offline markdown archiving.
hc-tecFetch and inspect XiaoHongShu saved notes and boards with Playwright.
PaulKinlanParse markdown files and generate structured editorial review notes.
n0rvynExtract text from images and scanned PDFs using the macOS Vision framework.
felipesantiago-coderAutomate web page navigation, clicking, form filling, and data extraction via CLI or Node.js runtime.
