xhs-copy-v2

Extract Xiaohongshu image URLs, OCR text, and package ZIP deliverables.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/zwmopen/skills --skill xhs-copy-v2
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: xhs-copy-v2
Source: https://github.com/zwmopen/skills/tree/main/xhs-copy-v2_skill_update
Command: npx skills add https://github.com/zwmopen/skills --skill xhs-copy-v2

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires beautifulsoup4, httpx, and includes scripts (resource) components.

What problem does it solve?

Xiaohongshu content capture often yields unstable links and inconsistent assets. This skill provides end-to-end capture, real image URL extraction, OCR-backed content, and a packaged final deliverable.

Core Features & Use Cases

  • Real image URL extraction from Xiaohongshu shares, including image URLs without file extensions.
  • OCR processing of downloaded images to assemble readable notes.
  • End-to-end packaging: output a clean finished product ZIP with the required folder structure (00_原始提取, 01_成品发布, 02_生图提示词).
  • Cover image generation with device extraction (when available).

Quick Start

Run the workflow to capture a Xiaohongshu note, resolve real image URLs, download originals, perform OCR, generate cover art, and assemble the final product ZIP.

Frequently Asked Questions about xhs-copy-v2

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

FAQPage Schema
How do I extract real image URLs from Xiaohongshu posts for web scraping?

This skill resolves real image URLs from Xiaohongshu posts, including addresses without file extensions, and downloads the original images for reliable content packaging.

Can I automatically OCR Xiaohongshu images and assemble readable notes?

Yes, you can OCR Xiaohongshu images to assemble readable text. The workflow downloads original images and applies OCR processing to extract and compile the post content automatically.

Does Xiaohongshu content packaging require network access and Python dependencies?

Xiaohongshu content packaging requires network access and Python dependencies. The workflow relies on httpx and beautifulsoup4 to parse notes, fetch images, and generate the final ZIP deliverable.

What is the best way to package scraped Xiaohongshu content into a structured ZIP file?

The best way to package scraped Xiaohongshu content is automated end-to-end packaging. It generates a structured ZIP file containing folders for raw extraction, finished publishing content, and image generation prompts.

Why does Xiaohongshu image extraction yield unstable links and inconsistent assets?

Xiaohongshu image extraction yields unstable links because share URLs hide real image addresses and omit file extensions. This skill resolves the actual image URLs to ensure consistent asset downloads.