yhslgg-arch

yhslgg-arch / url-reader

Public

智能网页内容读取器 - Claude Code Skill，支持微信公众号、小红书、今日头条等中国主流平台

114
23
100% credibility
Found Feb 06, 2026 at 52 stars 2x -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

A Python-based tool that intelligently extracts content from Chinese websites like WeChat, Xiaohongshu, and others, formats it as Markdown, downloads images, and saves everything locally.

How It Works

1
🔍 Discover the tool

You hear about URL Reader, a simple helper that grabs full articles from sites like WeChat public accounts or Little Red Book and saves them neatly on your computer.

2
📥 Get it ready

Download the files to your computer and follow easy steps to prepare everything so it's set up and waiting for you.

3
🔗 Link a helper service

Optionally sign up for a web reading service and connect it quickly to handle even the trickiest pages smoothly.

4
📋 Pick your article

Copy the web link of any article you want to keep, from shopping sites, news, or social posts.

5
🚀 Feed it the link

Give the tool the link and watch it smartly figure out the best way to pull out all the good stuff.

6
⏳ Wait a moment

It works its magic, grabbing text, spotting pictures, and organizing everything nicely.

💾 Saved perfectly

Open your folder to find the clean article ready to read anytime, with all pictures downloaded right there.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 52 to 114 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is url-reader?

URL-reader is a Python tool that grabs clean Markdown content from Chinese platforms like WeChat Public Accounts, Xiaohongshu, Toutiao, and more, bypassing anti-bot hurdles with fallback strategies including Firecrawl, Jina Reader, and browser automation. Feed it any URL via CLI command like `python url_reader.py --save`, and it auto-detects the site, extracts text and metadata, downloads images, and saves everything to dated local folders. Ideal for devs needing a reliable url reader ai without manual copying or failed scrapes.

Why is it gaining traction?

Its smart platform detection and tiered fallback ensure high success rates where single-tool scrapers fail, plus seamless output to Markdown with local image assets saves hours on content pipelines. The Claude Code integration shines—drop URLs into claude code agents for instant reads, tying into claude code github workflows or claude github copilot setups without extra claude code install hassle. With 85 stars, it's pulling devs exploring claude code docs and claude code changelog for China-focused url reader needs.

Who should use this?

Content researchers scraping WeChat or Xiaohongshu for claude code web analysis, Python scripters automating claude github actions for knowledge bases, or AI builders piping articles into claude github integration pipelines. Perfect for backend devs handling claude github pr review bots that need fresh url content, or anyone tired of captcha-blocked fetches from Toutiao and Bilibili.

Verdict

Grab it if you're in the Claude ecosystem and need a battle-tested url reader for Chinese sites—check claude code github for the repo, though its 1.0% credibility score and 85 stars signal early-stage maturity with basic docs but no tests. Worth a quick claude code download for prototypes, but watch for updates before production. (198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.