skills.rest
jackjin1997
jackjin1997COMMUNITY
Explore all skills by this author →
WebsiteGitHub

news-extractor

Extract news articles from Chinese platforms into JSON and Markdown.

11|2|Updated Feb 3, 2026
Search Tags:#content#scraping#extraction#wechat#news#toutiao
One-click install
npx skills add https://github.com/jackjin1997/ClawForge --skill news-extractor-jackjin1997
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: news-extractor
Source: https://github.com/jackjin1997/ClawForge/tree/main/skills/news-extractor
Command: npx skills add https://github.com/jackjin1997/ClawForge --skill news-extractor-jackjin1997

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pydantic, requests, curl_cffi, tenacity, parsel, demjson3, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the extraction of news articles from various Chinese news platforms, saving users the time and effort of manually copying and pasting content.

Core Features & Use Cases

  • Multi-Platform Support: Extracts content from WeChat Official Accounts, Toutiao, Netease News, Sohu News, and Tencent News.
  • Flexible Output: Provides extracted content in both structured JSON and readable Markdown formats.
  • Use Case: When you find an interesting article on Toutiao, you can use this Skill to quickly get its content in a clean Markdown format for easy reading or sharing.

Quick Start

Use the news-extractor skill to extract the content from the provided URL.

Frequently Asked Questions about news-extractor

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

FAQPage Schema
How do I extract news articles from WeChat and Toutiao into Markdown?▼

To extract news articles from WeChat and Toutiao into Markdown, use this Skill to fetch content from specified URLs and automatically format the output into readable Markdown or structured JSON.

Can I scrape content from Netease, Sohu, and Tencent News platforms?▼

Yes, you can scrape content from Netease, Sohu, and Tencent News platforms. The Skill supports extraction from these Chinese news sources alongside WeChat and Toutiao for structured data analysis.

Do I need specific Python libraries to parse Chinese news content?▼

Yes, you need specific Python libraries including requests, curl_cffi, parsel, and tenacity to parse Chinese news content. These dependencies handle web scraping, parsing, and retry logic.

What is the best way to automate extracting news content from multiple Chinese platforms?▼

The best way to automate extracting news content from multiple Chinese platforms is using a dedicated scraping Skill that supports WeChat, Toutiao, Netease, Sohu, and Tencent, outputting clean JSON or Markdown formats.

Does the news extractor output structured JSON data for article analysis?▼

Yes, the news extractor outputs structured JSON data for article analysis. It also provides Markdown format, allowing you to choose between readable consumption and structured data extraction.

Related Skills

Explore More Content & Communication Skills→
GolferGeekGolferGeek

create-worktree-skill

Create isolated Git worktrees with independent ports and configuration.

Community
Basic
Celia-12Celia-12

file-converter

Convert data between CSV, JSON, YAML, XML, Markdown, and image formats.

Community
Advanced
NanmiCoderNanmiCoder
60

news-extractor

Extract article content from Chinese news platforms into JSON and Markdown.

Community
Advanced
0xmariowu0xmariowu
40

sogou_weixin

Scrape Sogou Weixin search results for Chinese WeChat Official Account articles.

Community
Intermediate