skills.rest
NanmiCoder
NanmiCoderCOMMUNITY
Explore all skills by this author →
𝕏@relakkesyangGitHub

news-extractor

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

60|19|Updated Dec 27, 2025
Search Tags:#markdown#json#wechat#web-scraping#news-extractor#toutiao#netease
One-click install
npx skills add https://github.com/NanmiCoder/claude-code-skills --skill news-extractor
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: news-extractor
Source: https://github.com/NanmiCoder/claude-code-skills/tree/main/plugins/news-extractor/skills/news-extractor
Command: npx skills add https://github.com/NanmiCoder/claude-code-skills --skill news-extractor

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 article content from major Chinese news platforms and converts it into structured JSON and readable Markdown for downstream analysis, auditing, or archiving.

Core Features & Use Cases

  • Platform-aware crawlers for WeChat, Toutiao, Netease, Sohu, and Tencent News.
  • Produces both JSON artifacts and Markdown summaries with media (text, images, videos).
  • Use cases include archiving articles, building summaries, or feeding data into analytics pipelines.

Quick Start

Provide a news URL to extract article content and generate both JSON and Markdown outputs.

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 content from WeChat and Toutiao URLs into JSON?▼

To extract news content from WeChat and Toutiao, you provide the article URLs to automated crawlers that fetch and parse the pages, outputting structured JSON artifacts for easy consumption in analytics or archiving pipelines.

Can I scrape Tencent News and Netease articles and save them as Markdown files?▼

Yes, you can scrape Tencent News and Netease articles. The extraction process parses the web pages and generates readable Markdown summaries alongside JSON, preserving text, images, and video media.

What is the best way to automate archiving Chinese news platform articles?▼

Automating archiving of Chinese news platform articles is best handled by platform-aware crawlers that extract content from WeChat, Sohu, and others, serializing the data into structured JSON and Markdown outputs.

Do I need curl_cffi and parsel to parse news article media into JSON?▼

Yes, curl_cffi and parsel are required dependencies. They work alongside pydantic, requests, tenacity, and demjson3 to fetch web content, parse HTML, and serialize article media into JSON robustly.

Does web scraping for news content support both JSON and Markdown outputs?▼

Web scraping for news content supports both JSON and Markdown outputs. The crawlers extract article details and media, producing structured JSON artifacts and readable Markdown summaries simultaneously.

Related Skills

Explore More Software Engineering Skills→
GolferGeekGolferGeek

create-worktree-skill

Create isolated Git worktrees with independent ports and configuration.

Community
Basic
sungaoxiang-backendsungaoxiang-backend

rss-article-retriever

Fetch, clean, and structure RSS articles into JSON via WeWe-RSS and Playwright.

Community
Advanced
GeorgeKuzoraGeorgeKuzora

pydantic

Validate and coerce Python data into typed Pydantic v2 models.

Community
Advanced
jackjin1997jackjin1997
11

news-extractor

Extract news articles from Chinese platforms into JSON and Markdown.

Community
Intermediate