content-extractor

Extract text, media URLs, and metadata from online platforms.

28|13|Updated Feb 27, 2026

Search Tags:#multi-platform #web scraping #content extraction #data retrieval #media download

Ready to run

npx skills add https://github.com/wulaosiji/skills --skill content-extractor

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: content-extractor
Source: https://github.com/wulaosiji/skills/tree/main/content-extractor
Command: npx skills add https://github.com/wulaosiji/skills --skill content-extractor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, requests, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill simplifies the process of gathering information from various online platforms, saving users time and effort in content collection.

Core Features & Use Cases

Multi-Platform Support: Extracts content from popular sites like Xiaoyuzhou, Douyin, WeChat Official Accounts, Bilibili, and Xiaohongshu.
Versatile Extraction: Can fetch audio, video, text, and image content depending on the platform.
Use Case: Quickly download the audio from a podcast episode on Xiaoyuzhou, or save a video from Douyin, or extract the full text and images from a WeChat article.

Quick Start

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

Frequently Asked Questions about content-extractor

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

FAQPage Schema

How do I extract content and download media from multiple platforms like Xiaoyuzhou and Bilibili?▼

To extract content from multiple platforms like Xiaoyuzhou and Bilibili, you can use a Skill that fetches text, media URLs, and metadata. It supports downloading audio and video using requests and playwright.

Can I batch extract articles and media URLs from WeChat Official Accounts and Xiaohongshu?▼

Yes, you can batch extract articles and media URLs from WeChat Official Accounts and Xiaohongshu. The Skill supports single and batch extraction, retrieving text, images, and metadata across various platforms.

What is the best way to scrape text and video content from Douyin using Python?▼

The best way to scrape text and video content from Douyin is leveraging libraries like playwright and requests. This approach handles web scraping and data retrieval to fetch video URLs and metadata effectively.

Does web scraping with Playwright support dynamic content extraction for social media?▼

Yes, web scraping with Playwright supports dynamic content extraction for social media. It handles JavaScript-rendered pages to retrieve text, images, and video URLs from platforms like Douyin and Bilibili.

What are the limitations of using requests for data retrieval versus Playwright?▼

Using requests for data retrieval is faster but may fail on JavaScript-heavy social media sites, whereas Playwright handles dynamic rendering. The Skill leverages both to ensure versatile extraction across platforms.