Ready-to-run examples for ContentAPI — the content extraction API for AI agents and RAG pipelines.
- Get a free API key at getcontentapi.com (5,000 requests/month, no credit card required)
- Set your API key:
export CONTENTAPI_KEY=sk_live_your_key_here - Pick an example and run it!
| Example | Language | Description |
|---|---|---|
| RAG Pipeline | Python | Build a complete RAG pipeline with ContentAPI + ChromaDB |
| YouTube Analyzer | Python | Analyze a channel's content, comments, and topics |
| Web Monitor | Python | Monitor pages for changes with webhooks |
| Batch Scraper | Python | Extract 50 URLs in one API call |
| Web Crawler | TypeScript | Crawl documentation sites recursively |
| Content Pipeline | TypeScript | Extract → Summarize → Store pipeline |
| cURL Examples | Shell | All API endpoints as curl commands |
# Python SDK
pip install contentapi
# TypeScript SDK
npm install contentapi
# LangChain integration
pip install langchain-contentapi
# LlamaIndex integration
pip install llamaindex-contentapiContentAPI provides a unified API for extracting content from any source:
| Endpoint | Description |
|---|---|
/web/extract |
Extract clean content from any URL |
/web/extract/batch |
Batch extract up to 50 URLs at once |
/web/search |
Search the web and extract results |
/youtube/transcript |
Get YouTube video transcripts |
/youtube/comments |
Fetch YouTube video comments |
/youtube/channel |
Get channel metadata and videos |
All endpoints return clean, structured data optimized for LLMs and RAG pipelines.
- 🧹 Clean Extraction — Boilerplate-free content from any webpage
- 📦 Batch Processing — Extract up to 50 URLs in a single request
- 🎬 YouTube Support — Transcripts, comments, channel data
- 🔍 Web Search — Search + extract in one call
- 🧩 RAG-Ready — Built-in chunking optimized for embeddings
- ⚡ Fast — Median response time under 2 seconds
- 🔑 Free Tier — 5,000 requests/month, no credit card
- Website
- API Documentation
- Python SDK on PyPI
- MCP Server — Use with Claude, Cursor, Windsurf
- Blog
MIT