Scripts2026年3月31日·1 分钟阅读

Jina Reader — Convert Any URL to LLM-Ready Text

Convert any URL to clean, LLM-friendly markdown with a simple prefix. Just prepend r.jina.ai/ to any URL. Handles JS-rendered pages, PDFs, and images. 10K+ stars.

TO
TokRepo精选 · Community
快速使用

先拿来用,再决定要不要深挖

这里应该同时让用户和 Agent 知道第一步该复制什么、安装什么、落到哪里。

Just prepend https://r.jina.ai/ to any URL:

curl https://r.jina.ai/https://example.com

Or use the API:

import requests
resp = requests.get("https://r.jina.ai/https://en.wikipedia.org/wiki/AI")
print(resp.text)  # Clean markdown

介绍

Jina Reader converts any URL to clean, LLM-friendly markdown text with a simple prefix. No API key needed for basic usage. Handles JavaScript-rendered pages, PDFs, images (with OCR), and complex layouts. Just prepend https://r.jina.ai/ to any URL and get structured content back. Perfect for RAG pipelines and AI agent web browsing. 10,000+ GitHub stars, Apache 2.0.

Best for: RAG data ingestion, AI agent web browsing, content extraction pipelines Works with: Any LLM pipeline — LangChain, LlamaIndex, Haystack, custom agents


Features

Zero Setup

No installation, no API key, no config. Just prefix any URL:

https://r.jina.ai/https://docs.python.org/3/tutorial/

Content Types

  • Web pages — full JS rendering (Playwright-based)
  • PDFs — text extraction with layout preservation
  • Images — OCR with description generation
  • Google searchhttps://s.jina.ai/your+query for search results

Output Formats

  • Markdown (default) — clean, structured, LLM-optimized
  • HTML — processed HTML with Accept: text/html header
  • JSON — structured with metadata via Accept: application/json

Advanced

  • Screenshotshttps://r.jina.ai/https://example.com?screenshot=true
  • Proxy support — rotate IPs for blocked sites
  • Streaming — stream large documents
  • Self-hosted — run your own instance with Docker

FAQ

Q: What is Jina Reader? A: A service that converts any URL to LLM-friendly markdown by prepending r.jina.ai/ to the URL. Handles JS pages, PDFs, and images. No setup needed. 10K+ stars.

Q: Is there a rate limit? A: Free tier allows 20 requests/minute. Get an API key from jina.ai for higher limits.


🙏

来源与感谢

Created by Jina AI. Licensed under Apache 2.0. jina-ai/reader — 10,000+ GitHub stars

相关资产