{"skill":{"slug":"haibo-jina-reader","displayName":"Jina Reader","summary":"Extract clean, readable markdown content from any URL using Jina Reader API. Use when you need to fetch and parse web pages without dealing with HTML, JavaScript rendering, or paywalls. Ideal for research, article summarization, content analysis, and working with search results from tavily-search, web_search, or searxng skills.","description":"---\nname: jina-reader\ndescription: Extract clean, readable markdown content from any URL using Jina Reader API. Use when you need to fetch and parse web pages without dealing with HTML, JavaScript rendering, or paywalls. Ideal for research, article summarization, content analysis, and working with search results from tavily-search, web_search, or searxng skills.\n---\n\n# Jina Reader\n\n## Overview\n\nJina Reader provides clean markdown extraction from any URL, bypassing HTML complexity, JavaScript rendering, and many paywalls. It returns structured text content with metadata (title, URL, published time) that's perfect for AI analysis.\n\n## Quick Start\n\n### Extract markdown content\n```bash\nscripts/jina-reader.py <url>\n```\n\n### Extract with JSON metadata\n```bash\nscripts/jina-reader.py <url> --format json\n```\n\n### Save to file\n```bash\nscripts/jina-reader.py <url> -o output.md\n```\n\n## Core Operations\n\n### 1. Basic Extraction\n\nExtract clean markdown from any URL:\n```bash\nscripts/jina-reader.py https://example.com/article\n```\n\n**Returns:** Full markdown content including title, metadata headers, and structured text.\n\n**Use when:** You need readable text from a webpage for summarization, analysis, or content processing.\n\n### 2. JSON Format\n\nGet structured data with metadata:\n```bash\nscripts/jina-reader.py https://example.com/article --format json\n```\n\n**Returns:**\n```json\n{\n  \"status\": \"success\",\n  \"metadata\": {\n    \"title\": \"Article Title\",\n    \"url\": \"https://example.com/article\",\n    \"published\": \"Mon, 10 Feb 2026 12:00:00 GMT\"\n  },\n  \"content\": \"Markdown content...\"\n}\n```\n\n**Use when:** You need programmatic access to metadata or want to integrate with other tools.\n\n### 3. Shell Script Quick Access\n\nFor simple one-liners:\n```bash\nscripts/jina-reader.sh https://example.com/article\n```\n\n**Returns:** Raw markdown content directly to stdout.\n\n**Use when:** Quick extraction without arguments or when piping to other commands.\n\n## Usage Patterns\n\n### Combining with Search\n\nWhen using tavily-search, web_search, or searxng skills:\n1. Get search results with relevant URLs\n2. Extract content from top results using jina-reader\n3. Process and summarize the extracted content\n\n```bash\n# Example workflow\nURL=\"https://example.com/article\"\nscripts/jina-reader.py \"$URL\" --format json | jq -r '.content'\n```\n\n### Batch Processing\n\nExtract from multiple URLs:\n```bash\nfor url in $(cat urls.txt); do\n  scripts/jina-reader.py \"$url\" -o \"output/$(basename $url).md\"\ndone\n```\n\n### Content Analysis\n\nPipe extracted content to analysis tools:\n```bash\nscripts/jina-reader.py https://example.com/article | wc -w\nscripts/jina-reader.py https://example.com/article | grep -i \"keyword\"\n```\n\n## Options\n\n### Python Script (`jina-reader.py`)\n\n- `url` (required): The URL to extract content from\n- `-f, --format`: Output format - `markdown` or `json` (default: markdown)\n- `-t, --timeout`: Request timeout in seconds (default: 30)\n- `-o, --output`: Save output to file instead of stdout\n\n### Shell Script (`jina-reader.sh`)\n\n- `url` (required): The URL to extract content from\n\n## Limitations\n\n- **Timeout:** Default 30 seconds. Increase with `-t` for slow-loading pages\n- **Rate limits:** Jina Reader API has rate limits. Use batching strategically\n- **Dynamic content:** Can't extract content generated by client-side JavaScript after page load\n- **Authentication:** Can't access pages requiring login or special headers\n\n## Troubleshooting\n\n### Timeout errors\n```bash\nscripts/jina-reader.py <url> -t 60  # Increase timeout\n```\n\n### Invalid URLs\nThe tool auto-prepends `https://` if missing. Use fully qualified URLs for reliability.\n\n### Empty content\nSome pages may block scraping. Try the shell script as fallback, or verify the URL is accessible.\n\n## Resources\n\n### scripts/jina-reader.py\nFull-featured Python tool with JSON output, metadata extraction, and file saving.\n\n### scripts/jina-reader.sh\nLightweight shell script for quick markdown extraction.\n","tags":{"content-extraction":"1.0.0","latest":"1.0.0","research":"1.0.0","web-scraping":"1.0.0"},"stats":{"comments":0,"downloads":1632,"installsAllTime":61,"installsCurrent":4,"stars":0,"versions":1},"createdAt":1770748110858,"updatedAt":1778989626151},"latestVersion":{"version":"1.0.0","createdAt":1770748110858,"changelog":"Initial release: Extract clean markdown from any URL using Jina Reader API","license":null},"metadata":null,"owner":{"handle":"smile-xuc","userId":"s175fqvaq1g8g5aany22ra7wj988572k","displayName":"smile-xuc","image":"https://avatars.githubusercontent.com/u/19898401?v=4"},"moderation":null}