Jina Reader

by sundial-orgb80cde2ef852No license663 starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 7 months ago

Web content extraction via Jina AI Reader API. Three modes: read (URL to markdown), search (web search + full content), ground (fact-checking). Extracts clean content without exposing server IP.

Includes scriptsResearch & Analysis
AI-generated overview

Extracts clean web content, runs web searches, and fact-checks claims through the Jina AI Reader API.

What it does
Wraps the Jina AI Reader API in a shell script with three modes: read converts a URL into markdown, html, text, or a screenshot; search returns top web results with full content; ground fact-checks a statement. Options control CSS selectors for extraction and removal, waiting, geo-proxy country, cache bypass, and raw JSON output. Requests route through Jina's infrastructure so the caller's server IP is not exposed.
When to use it
Use it to pull readable article content from a URL, to gather current web results with their full text, or to check whether a factual claim holds up. It suits research and content-gathering tasks where clean text and IP protection matter.
Requirements
Requires curl and jq binaries, network access to the Jina AI Reader API, and a JINA_API_KEY environment variable (free tier available). Ships an executable script at scripts/reader.sh.

Jina Reader

Extract clean web content via Jina AI — without exposing your server IP.

Read a URL

bash
{baseDir}/scripts/reader.sh "https://example.com/article"

Search the web (top 5 results with full content)

bash
{baseDir}/scripts/reader.sh --mode search "latest AI news 2025"

Fact-check a statement

bash
{baseDir}/scripts/reader.sh --mode ground "OpenAI was founded in 2015"

Options

FlagDescriptionDefault
--moderead, search, groundread
--selectorCSS selector to extract specific region—
--waitCSS selector to wait for before extraction—
--removeCSS selectors to remove (comma-separated)—
--proxyCountry code for geo-proxy (br, us, etc.)—
--nocacheForce fresh content (skip cache)off
--formatmarkdown, html, text, screenshotmarkdown
--jsonRaw JSON outputoff

Examples

bash
# Extract article content{baseDir}/scripts/reader.sh "https://blog.example.com/post"
# Extract specific section via CSS selector{baseDir}/scripts/reader.sh --selector "article.main" "https://example.com"
# Remove nav and ads before extraction{baseDir}/scripts/reader.sh --remove "nav,footer,.ads" "https://example.com"
# Search with JSON output{baseDir}/scripts/reader.sh --mode search --json "AI enterprise trends"
# Read via Brazil proxy{baseDir}/scripts/reader.sh --proxy br "https://example.com.br"
# Fact-check a claim{baseDir}/scripts/reader.sh --mode ground "Tesla is the most valuable car company"

API Key

bash
export JINA_API_KEY="jina_..."

Free tier: 10M tokens (no signup needed). Get key at https://jina.ai/reader/

Pricing

  • Read: ~$0.005/page (standard) | 3x for ReaderLM-v2
  • Search: 10K tokens fixed + variable per result
  • Ground: ~300K tokens/request (~30s latency)

Why Jina Reader?

  • IP protection — requests route through Jina's infra, not your server
  • Clean markdown — readability extraction + optional ReaderLM-v2
  • Dynamic content — headless Chrome renders JavaScript
  • Structured extraction — JSON schema support for data extraction

Source and attribution

Source:sundial-org/awesome-openclaw-skillsinskills/jina-readerat commitb80cde2

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

Jina Reader Agent Skill | SourceWeft