Jina Reader

基于 Jina AI Reader API 的网页内容提取技能，用 Bash 脚本经 curl 调用 r.jina.ai、s.jina.ai 与 g.jina.ai，提供 read（URL 转 markdown/html/text/screenshot）、search（网页搜索返回前 5 条完整内容）、ground（事实核查）三种模式，支持 CSS 选择器、地理代理、nocache 与 JSON…

ericsantos

热度 98.63

最近更新 2026-05-21 23:34:28

分类：搜索依赖：代码执行 / 第三方 API / 读写文件应用场景：研究

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add jina-reader

Metadata

name: jina-reader
description: 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.
homepage: https://jina.ai/reader
metadata: {"clawdbot":{"emoji":"📖","requires":{"bins":["curl","jq"]},"primaryEnv":"JINA_API_KEY"}}

Jina Reader

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

Read a URL

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

Search the web (top 5 results with full content)

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

Fact-check a statement

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

Options

Flag	Description	Default
`--mode`	`read`, `search`, `ground`	`read`
`--selector`	CSS selector to extract specific region	—
`--wait`	CSS selector to wait for before extraction	—
`--remove`	CSS selectors to remove (comma-separated)	—
`--proxy`	Country code for geo-proxy (`br`, `us`, etc.)	—
`--nocache`	Force fresh content (skip cache)	off
`--format`	`markdown`, `html`, `text`, `screenshot`	`markdown`
`--json`	Raw JSON output	off

Examples

# 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

Resolution order:

$JINA_API_KEY env var
~/.config/jina/api_key file (canonical local path)

Either is fine. Pick one:

# Option A: env var
export JINA_API_KEY="jina_..."

# Option B: config file (preferred for local installs)
mkdir -p ~/.config/jina && echo "jina_..." > ~/.config/jina/api_key
chmod 600 ~/.config/jina/api_key

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