Back to Details

jina-reader

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Jina Reader

Jina Reader

Extract clean web content via Jina AI — without exposing your server IP.
通过Jina AI提取干净的网页内容，且不会暴露你的服务器IP。

Read a URL

读取URL

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

Search the web (top 5 results with full content)

网页搜索（返回前5条结果的完整内容）

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

Fact-check a statement

对陈述进行事实核查

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

Options

可选参数

FlagDescriptionDefault
--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 outputoff
标识说明默认值
--mode
read
、
search
、
ground
read
--selector
用于提取特定区域的CSS选择器—
--wait
提取前等待加载的CSS选择器—
--remove
要移除的CSS选择器（逗号分隔）—
--proxy
地理代理的国家代码（
br
、
us
等）		—
--nocache
强制获取最新内容（跳过缓存）关闭
--format
markdown
、
html
、
text
、
screenshot
markdown
--json
输出原始JSON关闭

Examples

示例

bash
undefined
bash
undefined

Extract article content

提取文章内容

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

Extract specific section via CSS selector

通过CSS选择器提取特定区块

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

Remove nav and ads before extraction

提取前移除导航、广告等元素

{baseDir}/scripts/reader.sh --remove "nav,footer,.ads" "https://example.com"
{baseDir}/scripts/reader.sh --remove "nav,footer,.ads" "https://example.com"

Search with JSON output

搜索并输出JSON格式结果

{baseDir}/scripts/reader.sh --mode search --json "AI enterprise trends"
{baseDir}/scripts/reader.sh --mode search --json "AI enterprise trends"

Read via Brazil proxy

通过巴西代理读取内容

{baseDir}/scripts/reader.sh --proxy br "https://example.com.br"
{baseDir}/scripts/reader.sh --proxy br "https://example.com.br"

Fact-check a claim

事实核查声明

{baseDir}/scripts/reader.sh --mode ground "Tesla is the most valuable car company"
undefined
{baseDir}/scripts/reader.sh --mode ground "Tesla is the most valuable car company"
undefined

API Key

API密钥

bash
export JINA_API_KEY="jina_..."
Free tier: 10M tokens (no signup needed). Get key at https://jina.ai/reader/
bash
export JINA_API_KEY="jina_..."
免费额度：10M tokens（无需注册），可前往https://jina.ai/reader/ 获取密钥。

Pricing

定价

  • Read: ~$0.005/page (standard) | 3x for ReaderLM-v2
  • Search: 10K tokens fixed + variable per result
  • Ground: ~300K tokens/request (~30s latency)
  • 读取模式： ~0.005美元/页（标准版本）| 使用ReaderLM-v2则为3倍价格
  • 搜索模式： 固定扣除1万tokens + 按结果数量浮动扣除
  • 核验模式： ~30万tokens/次请求（延迟约30秒）

Why Jina Reader?

为什么选择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
  • IP保护 — 请求通过Jina的基础设施路由，不会经过你的服务器
  • 干净的markdown输出 — 可读性优化提取 + 可选ReaderLM-v2支持
  • 支持动态内容 — 无头Chrome可渲染JavaScript
  • 结构化提取 — 支持JSON Schema用于数据提取