Jina-CLI：AI驱动的网页内容读取与网络搜索命令行工具

jina-cli by geekjourneyx/jina-cli

151 周安装量

283 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/geekjourneyx/jina-cli --skill jina-cli

AI/机器学习自动化命令行工具

🇨🇳中文介绍

jina - 网页内容读取与搜索工具

用于读取网页内容并执行 AI 驱动的网络搜索的 CLI 工具。

快速开始

安装 :

curl -fsSL https://raw.githubusercontent.com/geekjourneyx/jina-cli/main/scripts/install.sh | bash

基本用法 :

# 读取一个 URL
jina read --url "https://example.com"

# 搜索网络
jina search --query "golang latest news"

命令

命令	用途
`read`	从 URL 提取内容并转换为适合 LLM 的格式
`search`	使用 AI 驱动的结果处理进行网络搜索
`config`

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

相关 Skills

FlyClaw：零登录航班聚合查询工具，Python实现多源航班信息与价格搜索

4,000,000 周安装

find-skills 技能搜索工具 - Vercel Labs 开源智能体技能包管理器

879,700 周安装

Azure RBAC 权限管理工具：查找最小角色、创建自定义角色与自动化分配

131,500 周安装

React 组合模式指南：Vercel 组件架构最佳实践，提升代码可维护性

118,000 周安装

从任意 URL 提取内容：

# 基本读取
jina read --url "https://example.com"

# 读取并生成图片描述
jina read -u "https://x.com/user/status/123" --with-alt

# 从文件批量处理
jina read --file urls.txt

# 以 Markdown 格式输出
jina read -u "https://example.com" --output markdown

# 保存到文件
jina read -u "https://example.com" --output-file result.md

API 可以通过 --format 参数返回不同格式的内容：

markdown - 默认，适合 LLM 的 Markdown 格式
html - 原始 HTML
text - 纯文本
screenshot - 截图的 URL

# 绕过缓存
jina read -u "https://example.com" --no-cache

# 使用代理
jina read -u "https://example.com" --proxy "http://proxy.com:8080"

# CSS 选择器提取
jina read -u "https://example.com" --target-selector "article.main"

# 等待元素加载
jina read -u "https://example.com" --wait-for-selector "#content"

# 转发 Cookie
jina read -u "https://example.com" --cookie "session=abc123"

# 针对使用哈希路由的单页应用使用 POST 方法
jina read -u "https://example.com/#/route" --post

搜索网络，并自动获取顶部结果的内容：

# 基本搜索
jina search --query "golang latest news"

# 限制到特定网站
jina search -q "AI developments" --site techcrunch.com --site theverge.com

# 限制结果数量
jina search -q "climate change" --limit 10

# 输出格式
jina search -q "news" --output markdown

使用多个 --site 标志将搜索限制在特定域名：

jina search -q "startup funding" --site techcrunch.com --site theverge.com --site wired.com

配置文件：~/.jina-reader/config.yaml

优先级：命令行参数 > 环境变量 > 配置文件 > 默认值

JINA_API_BASE_URL - 读取 API 的 URL（默认：https://r.jina.ai/）
JINA_SEARCH_API_URL - 搜索 API 的 URL（默认：https://s.jina.ai/）
JINA_TIMEOUT - 请求超时时间（秒）（默认：30）
JINA_WITH_GENERATED_ALT - 启用图片描述生成（默认：false）
JINA_OUTPUT_FORMAT - 输出格式：json/markdown（默认：json）
JINA_PROXY_URL - 代理服务器 URL

# 设置配置
jina config set timeout 60
jina config set with-generated-alt true

# 查看配置
jina config list
jina config get timeout
jina config path

JSON 格式（默认，机器可读）：

{
  "success": true,
  "data": {
    "url": "https://example.com",
    "content": "# Extracted Content\n\n...",
    "title": "Page Title"
  }
}

Markdown 格式（人类可读）：

jina read -u "https://example.com" --output markdown

读取社交媒体帖子

# X（Twitter）帖子
jina read -u "https://x.com/elonmusk/status/123456" --with-alt

# --with-alt 标志为嵌入的图片启用 VLM 图片描述生成

# 标准文章
jina read -u "https://blog.example.com/article"

# 使用特定格式
jina read -u "https://example.com" --format text --output markdown

# 1. 搜索主题
jina search -q "quantum computing 2025" --limit 10

# 2. 读取特定结果
jina read --file search_results.txt

创建一个文件，每行一个 URL：

cat > urls.txt << EOF
https://example.com/page1
https://example.com/page2
https://x.com/user/status/123
EOF

jina read --file urls.txt --output markdown

cli/
├── main.go              # 根命令
├── read.go              # read 命令
├── search.go            # search 命令
├── config.go            # config 命令
└── pkg/
    ├── api/client.go    # Jina API HTTP 客户端
    ├── config/          # 配置文件管理
    └── output/          # JSON/Markdown 格式化器

需要 Go 1.24+
零依赖（Cobra 除外）
单一二进制文件分发
配置以简单的 key=value 格式存储（无 YAML 库依赖）

有关 API 详情：请参阅 cli/pkg/api/client.go

2026 年 2 月 28 日

🇺🇸English

jina - Web Content Reader & Search

CLI tool for reading web content and performing AI-powered web searches.

Quick start

Install :

curl -fsSL https://raw.githubusercontent.com/geekjourneyx/jina-cli/main/scripts/install.sh | bash

Basic usage :

# Read a URL
jina read --url "https://example.com"

# Search the web
jina search --query "golang latest news"

Commands

Command	Purpose
`read`	Extract and convert content from URLs to LLM-friendly format
`search`	Search the web with AI-powered result processing
`config`	Manage settings (set/get/list/path)

Read command

Extract content from any URL:

# Basic read
jina read --url "https://example.com"

# Read with image captioning
jina read -u "https://x.com/user/status/123" --with-alt

# Batch process from file
jina read --file urls.txt

# Output as Markdown
jina read -u "https://example.com" --output markdown

# Save to file
jina read -u "https://example.com" --output-file result.md

Response formats

The API can return content in different formats via --format:

markdown - Default, LLM-friendly Markdown
html - Raw HTML
text - Plain text
screenshot - URL to a screenshot

Advanced options

# Bypass cache
jina read -u "https://example.com" --no-cache

# Use proxy
jina read -u "https://example.com" --proxy "http://proxy.com:8080"

# CSS selector extraction
jina read -u "https://example.com" --target-selector "article.main"

# Wait for element to load
jina read -u "https://example.com" --wait-for-selector "#content"

# Forward cookies
jina read -u "https://example.com" --cookie "session=abc123"

# POST method for SPA with hash routing
jina read -u "https://example.com/#/route" --post

Search command

Search the web with automatic content fetching from top results:

# Basic search
jina search --query "golang latest news"

# Restrict to specific sites
jina search -q "AI developments" --site techcrunch.com --site theverge.com

# Limit results
jina search -q "climate change" --limit 10

# Output format
jina search -q "news" --output markdown

Site filtering

Use multiple --site flags to restrict search to specific domains:

jina search -q "startup funding" --site techcrunch.com --site theverge.com --site wired.com

Configuration

Config file: ~/.jina-reader/config.yaml

Priority : Command args > Environment vars > Config file > Defaults

Environment variables :

JINA_API_BASE_URL - Read API URL (default: https://r.jina.ai/)
JINA_SEARCH_API_URL - Search API URL (default: https://s.jina.ai/)
JINA_TIMEOUT - Request timeout in seconds (default: 30)
JINA_WITH_GENERATED_ALT - Enable image captioning (default: false)
JINA_OUTPUT_FORMAT - Output format: json/markdown (default: json)

Config commands :

# Set configuration
jina config set timeout 60
jina config set with-generated-alt true

# View configuration
jina config list
jina config get timeout
jina config path

Output formats

JSON format (default, machine-readable):

{
  "success": true,
  "data": {
    "url": "https://example.com",
    "content": "# Extracted Content\n\n...",
    "title": "Page Title"
  }
}

Markdown format (human-readable):

jina read -u "https://example.com" --output markdown

Common use cases

Reading social media posts

# X (Twitter) posts
jina read -u "https://x.com/elonmusk/status/123456" --with-alt

# The --with-alt flag enables VLM image captioning for embedded images

Reading articles/blogs

# Standard article
jina read -u "https://blog.example.com/article"

# With specific format
jina read -u "https://example.com" --format text --output markdown

Research workflows

# 1. Search for topic
jina search -q "quantum computing 2025" --limit 10

# 2. Read specific results
jina read --file search_results.txt

Batch processing

Create a file with one URL per line:

cat > urls.txt << EOF
https://example.com/page1
https://example.com/page2
https://x.com/user/status/123
EOF

jina read --file urls.txt --output markdown

Project structure

cli/
├── main.go              # Root command
├── read.go              # read command
├── search.go            # search command
├── config.go            # config command
└── pkg/
    ├── api/client.go    # Jina API HTTP client
    ├── config/          # Config file management
    └── output/          # JSON/Markdown formatter

Implementation notes

Go 1.24+ required
Zero dependencies except Cobra
Single binary distribution
Config stored as simple key=value format (no YAML library dependency)

For API details: See cli/pkg/api/client.go

Weekly Installs

128

Repository

geekjourneyx/jina-cli

GitHub Stars

272

First Seen

Feb 28, 2026

Security Audits

Gen Agent Trust HubFail SocketPass SnykFail

Installed on

gemini-cli123

codex123

amp123

cline123

kimi-cli123

cursor123

AI Elements：基于shadcn/ui的AI原生应用组件库，快速构建对话界面

67,500 周安装

JINA_PROXY_URL - Proxy server URL

Jina-CLI：AI驱动的网页内容读取与网络搜索命令行工具

🇨🇳中文介绍

jina - 网页内容读取与搜索工具

快速开始

命令

相关 Skills

读取命令

响应格式

高级选项

搜索命令

网站过滤

配置

输出格式

常见用例