Back to Details

visit-webpage

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Visit Webpage

访问网页

Fetch and extract readable content from web pages as markdown, or download images. Handles JavaScript-rendered content via Jina Reader service.
从网页中获取并提取可读内容为markdown格式，或下载图片。通过Jina Reader服务处理JavaScript渲染的内容。

Setup

设置

Optionally get a Jina API key for higher rate limits:
  1. Create an account at https://jina.ai/
  2. Get your API key from the dashboard
  3. Add to your shell profile (
    ~/.profile
    or 
    ~/.zprofile
    for zsh):
    bash
    export JINA_API_KEY="your-api-key-here"
Without an API key, the service works with rate limits.
可选获取Jina API密钥以获得更高的请求速率限制：
  1. 在https://jina.ai/创建账户
  2. 从控制台获取你的API密钥
  3. 添加到你的shell配置文件中（zsh用户为~/.profile或~/.zprofile）：
    bash
    export JINA_API_KEY="your-api-key-here"
没有API密钥的话，服务仍可使用，但会受到速率限制。

Usage

使用方法

bash
{baseDir}/visit.py <url>
bash
{baseDir}/visit.py <url>

Examples

示例

bash
undefined
bash
undefined

Read an article (returns markdown)

读取文章（返回markdown格式）

{baseDir}/visit.py https://example.com/article
{baseDir}/visit.py https://example.com/article

Fetch documentation

获取文档

{baseDir}/visit.py https://docs.python.org/3/library/asyncio.html
{baseDir}/visit.py https://docs.python.org/3/library/asyncio.html

Download an image (auto-detected by content-type)

下载图片（通过内容类型自动检测）

{baseDir}/visit.py https://example.com/image.png
{baseDir}/visit.py https://example.com/image.png

Then use read tool to view: read /tmp/visit-image-xxx.png

之后使用read工具查看：read /tmp/visit-image-xxx.png

undefined
undefined

Output

输出

For HTML pages: Returns markdown content to stdout.
For images: Downloads the image to a temp file and prints the path. Use the 
read
tool to view it. Supports PNG, JPEG, GIF, and WebP formats.
对于HTML页面：将markdown内容输出到标准输出。
对于图片：将图片下载到临时文件并打印路径。使用
read
工具查看。支持PNG、JPEG、GIF和WebP格式。

Features

功能特性

  • Extracts main content from HTML pages
  • Converts HTML to clean markdown
  • Handles JavaScript-rendered pages via Jina Reader
  • Auto-detects and downloads images to temp files
  • Retries on rate limiting (HTTP 451)
  • 5MB max image size limit
  • 从HTML页面提取主要内容
  • 将HTML转换为整洁的markdown格式
  • 通过Jina Reader处理JavaScript渲染的页面
  • 自动检测并将图片下载到临时文件
  • 遇到速率限制（HTTP 451）时自动重试
  • 图片最大大小限制为5MB

When to Use

使用场景

  • Reading articles, blog posts, or documentation
  • Extracting content from search results
  • Downloading images from URLs (then use 
    read
    to view)
  • Following links found during web search
  • 阅读文章、博客帖子或文档
  • 从搜索结果中提取内容
  • 从URL下载图片（然后使用
    read
    查看）
  • 访问网页搜索中找到的链接