browser-scrape

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Chinese

Extract structured data from web pages using browser automation.

使用浏览器自动化从网页中提取结构化数据。

When you need to gather information from web pages that require JavaScript rendering, authentication, or dynamic content loading.

当你需要从需要JavaScript渲染、身份验证或动态加载内容的网页中收集信息时。

Open page — call
```
mcp__claude-flow__browser_open
```
with the target URL
Wait for content — call
```
mcp__claude-flow__browser_wait
```
for dynamic content to load
Get accessibility tree — call
```
mcp__claude-flow__browser_snapshot
```
for structured page content
Extract text — call
```
mcp__claude-flow__browser_get-text
```
with CSS selectors
Run queries — call
```
mcp__claude-flow__browser_eval
```
with JavaScript to extract structured data
Paginate — use
```
browser_click
```
on next/load-more buttons, then repeat extraction
Close — call
```
mcp__claude-flow__browser_close
```
when done

Prefer
```
browser_snapshot
```
(accessibility tree) over raw HTML for structured extraction
Use
```
browser_eval
```
with
```
document.querySelectorAll
```
for bulk extraction
Add
```
browser_wait
```
between page loads to avoid timing issues
Respect robots.txt and rate limits