RAG Web Browser
Pricing
Try for freeRAG Web Browser
odin-kael/rag-web-browser-worker
A high-performance web scraper for RAG and AI, featuring Google search integration, dual-mode extraction (HTTP/Browser), and multi-format output.
Search Queries or URLs | 搜索关键词或 URLRequired
Enter Google Search keywords or URLs to scrape. Each line runs as a separate task. | 输入 Google 搜索关键词或要抓取的 URL。每行作为独立任务运行。
Type: array
Max Results | 最大结果数Optional
Maximum number of search results to return (1-100). Ignored if query is a URL. | 返回的最大搜索结果数（1-100）。如果 query 是 URL 则忽略。
Type: integer
Default: 3
Output Format | 输出格式Optional
The format of the output content. | 输出内容的格式。
Type: select
Default: markdown
Options:
MarkdownPlain Text | 纯文本HTML
Scraping Tool | 抓取工具Optional
⚠️ Raw HTTP: Fast but CANNOT handle JavaScript, Cloudflare, or anti-bot protection. Use for: static HTML pages, APIs, simple websites. ✅ Browser: Handles dynamic JS, SPAs, Cloudflare, but slower. | ⚠️ Raw HTTP：快速但无法处理 JavaScript、Cloudflare 或反爬保护。适用于：静态 HTML 页面、API、简单网站。✅ 浏览器：可处理动态 JS、SPA、Cloudflare，但较慢。
Type: select
Default: browser-playwright
Options:
Raw HTTP (Static sites only) | 仅静态站点Browser (Dynamic/Protected) | 动态/受保护站点
Request Timeout (secs) | 请求超时(秒)Optional
Maximum time in seconds to wait for a request to complete (1-300). | 请求完成的最大等待时间（秒，1-300）。
Type: integer
Default: 40
Max Retries | 最大重试Optional
Number of retry attempts for failed requests. | 失败请求的重试次数。
Type: integer
Default: 1
Concurrency | 并发数Optional
Number of parallel scraping operations. Higher = faster but more resources. | 并行抓取操作数。越高越快但消耗更多资源。
Type: integer
Default: 3
Dynamic Content Wait (secs) | 动态内容等待(秒)Optional
Time to wait for dynamic page content (browser mode only). | 等待动态页面内容的时间（仅浏览器模式）。
Type: integer
Default: 10
Remove Cookie Warnings | 移除 Cookie 警告Optional
Automatically remove cookie warning banners from pages. | 自动移除页面的 Cookie 警告横幅。
Type: boolean
Default: true
Debug Mode | 调试模式Optional
Enable debug logging and performance metrics. | 启用调试日志和性能指标。
Type: boolean
Default: false
Pricing
Failed results don't count
Rating
5.0
Developer
Kael Odin
Worker Stats
6 Total runs
Success rate: 100.00%
Last updated: Apr 15, 2026
Categories
Share
You might also like
Explore more popular scrapers from our marketplace
Google Search Results (SERP) Scraper API
by CoreClaw
It queries the Google search engine by keyword and returns a structured SERP summary, including the final search parameters, organic results, related queries, and people-also-ask data.
4.8
604 runs
From $1.2/1,000 results
Dataset Deduplication & Merge Tool
by Kael Odin
Dedup Datasets Worker is a powerful tool for merging and deduplicating datasets from multiple JSON/JSONL files. Fully optimized for the CafeScraper platform with enhanced features and robust error handling.
5.0
15 runs
From $1.2/1,000 results
Google Sheets Import Export Tool
by Kael Odin
A powerful Google Sheets data import export tool designed for data synchronization, backup, and integration between Google Sheets and external systems. Supports three operation modes, two authentication methods, batch processing, data deduplication, and automatic backup.
5.0
2 runs
From $1.2/1,000 results
Cheerio Web Scraping
by Kael Odin
A high-speed static page scraper based on Cheerio, designed specifically for static HTML pages. Uses Cheerio for HTML parsing, delivering speeds 10-50 times faster than full browser rendering.
5.0
3 runs
From $1.2/1,000 results