Browse and scrape any webpage with advanced proxy and rendering capabilities.

Best for:

• Reading webpage content

• Taking screenshots of websites

• Verifying how a site looks from different countries

• Bypassing anti-bot protections

• Accessing JavaScript-rendered content

Key Features:

• Geo-targeting: Access websites from different countries

• JavaScript Rendering: Render SPAs and dynamic content

• Residential/Mobile Proxies: Better success on challenging sites

• Screenshots: Capture visual snapshots of pages

• Anti-Bot Bypass: Multiple bypass levels for protected sites

• Wait Controls: Wait for elements or time before capture

Usage Examples:

1. Simple page browse:

{
  "name": "maps_web",
  "arguments": {
    "url": "https://example.com"
  }
}

2. Screenshot for website:

{
  "name": "maps_web",
  "arguments": {
    "url": "https://example.de",
    "render_js": true,
    "json_response": true,
    "screenshot": true
  }
}

3. Access Cloudflare-protected site:

{
  "name": "maps_web",
  "arguments": {
    "url": "https://protected-site.com",
    "bypass_level": "cloudflare_level_2",
    "residential": true,
    "render_js": true
  }
}

4. Wait for dynamic content:

{
  "name": "maps_web",
  "arguments": {
    "url": "https://spa-app.com",
    "render_js": true,
    "wait_for": ".product-list",
    "wait": 2000
  }
}

Returns: HTML content, or JSON with screenshot (base64) if screenshot=true.

IMPORTANT - Default Behavior:

• Always start with BASIC settings (just the URL)

• Do NOT use advanced parameters (render_js, residential, bypass_level, premium) unless:

  1. The user explicitly requests them, OR

  2. A previous request failed AND the user gives permission to use them

If a request fails:

• The error response will ask for permission to retry with advanced options

• Wait for user confirmation before using advanced parameters

• Never auto-enable advanced parameters without user consent

Extract structured data from webpages using auto-parsing or LLM-powered extraction.

Best for:

• Getting product information (prices, names, descriptions)

• Extracting job listings data

• Parsing search results

• Collecting structured company information

• Real estate listings extraction

Extraction Modes:

• auto: Domain-specific parsers for common sites (Amazon, Google, etc.)

• llm: AI-powered extraction with customizable schemas

Data Schemas (for LLM mode):

• Product: product_page, product_reviews_page, product_search_page, product_seller_page

• Jobs: job_page, job_advert_page, job_search_page

• Company: company_page, company_job_page, company_review_page, company_search_page

• Real Estate: real_estate_page, real_estate_profile_page, real_estate_search_page

• Search: serp_search_page

Usage Examples:

1. Auto-extract from known domain:

{
  "name": "extract_data",
  "arguments": {
    "url": "https://www.amazon.com/dp/B09V3KXJPB",
    "mode": "auto"
  }
}

2. LLM extraction for product page:

{
  "name": "extract_data",
  "arguments": {
    "url": "https://shop.example.com/product/123",
    "mode": "llm",
    "data_schema": "product_page",
    "response_format": "json"
  }
}

3. Extract job listings with anti-bot bypass:

{
  "name": "extract_data",
  "arguments": {
    "url": "https://careers.example.com/jobs",
    "mode": "llm",
    "data_schema": "job_search_page",
    "bypass_level": "generic_level_2",
    "render_js": true
  }
}

4. Extract real estate data in markdown:

{
  "name": "extract_data",
  "arguments": {
    "url": "https://realestate.example.com/listing/456",
    "mode": "llm",
    "data_schema": "real_estate_page",
    "response_format": "markdown"
  }
}

Returns: Structured JSON or Markdown data extracted from the page.

Extract and categorize all URLs from a webpage.

Best for:

• Discovering all links on a page

• Building sitemaps

• Finding all assets (images, scripts, stylesheets)

• Web crawling and link analysis

• Identifying internal vs external links

What it extracts:

• Links from , tags

• Images from ,

• Scripts from

• Stylesheets from

• Media from , ,

• Embedded content from , ,

• URLs from CSS url() functions

• Meta refresh redirects

• Open Graph and meta image URLs

URL Processing:

• Converts relative URLs to absolute

• Removes duplicates

• Filters out mailto:, tel:, javascript:, data: URLs

• Categorizes into pages vs assets

Returns: JSON with two arrays:

• pages: HTML documents and navigational URLs

• assets: Static resources (js, css, images, fonts, media)

Usage Examples:

1. Basic URL extraction:

{
  "name": "return_links",
  "arguments": {
    "url": "https://example.com"
  }
}

2. Extract URLs from protected site:

{
  "name": "return_links",
  "arguments": {
    "url": "https://protected-site.com",
    "bypass_level": "generic_level_1"
  }
}

3. Geo-targeted extraction:

{
  "name": "return_links",
  "arguments": {
    "url": "https://example.de",
    "country": "de"
  }
}