web_get_page
Fetch web page content quickly with configurable output formats and proxy options for reliable data extraction.
Instructions
Quick page fetch with sane defaults. Use tool scraping_instruction_enhanced before using this tool. Use when you just need the content fast.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The target URL to scrape. | |
| country | No | The country to use for the proxy. Supports ISO 3166-1 alpha-2 country codes. | |
| format | No | The desired output format for the content. Supports clean_html, markdown, text, and json | markdown |
| format_options | No | Additional options (only available for markdown and text formats) | |
| proxy_pool | No | The proxy pool to use. Supports public_datacenter_pool and public_residential_pool, defaults: public_datacenter_pool | public_datacenter_pool |
| rendering_wait | No | Wait for this number of milliseconds before returning the response. | |
| capture_page | No | If true, also capture the page as a screenshot. | |
| capture_flags | No | Screenshot flags to use for the screenshot. | |
| extraction_model | No | The extraction model to use for the offloaded extraction. Exclusive with extraction_template and extraction_prompt. | |
| pow | Yes | use scraping_instruction_enhanced tool use for instructions |