Skip to main content
Glama

Scrapy MCP Server

by ThreeFish-AI

scrape_webpage

Extract and scrape webpage content using auto, simple, Scrapy, or Selenium methods. Define extraction rules or wait for specific elements to retrieve targeted data.

Instructions

Scrape a single webpage and extract its content.

This tool can scrape web pages using different methods:

  • auto: Automatically choose the best method

  • simple: Fast HTTP requests (no JavaScript)

  • scrapy: Robust scraping with Scrapy framework

  • selenium: Full browser rendering (supports JavaScript)

You can specify extraction rules to get specific data from the page.

Input Schema

NameRequiredDescriptionDefault
requestYes

Input Schema (JSON Schema)

{ "$defs": { "ScrapeRequest": { "description": "Request model for scraping operations.", "properties": { "extract_config": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null, "description": "Configuration for data extraction", "title": "Extract Config" }, "method": { "default": "auto", "description": "Scraping method: auto, simple, scrapy, selenium", "title": "Method", "type": "string" }, "url": { "description": "URL to scrape", "title": "Url", "type": "string" }, "wait_for_element": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "CSS selector to wait for (Selenium only)", "title": "Wait For Element" } }, "required": [ "url" ], "title": "ScrapeRequest", "type": "object" } }, "properties": { "request": { "$ref": "#/$defs/ScrapeRequest", "title": "Request" } }, "required": [ "request" ], "type": "object" }

Other Tools from Scrapy MCP Server

Related Tools

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ThreeFish-AI/scrapy-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server