Context.dev

Context.dev Web Scraping API

The Web Scraping API from Context.dev — 7 operation(s) for web scraping.

GitHub OpenAPI

Operations 7

Each operation below carries the questions people ask an LLM about it and the instructions they give an agent to run it. Generated by API Evangelist overlay

GET /web/scrape/html Scrape a page's raw HTML · Scrape HTML #
Ask an LLM
“Can I get the raw HTML of a web page, rendered in a browser?”
“Is there a way to keep only certain CSS selectors when scraping HTML?”
Tell an agent
Scrape the raw HTML of {url}.
Get the HTML of {url} keeping only elements matching {includeSelectors}.
GET /web/scrape/markdown Scrape a single page into Markdown · Scrape Markdown #
Ask an LLM
“How do I turn one web page into clean Markdown for an LLM?”
“Can I strip headers, footers and navigation so only the main article comes through as Markdown?”
Tell an agent
Scrape {url} into Markdown.
Convert only the main content of {url} to Markdown {useMainContentOnly}.
GET /web/scrape/images Collect all images on a web page · Scrape Images #
Ask an LLM
“Can I list every image on a page, including SVGs, CSS backgrounds and video posters?”
“Is there an option to remove visually duplicate images from the results?”
Tell an agent
Extract all images from {url}.
Get the images on {url} with duplicates removed {dedupe}.
GET /web/scrape/sitemap List every page URL on a website · Crawl Sitemap #
Ask an LLM
“How can I get a list of all the page URLs on a website from its sitemap?”
“Can I filter sitemap URLs with a regex, like only blog posts?”
Tell an agent
Crawl the sitemap of {domain} and list its URLs.
List up to {maxLinks} URLs on {domain} matching {urlRegex}.
POST /web/crawl Crawl a site and scrape many pages to Markdown · Crawl Website & Scrape Markdown #
Ask an LLM
“Can I crawl a whole docs site from one starting URL and get every page back as Markdown?”
“What's the maximum number of pages a multi-page crawl will scrape?”
Tell an agent
Crawl starting at {url} and return every page as Markdown.
Crawl {url} up to {maxPages} pages and depth {maxDepth}, scraping each to Markdown.
POST /web/search Search the web and optionally scrape results · Web Search #
Ask an LLM
“Can I run a web search and get each result scraped into Markdown in one call?”
“Is it possible to limit web search results to certain domains or recent content?”
Tell an agent
Search the web for {query}.
Search for {query} only on {includeDomains} published within {freshness}.
GET /web/screenshot Capture a screenshot of a website · Scrape Screenshot #
Ask an LLM
“Can I take a full-page screenshot of a website?”
“Does the screenshot tool dismiss cookie banners and support dark mode?”
Tell an agent
Take a screenshot of {domain}.
Capture a full-page screenshot of {directUrl} {fullScreenshot} in the {colorScheme} theme.

Documentation

📖
APIReference
https://docs.context.dev
📖
Documentation
https://docs.context.dev/introduction

Specifications

⚙
OpenAPI
https://raw.githubusercontent.com/api-evangelist/contextdev/refs/heads/main/openapi/contextdev-web-scraping-api-openapi.yml

Other Resources

🔗
Webhooks
https://raw.githubusercontent.com/api-evangelist/contextdev/refs/heads/main/asyncapi/contextdev-webhooks.yml

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API 
curl "https://apis.io/api/v1/apis/contextdev:contextdev-web-scraping-api"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

contextdev-web-scraping-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: Context Web Scraping API
  description: API for retrieving context data from any website
  version: 1.0.0
servers:
- url: https://api.context.dev/v1
tags:


# --- truncated at 32 KB (139 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/contextdev/refs/heads/main/openapi/contextdev-web-scraping-api-openapi.yml