web-data

The context API to search, scrape, and interact with the web at scale. 🔥

Search the web from your coding agent with concise mini-briefings, ratings, and source links—no tab switching required

Crawlora Agent Skills — structured public web data (search, e-commerce, social, finance, app stores, media, reviews) via the Crawlora REST API. Installable in any agent with the skills CLI or as a Claude Code plugin marketplace.

Python scraper based on AI

Extract text from images using a robust OCR model designed for accuracy and efficiency in varied visual contexts.

Bright Data — independent third-party profile of a public API surface, by API Evangelist. Bright Data is a web data platform providing a global proxy network (residential, datacenter, ISP, mobile), pre-built Web Scraper APIs for 100+ sites, a SERP API, the Web Unlocker, ready-made Datasets, and a Scraping Browser (Browser API) that exposes a real C

Bright Data — independent third-party profile of a public API surface, by API Evangelist. Bright Data is an Israeli web data platform and operator of the world's largest legitimate residential proxy network (400M+ IPs across 195 countries). The platform combines proxy infrastructure (residential, ISP, datacenter, mobile) with higher-level web-acces

A web-based email scraper for 2026, enabling fast and easy email data collection directly from your browser.

Scrape local events and activities directly in your browser with this simple HTML scraper. Find nearby happenings fast.

Get web data for AI agents and LLMs - fast, efficient, and reliable with Rust

Thinknum — independent third-party profile of a public API surface, by API Evangelist. Thinknum is an alternative data platform that collects and structures web-sourced datasets to power investment and business intelligence. It tracks metrics such as job listings, store locations, product pricing, web traffic, app reviews, and social engagement acr

Oxylabs — independent third-party profile of a public API surface, by API Evangelist. Oxylabs is a Lithuanian (Vilnius-based) web intelligence platform providing premium proxy networks (Residential, Datacenter, Mobile, ISP, Dedicated), web data acquisition APIs (Web Scraper API, SERP Scraper API, E-Commerce Scraper API, Real Estate Scraper API, Web

Nimbleway — independent third-party profile of a public API surface, by API Evangelist. Nimble (Nimbleway) is a real-time web data intelligence platform that turns any public web page into structured, analysis-ready data at scale. Its AI-Native SDK exposes Search, Extract, Map, Crawl, SERP, Media Download, and Web Search Agents over a single REST A

CrawlGraph — independent third-party profile of a public API surface, by API Evangelist. A backlink-intelligence SaaS built on Common Crawl's open hyperlink graph (~120M domains / 4.4B links). Provides referring-domain lookups, competitor gap analysis, and outreach-target discovery as a low-cost alternative to Ahrefs/Moz/Semrush.

Crawlbase — independent third-party profile of a public API surface, by API Evangelist. Crawlbase (formerly ProxyCrawl) is a web crawling and scraping platform that fetches any web page through a large rotating proxy network with optional headless-Chrome JavaScript rendering, returning raw HTML, Markdown, screenshots, or structured JSON.

Coresignal — independent third-party profile of a public API surface, by API Evangelist. Coresignal is a data-as-a-service company providing access to public web data on companies, employees, and jobs through a suite of REST APIs. The platform aggregates and refines more than 4.5 billion data records covering 75M+ companies (with 500+ data fields),

Context.dev — independent third-party profile of a public API surface, by API Evangelist. Context.dev is the unified web-context API for software and AI agents — one API that turns any domain or URL into structured, typed JSON. It covers brand intelligence (logos, colors, fonts, socials, address, industry codes, stock ticker / ISIN and transaction-

2Captcha MCP server for AI agents with web search, web scraping, browser automation, captcha solving, and scalable web data collection.

39 Agent Skills for the Scavio web data API: Google, Amazon, TikTok, LinkedIn, YouTube and 28 more platforms as structured JSON