Built by Metorial, the integration platform for agentic AI.
Extract entities, facts, relationships, and sentiment from raw text using Diffbot's NLP engine. Identifies people, organizations, products, and other entities, links them to Knowledge Graph records, and extracts structured facts and relationships between entities.
Extract structured data from a web page using Diffbot's AI-powered extraction engine. Supports automatic page type detection or targeted extraction for articles, products, discussions, images, videos, lists, events, and job postings. Can also process raw HTML/text content directly.
Create, monitor, control, and retrieve results from Diffbot web crawl jobs. Crawls spider websites from seed URLs, discover linked pages, and process them through Diffbot's extraction APIs. Supports creating new crawls, checking status, pausing/resuming, restarting, deleting, and listing all crawl jobs.
Enrich a person or organization record with comprehensive data from the public web. Provide minimal identifiers (name, domain, email, etc.) and receive a complete entity profile with 50+ fields. Optionally combine a person lookup with their current employer data in a single request.
Search Diffbot's Knowledge Graph containing over 10 billion entities (organizations, people, articles, products, etc.) using DQL (Diffbot Query Language). Returns structured records with comprehensive fields and properties.
Create, monitor, and retrieve results from Diffbot bulk extraction jobs. Bulk jobs process a list of known URLs through Diffbot's extraction APIs as a batch. Supports creating jobs, checking status, deleting, listing, and downloading results.