Supply URLs; review enrichment
Connect
SPIRITT
DiffbotStructure the web
Put its data to work
SPIRITT uses Diffbot to extract articles, products, jobs, and more into structured records. Build useful applications around that data, enrich entities, and keep collection workflows running.
What you can do with Diffbot.
Usable web data
Turn product pages, job listings, and articles into structured collections with source links, rather than another folder of unread pages.
Richer company context
Enrich organizations with Knowledge Graph data, combine entity profiles, and separate confident matches from records needing review.
Collection that keeps running
Operate crawl and bulk extraction jobs, retrieve results, and maintain the datasets behind your team's research tools and dashboards.
Works with your other apps.
Get started in three steps.
01
Open your workspace
Start a SPIRITT workspace for web research, data collection, or company intelligence you want operated for you.
02
Connect Diffbot
Connect Diffbot with your API key so SPIRITT can use the extraction, Knowledge Graph, and job capabilities available to your account.
03
Delegate an outcome
Provide seed URLs, entity identifiers, or a research question. SPIRITT builds the collection workflow and turns its results into a working system.
Hand over a mission.
Choose a mission. Make it yours.
Put Diffbot to work.
Give web data a working purpose
Questions
Diffbot, with SPIRITT.
01What kinds of pages can SPIRITT extract with Diffbot?+
Diffbot supports structured extraction for articles, products, job postings, lists, discussions, events, images, and videos. SPIRITT can also use Analyze to identify page types and select a suitable extraction workflow, then normalize the returned fields into a useful dataset.
02What access do I need to connect Diffbot?+
You connect using a Diffbot API key. The workflow uses the capabilities available to that account, and SPIRITT can retrieve account details including plan information, usage history, and credit balance to help manage collection scope.
03Can SPIRITT operate large or recurring collection jobs?+
Yes. SPIRITT can start bulk extraction and crawl jobs, retrieve their results, and manage supported pause or restart operations. It can schedule collection cycles, retain snapshots in a connected data store, and route failed or incomplete records into an exception queue.
04Where can the extracted data go?+
SPIRITT can carry Diffbot results into connected systems such as Google Sheets for analysis, Supabase for application data, or HubSpot for verified company enrichment. Source URLs, collection dates, and matching decisions can travel with the records so downstream users can check their origins.
05Can SPIRITT build something beyond a spreadsheet?+
Yes. Product comparison apps, event directories, hiring dashboards, and searchable research libraries can use Diffbot data as their foundation. SPIRITT builds the interface and surrounding workflow, while Diffbot supplies structured page content or enriched entity records.
06How is Knowledge Graph enrichment different from page extraction?+
Extraction structures content from supplied web pages. Knowledge Graph search finds entities using query criteria, while Enhance enriches people or organizations from identifiers. SPIRITT can combine these approaches, reconcile profiles, and resolve lost entity IDs without treating every page mention as a verified identity match.