SEC EDGAR Filings
Structured SEC filings ready for AI and RAG pipelines
What it does
Pull SEC EDGAR filings, including 10-K, 10-Q, 8-K, and more, as clean structured JSON ready for AI and RAG pipelines. Financial facts, filing text, entity data. Empty results are never charged.
Built in
- ✓ 10-K, 10-Q, 8-K and 20+ form types
- ✓ Structured financial facts extracted
- ✓ Full filing text for RAG ingestion
- ✓ CIK and ticker lookup supported
- ✓ Empty results are never charged
Guides & tutorials
SEC EDGAR Filings Use Cases: Financial Research, RAG Pipelines, and Compliance Monitoring
SEC EDGAR holds 30 years of public company filings. Here is who pulls them programmatically, what they build with the data, and why structured JSON beats raw XBRL.
Building a RAG Pipeline on SEC EDGAR Filings: A Step-by-Step Guide
How to scrape SEC EDGAR filings, chunk them for vector search, and build a provenance-aware Q&A system that cites specific filing sections using Claude.
Ask an AI for a Company's SEC CIK and It Will Lie to You. Here Is the Fix.
An AI that remembers is not an AI that verifies. This is the exact diligence flow: legal identity from GLEIF, filings from EDGAR, funding, engineering activity and hiring, run from Claude via MCP, grounded in real registries, for about sixteen cents a company.
Related scrapers
EU VAT Validator
Bulk EU VAT number verification via official VIES
World Bank Trade Scraper
Imports and exports by country and product, from World Bank WITS
GLEIF LEI Lookup
Legal entity identifiers and company data from GLEIF
World Bank Indicators
GDP, inflation, trade, and 1,400+ development indicators
Common questions
What SEC filing types can I pull? +
10-K (annual reports), 10-Q (quarterly reports), 8-K (current reports), 20-F, DEF 14A, S-1, and 20 more form types. Search by ticker, CIK, or company name.
Is the SEC EDGAR data free? +
Yes, EDGAR is a public database. The official API is free but rate-limited and returns raw XBRL or HTML. This scraper handles rate limiting and returns clean structured JSON.
Can I use this for RAG pipelines over financial documents? +
Yes. Each filing is returned with full document text pre-extracted and ready for chunking. Pair it with RAG Crawler for large multi-document ingestion pipelines.
How far back do the filings go? +
EDGAR has filings going back to 1993. Use date range filters to pull historical filings for any public company.
What data is extracted from each filing? +
Accession number, form type, filing date, company name, CIK, document URLs, and full text of the primary document. Financial fact tables are included where available in XBRL format.
Try it on Apify.
Pay only for results delivered. No credit card required to sign up.