SEC Filings Extractor

Extract SEC filings (10-K, 10-Q, 8-K) as structured Markdown with automatic section splitting by Item headers. Handles large financial documents with extended timeout and high token budget.

Features

• Large document support — 120-second timeout and 500,000 token budget for massive filings
• Automatic section splitting — splits by SEC Item headers (Item 1A. Risk Factors, Item 7. MD&A, etc.)
• High-quality extraction — uses ReaderlM v2 for complex document structure
• Full content + sections — get both the complete markdown and individual sections as a map
• Batch processing — extract multiple filings in a single run

How It Works

1. Provide SEC filing URLs (from EDGAR or direct links) as input.
2. The Actor fetches each filing with extended timeout for large documents.
3. Content is split by SEC Item headers into a structured sections map.
4. Both full markdown and section map are stored in the dataset.

Input

{
    "startUrls": [
        { "url": "https://www.sec.gov/Archives/edgar/data/320193/000032019323000106/aapl-20230930.htm" }
    ]
}

Output

{
    "url": "https://www.sec.gov/Archives/edgar/data/320193/000032019323000106/aapl-20230930.htm",
    "sectionCount": 15,
    "sections": {
        "Item 1. Business": "Apple Inc. designs, manufactures...",
        "Item 1A. Risk Factors": "The Company's business...",
        "Item 7. Management's Discussion and Analysis": "..."
    },
    "markdown": "# Full filing content..."
}

Use Cases

• Financial analysis and due diligence automation
• Build datasets of company risk factors
• Extract MD&A sections for sentiment analysis
• Feed filings into AI for financial research
• Regulatory compliance monitoring

Keywords

SEC scraper, 10-K extractor, EDGAR scraper, financial filings, SEC EDGAR API, 10-Q parser, annual report extractor

Pricing

$150 per 1,000 filing extractions.