Extract structured text or HTML content from SEC filings through the FinFeedAPI SEC Filings API.
Instead of downloading and parsing complete filing documents, applications can retrieve the entire filing content or specific filing items from supported forms. This simplifies access to commonly used sections of SEC filings while reducing the amount of custom document processing required.
SEC filings often contain lengthy documents with multiple sections covering financial results, business operations, risk disclosures, management discussion, exhibits, and other regulatory information.
For supported filing forms (8-K, 10-K, and 10-Q) the Extracted Filing Content endpoints classify filing documents into structured items. Applications can retrieve either the complete filing content or a specific filing item without manually parsing the original document.
Content can be returned as plain text or HTML, making it suitable for analytics platforms, search systems, AI applications, compliance workflows, and financial research.
Many applications need specific information from regulatory filings rather than the original filing document.
Applications can retrieve either the complete extracted filing content or a specific filing item. The complete filing endpoint requires the filing accession number, while item-level extraction additionally requires the filing item number.
Use GET /v1/extractor with the filing accession number when you need the entire classified filing.
Use GET /v1/extractor/item with the accession number and item number when you only need one classified section.
Extracted filing content can be returned in two formats, depending on how the data will be used.
| Format | Typical Use Cases |
|---|---|
| Plain text | AI pipelines, NLP, search indexing, analytics |
| HTML | Document rendering, web applications, preserving formatting |
Applications can choose the format that best fits their processing pipeline without downloading and parsing the original filing document.
To retrieve a specific filing item, specify the filing accession number, item number, and desired output format. The API returns the requested filing item as structured text.
GET /v1/extractor/item?accession_number=0000123456-24-000001&item_number=1A&type=textFor complete filing extraction, use the /v1/extractor endpoint without selecting an individual filing item.
Extracted filing content can serve as the foundation for document analysis, search, and AI workflows. After identifying a supported filing, applications can retrieve its complete extracted content or select a specific filing item for downstream processing without parsing the original SEC document.
Structured filing content can also be combined with other SEC Filings API capabilities, such as downloading original filing documents or converting XBRL filings into structured JSON, depending on the application requirements.
Structured filing content reduces the complexity of working with supported SEC forms by eliminating much of the document parsing typically required when processing EDGAR documents.
Retrieve structured text or HTML content through the FinFeedAPI SEC Filings API.
Extract complete filing content or individual filing items without manually parsing EDGAR documents, and integrate the results into AI applications, search platforms, analytics systems, or regulatory workflows.