sec-edgar-parser

To parse SEC EDGAR filings, the skill retrieves documents via the SEC submissions JSON endpoint and extracts HTML tables into Pandas DataFrames using pd.read_html, while converting text content with BeautifulSoup. It handles CIK lookup, URL construction from accession numbers, and document retrieval automatically.

Yes, you can extract specific sections like Item 1A Risk Factors from 10-K filings. The skill parses HTML content using BeautifulSoup to extract readable text and structured table data, standardizing disclosures for downstream analysis by company ticker and form type.

The best way to automate financial data extraction is using the SEC submissions JSON endpoint with CIK padding to discover filings by ticker. The skill constructs Archives document URLs from accession numbers, downloads the HTML, and parses tables into DataFrames for analysis.

Yes, SEC-compliant User-Agent headers are required to download EDGAR filing data programmatically. The skill enforces this requirement when querying the submissions JSON endpoint and retrieving filing documents, ensuring compliant access to SEC EDGAR corporate filings.

This SEC filing parser focuses on HTML table extraction via Pandas and text parsing via BeautifulSoup. While XBRL is listed as a related keyword, the core implementation retrieves filing HTML and converts tables to DataFrames rather than parsing XBRL tags directly.

To find a company's CIK from a ticker symbol, the skill queries the SEC submissions JSON endpoint with CIK padding. It pulls recent submissions metadata for form types like 10-K, 10-Q, and 8-K, enabling filing discovery and document URL construction.