HomeToolsFinancial StatementsFinancial Statement Extractor

// FINANCIAL STATEMENTS

Financial Statement Extractor

Pull the three core financial statements — Balance Sheet, P&L, and Cash Flow — into a clean, comparable workbook.

financial-statement-extractor.run
> extract --statements ar_FY24.pdf
Detected statements: [x] Standalone Balance Sheet p.118 [x] Consolidated Balance Sheet p.220 [x] Standalone P&L p.119 [x] Consolidated P&L p.221 [x] Standalone Cash Flow p.121 [x] Consolidated Cash Flow p.223 Output: financials.xlsx Periods: FY24, FY23 (comparative)

// EXAMPLE INPUT

command
$ extract --statements ar_FY24.pdf

// EXAMPLE OUTPUT

output
Detected statements:
  [x] Standalone Balance Sheet     p.118
  [x] Consolidated Balance Sheet   p.220
  [x] Standalone P&L               p.119
  [x] Consolidated P&L             p.221
  [x] Standalone Cash Flow         p.121
  [x] Consolidated Cash Flow       p.223

Output: financials.xlsx
Periods: FY24, FY23 (comparative)

// EXTRACTION LOGIC

Statements are identified by header signatures and Schedule III / IFRS line-item ontology. Comparative periods are aligned column-wise; restated balances are flagged.

// SOURCE-LINKED OUTPUT

Each line item links to the PDF page and the exact row in the audited financial statements section, including any footnote reference next to the number.

anchor (per value)
{ file, page, table_id, row_id, cell_id, label, value, unit, period }

// FAQ

Does it separate standalone and consolidated statements?

Yes — each statement type produces its own sheet, tagged 'Standalone' or 'Consolidated'.

Are restated prior-period numbers detected?

Restated comparatives are flagged in a 'restated' column and the footnote explaining the restatement is linked.

Which accounting standards are supported?

Indian Schedule III (Ind AS), IFRS, and US GAAP formats are recognized.

// EARLY ACCESS

Get early access to the Financial Statement Extractor

Paper Data is currently in private beta. Request access to start converting your financial documents into source-linked tables.