Power your amazing NLP products
with our
PDF Parser

Many search and NLP pipelines rely on accurate pre-processing of visually structured documents.

Our top-of-the line parser extracts visual elements such as lists, tables, sections and retains the logical structure such as paragraph, table boundaries and their hierarchies.

Access the same parser we use to drive our search through a convenient API. Test your PDFs in our WYSWYG UI. Supported output formats are JSON, XML and HTML.

  • Done Outline
    Tables
  • Done Outline
    Lists
  • Done Outline
    Sections
  • Done Outline
    Section Hierarchy & Layout

Featured Documents

Machine readable EDGAR Filings

  • Prospectus: 
    Form 424
  • Company Reports:
    10-K, 10-Q, 40-F, 20-F
  • Offerings:
    S-1, S-2, S-3
  • Analyst reports:
    MS, BoA, GS, JPM and more
  • M&A:
    Form 425
  • Exhibits
    Forms 2, 4, 10

Machine readable Muni Prospectus

  • MSRB Emma Official Statements
  • Addendums