Split a PDF into sections by its contents

The scenario finds the PDF's table of contents, splits the document into sections by heading and level, and returns them separately or assembled as HTML, Markdown, or text.

  • Chapter-by-chapter split, hands-free
  • Heading and level per section
  • Fallback heading detection in text
  • Output as HTML, Markdown, or text
Chunkr
Set it up for yourselfScriptera

How it works

To connect pruffme and , you don't need a developer: a ready-made scenario links them in minutes.

  1. Starts when: When clicking ‘Execute workflow’
  2. Then: Download PDF from Google Drive
  3. Check: Merge
  4. Then: Convert the PDF to base64
  5. Then: Set File Name
  6. Then: POST Chunkr Task
  7. Then: Wait Before Polling the Chunkr Result
  8. Then: GET Chunkr Task
  9. Check: Status is:
  10. If yes: Take beginning of Document to look for Table of contents
  11. Then: Extract Sections headers as fallback
  12. Then: Table of Content Agent
  13. Then: Return each section individually
  14. Then: Return the whole document
  15. Then: Create HTML document
  16. Then: HTML
  17. Then: Move Binary Data
  18. Then: Create Markdown Document
  19. Then: Convert to File
  20. If no: Stop and Error
  21. Then: Google Gemini Chat Model
  22. Then: Structured Output Parser
  23. Then: Auto-fixing Output Parser
  24. Starts when: When Executed by Another Workflow
  25. Then: Download PDF from URL
  26. Then: Google Gemini Chat Model1

You can launch this integration in Scriptera: describe the task in plain words — the scenario is built, launched and monitored for you.

Similar scenarios