Simplify your workflows with Docy AI Workers— the Compliance-Grade  AI Infrastructure. Explore

  Team@docyai.com

Yearbook Parser

Yearbook Parser is a document processing agent designed specifically for yearbooks and similar name-heavy publications.

Category

Other

Version update

05/01/26

Language

English

About

🗒️ Agent Description

Yearbook Parser is a document processing agent built specifically for yearbooks and similar name-heavy publications.

Key capabilities:

· Supports uploading multiple pages in a single batch
· Automatically separates content into individual pages
· Extracts names on a page-by-page basis
· Structures the extracted names into Excel format
· Excludes group photos and non-text visual elements
· Maintains consistent structure across all pages

By enforcing page-level parsing, the agent delivers clean, well-organised Excel outputs that are easy to review, sort, and reuse.

✅ Input / Output

📌 Input

Multi-page PDF or multiple page images
Each page should represent a single yearbook page

📌 Output

Excel (.xlsx)
One row per extracted name
Page-level structure preserved (e.g. page number, section, or order)

“Turn yearbook pages into structured Excel rows“