Observed arrival · 2026-10-07
DocumentChimp: OCR by drawing boxes
A browser-based tool for extracting text from PDFs and images by marking fields, saving reusable templates, and applying them to batches of documents.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- People processing repeated forms, invoices, or other PDFs
- Worth noticing
- Templates store region names, page numbers, and coordinates; filename identifiers can help match documents to the right template.
Field notes
The described workflow saves region names, page numbers, and coordinates in reusable templates, with JSON export and import for moving them. An optional identifier can match a template to a filename, falling back to the selected template when there is no match. The site says files and extracted text remain in browser memory and are cleared when the page is refreshed or closed.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue