axarev/parsr repository overview

⁠Github repository

https://github.com/axa-group/Parsr.git⁠

⁠Turn your documents into data!

Parsr, is a minimal-footprint document (image, pdf) cleaning, parsing and extraction toolchain which generates readily available, organized and usable data for data scientists and developers.

It provides users with clean structured and label-enriched information set for ready-to-use applications ranging from data entry and document analysis automation, archival, and many others.

Currently, Parsr can perform:

• Document Hierarchy Regeneration - Words, Lines and Paragraphs
• Headings Detection
• Table Detection and Reconstruction
• Lists Detection
• Text Order Detection
• Named Entity Recognition (Dates, Percentages, etc)
• Key-Value Pair Detection (for the extraction of specific form-based entries)
• Page Number Detection
• Header-Footer Detection
• Link Detection
• Whitespace Removal

Parsr takes as input an image (.JPG, .PNG, .TIFF, ...) or a PDF generates the following output formats:

• JSON
• Markdown
• Text
• CSV (for tables), or Pandas Dataframes (see here⁠)
• PDF

⁠Getting Started

1. Run the API

docker run -p 3001:3001 axarev/parsr:latest

1. To use the GUI tool (the API needs to already be running), issue:

docker run -t -p 8080:80 axarev/parsr-ui-localhost:latest

⁠Tagging convention

latestand develop tags are related to the develop version of par.sr and can be considered as unstable.
master or v*are related to production versions.

⁠License

Copyright 2019 AXA Group Operations S.A.
Licensed under the Apache 2.0⁠ license (see the LICENSE⁠ file).