https://github.com/dentosal/kansataisteli-ocr

A script to download and OCR unpublished texts from http://kansataisteli.sshs.fi/
https://github.com/dentosal/kansataisteli-ocr

Last synced: 2 months ago
JSON representation

A script to download and OCR unpublished texts from http://kansataisteli.sshs.fi/

• Host: GitHub
• URL: https://github.com/dentosal/kansataisteli-ocr
• Owner: Dentosal
• License: mit
• Created: 2017-12-23T18:28:15.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2017-12-24T20:05:49.000Z (over 8 years ago)
• Last Synced: 2025-03-21T09:48:12.383Z (over 1 year ago)
• Language: Python
• Size: 5.86 KB
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Kansa taisteli - Fetch and OCR texts

Fetches and converts text to json format.

## Dependencies

Python3.6, ImageMagick, Tesseract-OCR

Python packages:

```

pip install regex requests pillow cv2 tesserocr

```

Install [Finnish training data for Tesseract](https://github.com/tesseract-ocr/tessdata/blob/master/fin.traineddata).

## Running

```

python app.py

```