PyPI page
Home page
Author:
Hazy Research
License:
MIT
Summary:
Convert PDF into hOCR with text, tables, and figures being recognized and preserved.
Latest version:
0.5.0
Required dependencies:
beautifulsoup4
|
ipython
|
keras
|
numpy
|
pandas
|
pdfminer.six
|
pillow
|
selectivesearch
|
sklearn
|
tabula-py
|
tensorflow
|
wand
Downloads last day:
102
Downloads last week:
606
Downloads last month:
2,811