PyPI page
Home page
Author:
None
License:
Apache-2.0
Summary:
Universal document parser: PDF / Office / email / images / HTML — tiered routing for cost & accuracy
Latest version:
0.2.0
Required dependencies:
extractous
|
filetype
|
numpy
|
pillow
|
pypdfium2
Optional dependencies:
duckdb
|
extract-msg
|
openpyxl
|
pyarrow
|
pytest
|
python-docx
|
python-pptx
|
sqlparse
Downloads last day:
12
Downloads last week:
147
Downloads last month:
361