bob oiuww09fn
oiuww09fn
/ document_to_text.py
Last active
August 29, 2015 14:03
— forked from bufke/document_to_text.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # pdf pdftotext | |
| # doc antiword | |
| # docx docx | |
| # excel xlrd | |
| from subprocess import Popen, PIPE | |
| from docx import opendocx, getdocumenttext | |
| #http://stackoverflow.com/questions/5725278/python-help-using-pdfminer-as-a-library | |
| from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter |