Kai mrnewguy

bufke / document_to_text.py

Last active September 30, 2024 20:46

Convert odt, doc, docx, pdf to text with python and some linux programs. Doesn't require Libreoffice.

	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
	from pdfminer.converter import TextConverter
	from pdfminer.layout import LAParams
	from pdfminer.pdfpage import PDFPage
	from cStringIO import StringIO