from os import name, getcwd
cwd = getcwd()
if name != 'nt': dirType = '/'
else: dirType = '\\'
xml = open('%s%sword%sdocument.xml' % (cwd, dirType, dirType))
text = xml.read()
line = 0
repr(xml)
size = len(xml)
while line != size:
.. text = xml[line]
.. line = (line+1)
.. repr(text[1])

import os, zipfile
print """DiXTiXa.py; GPLv3 Python DOCX to TXT Assembler
Converts MS Office Word 2007 files into text files quickly.
"""
fp = raw_input('Enter in the file location (including C:\ or /home): ')
cwd = os.getcwd()
if os.name != 'nt': dir = '/'
else: dir = '\\'
print "\nDirectory type: %s or %s\n" % (os.name, dir)
try:
	xml = zipfile.ZipFile("%s" % fp,'r')
	docx = xml.read('word%sdocument.xml' % dir)
	xml.close()
except IOError:
	print """Bad file or file location.
	Please do not type any ' or " marks in the filepath!
	You entered: %s
	Please make sure this file exists.
Will now exit.""" % fp
	exit
docx = str(repr(docx))
end = len(docx)
line = 0
out = open('%s%sConverted.txt' % (cwd,dir),'a')
print 'The converted file is %s%sConverted.txt' % (cwd,dir)
def stripCrap(newline):
	new = newline.lstrip()
	return new.rstrip()
def openTag(beg, type):
	loc = docx.find('</w:t>',beg,end)
	if type == 1:
		newline = str(docx[beg+5:loc])
		out.write('%s\n' % stripCrap(newline))
		print newline
	elif type == 2:
		newline = str(docx[beg+26:loc])
		out.write('%s\n' % stripCrap(newline))
		print newline
	print "   Starting location: ",beg, "   Ending location: ", loc,"   Type: ", type, "  "	
while line < end:
	if docx[line:line+5] == '<w:t>': openTag(line,1)
	else: pass
	if docx[line:line+26] == '<w:t xml:space="preserve">': openTag(line,2)
	else: pass
	line = (line+1)
out.close()
print "\nAll Done."