Extract the text of notes from an OpenOffice presentation

readNotes.py

#!/usr/bin/python

from lxml import etree
import zipfile

# some namespaces we may need
DRAW="urn:oasis:names:tc:opendocument:xmlns:drawing:1.0"
DRAWC = "{%s}" % DRAW
PRES='urn:oasis:names:tc:opendocument:xmlns:presentation:1.0'
PRESC = "{%s}" % PRES

NS = {'presentation': PRES,
      "draw":DRAW }

def getTree(path):
    return etree.XML(path.read())

def printNotes(slides):
    for slide in slides:
        title = slide.get(DRAWC+"name")
        print "---- %s ----" % title
        notes = slide.xpath("presentation:notes",namespaces=NS)
        for note in notes:
            bits =  [c.text for c in note.iterdescendants()]
            print "\n".join(filter(lambda x: x, bits))
            print " "


def getSlides(et):
    return et.xpath("//draw:page",namespaces=NS)

if __name__=="__main__":
    from sys import argv
    filepath = argv[1]
    z = zipfile.ZipFile(filepath)
    content = z.open("content.xml")
    et = getTree(content)
    slides = getSlides(et)
    printNotes(slides)