odp2anki.py

import sys
import os
import os.path
import zipfile
from lxml import etree
from lxml import objectify

tempdir = 'temp'
docfile = zipfile.ZipFile(sys.argv[1])
docfile.extractall(tempdir)
with open(os.path.join(tempdir, 'content.xml')) as f:
    xml = f.read()

root = objectify.fromstring(xml)
for el in root.body.presentation.iterchildren(tag="{urn:oasis:names:tc:opendocument:xmlns:drawing:1.0}page"):
    image_filename = el.frame.image.attrib["{http://www.w3.org/1999/xlink}href"]
    print image_filename
    notes = getattr(el, "{urn:oasis:names:tc:opendocument:xmlns:presentation:1.0}notes")
    text_box = getattr(notes, "{urn:oasis:names:tc:opendocument:xmlns:drawing:1.0}frame")["text-box"]
    span = getattr(text_box, "{urn:oasis:names:tc:opendocument:xmlns:text:1.0}p").span
    print span

pptx2anki.py

import sys
import os
import os.path
import zipfile
from lxml import etree

tempdir = 'temp'
docfile = zipfile.ZipFile(sys.argv[1])
docfile.extractall(tempdir)
presentation = etree.parse(os.path.join(tempdir, 'ppt', 'presentation.xml')).getroot()
slide_list = presentation.find("{http://schemas.openxmlformats.org/presentationml/2006/main}sldIdLst")
slides = []
for slide in slide_list:
  new_slide = {'id': slide.attrib['id'], 'rid': slide.get("{http://schemas.openxmlformats.org/officeDocument/2006/relationships}id")}
  slides.append(new_slide)

presentation_rels = etree.parse(os.path.join(tempdir, 'ppt', '_rels', 'presentation.xml.rels')).getroot()
for rel in  presentation_rels.getchildren():
  rel_id = rel.get('Id')
  rel_slide = [[slides.index(slide), slide] for slide in slides if slide['rid'] == rel_id]
  if rel_slide:
    slides[rel_slide[0][0]]['file'] = rel.get('Target')
    
for slide in slides:
  slide_file = slide['file']
  print slide_file
  slide_rel_parse = etree.parse(os.path.join(tempdir, 'ppt', 'slides', '_rels', slide_file.split('/')[1] + '.rels'))
  print etree.tostring(slide_rel_parse)
  rels = slide_rel_parse.findall('*')
  print rels
  for r in rels:
    print etree.tostring(r)
    print r.attrib['Target']
  #slide_parse = etree.parse(os.path.join(tempdir, 'ppt', slide_file))