ttml-extract.py

from __future__ import print_function
import xml.etree.ElementTree as ET
import string
import codecs

ns = { 'ttml' : 'http://www.w3.org/ns/ttml' }

f = codecs.open('abstract.tsv', 'w', "utf-8")
f.write("episode\tscript\n");

for episode in range(8):
    tree = ET.parse('abstract-s1e' + str(episode + 1) + '.ttml')
    root = tree.getroot()
    script = ""

    for elem in root.findall('./ttml:body/ttml:div/ttml:p/ttml:span',ns):
        script += string.strip(elem.text) + " "

    f.write(str(episode + 1) + "\t" + string.strip(script) + "\n")

f.close()