Script para extrair o body do content.xml

gistfile1.py

import re
from elementtree import ElementTree as etree

def get_text_element(tree):
    for i in tree.getiterator():
        if 'text' in i.tag and 'text-' not in i.tag:
            return i

def return_the_text(element):
    string = etree.tostring(element)
    text = re.search('</ns0:annotation>.*</ns1:p>', string).group(0)
    text = re.sub('</ns0:annotation>', '', text)
    text = re.sub('</ns1:p>', '', text)
    return text

tree = etree.parse('content.xml')
print return_the_text(get_text_element(tree))