1. Über python

Linguistische Datenverarbeitung mit python

2. Beispiel: Parsing eines XML-Dokuments und Ausgabe aller <p>-Inhalte

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import re
import xml.etree.ElementTree as etree

f = open('greif.csv', 'w')


#PARSING
tree = etree.parse('greif.xml')

root = tree.getroot()


#DEBUG: OUTPUT TAGS
for x in root.iter():
    print x.tag + ' = ' + (x.text if x.text else '')

             
#AUTOR-EXTRAKTION
for x in root.iter('{http://www.tei-c.org/ns/1.0}author'):
    author = x.text.replace('\n','').strip()


#TITEL-EXTRAKTION
for x in root.iter('{http://www.tei-c.org/ns/1.0}head'):
    title = x.text.replace('\n','').strip()


#TEXT-EXTRAKTION
for x in root.iter('{http://www.tei-c.org/ns/1.0}p'):

    if '{http://www.w3.org/XML/1998/namespace}id' in x.attrib:
        text = "".join(x.itertext())

    #TOKENISIERUNG    
        text = re.sub('([\.,:;!\?\-\'\"])',r' \1',text)
        tokens = text.split()

    #AUSGABE    
        for token in tokens:
            output = author+'\t'+title+'\t'+token+'\n'
            output = output.encode('utf-8')
            f.write(output)


f.close()