A tool to parse eis pattern content from xml documents.

eisparser.py

from os.path import join, basename, dirname
from nltk.util import clean_html
from nltk.corpus.reader import PlaintextCorpusReader
from os import system
import re

class EisParser(object):
	
	def __init__(self, path):
		self._name = basename(path)
		self._path = dirname(path)
		
	def _unzip_odt(self):
		system('unzip %s/%s -d %s content.xml' %(self._path, self._name, self._path))

	def legible_text(self):
		self._unzip_odt()
		self._raw_content_text = PlaintextCorpusReader(self._path, 'content.xml').raw()
		self._cleaned_text = clean_html(self._raw_content_text)
		self.content = re.sub(r'\w+ \d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2} ', '', self._cleaned_text)
		return self.content