gistfile1.txt

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

# http://assicanti.pt/category/uptec/

import PyPDF2
import re
from itertools import takewhile


def ementa(data):
    if len(data) == 0:
        return "a"
    head, tail = data[0], data[1:]

    if head in ['SEGUNDA', 'TERÇA']:
        print head

    ementa(tail)

pdfFileObj = open('ement.pdf', 'rb')
pdfReader = PyPDF2.PdfFileReader(pdfFileObj)

pageObj = pdfReader.getPage(0)
text = re.sub(' +', ' ', pageObj.extractText())
text = re.sub('\s{2,}', ' ', text)
text = re.sub('[\r\n\t]', '', text)


# separa todos os elementos da string
data = re.split('\s(?=[A-Z]{2,})', text.strip())
ementa(data)