[Django]-How to import data from scanned text into Django models

This is the working version I came up with. Dirty, but effective. Both @akonsu and @Ivan Kharlamov were helpful. Thanks…

import os, re, Levenshtein as lev, codecs
from SimpleQuiz.quiz.models import Choice, Question
from django.core.management.base import BaseCommand, CommandError
import optparse

class Command(BaseCommand):
    args = '--datapath=/path/to/text/data/'
    can_import_settings = True
    help = 'Imports scanned text into Questions and Choices'
    option_list = BaseCommand.option_list + (
        optparse.make_option('--datapath', action='store', type='string',
                             dest='datapath',
                             help='Path to OCRd text files to be parsed.'),
        )
    requires_model_validation = True
    # Parser REs
    BACKUP_RE = re.compile(r'\~$|bak$|back$|backup$')
    QUEST_RE = re.compile(r'^[0-9]{1,3}[.][ ]')
    CHOICE_RE = re.compile(r'^[a-e][.][ ]')

    def handle(self, *args, **options):
        # get the data path
        try:
            os.path.exists(options['datapath'])
        except Exception as e:
            raise CommandError("None or invalid path provided: %s" % e.message)
        self.datapath = os.path.expanduser(options['datapath'])

        # generate list of text strings from lines in target files
        self.data_lines = []
        for fn in os.listdir(os.path.join(self.datapath, 'questions/')):
            if self.BACKUP_RE.search(fn):
                self.stderr.write("Skipping backup: %s\n" % (fn))
            else:
                for line in codecs.open(os.path.join(self.datapath, 'questions/', fn), 'r', encoding='latin-1'):
                    if not self.is_boilerplate(line):
                        if not line.strip() == '':
                            self.data_lines.append(line)

    #----------------------------------------------------------------------- 
    #--------------------- Parse the text lines and create Questions/Choices
    #----------------------------------------------------------------------- 
        cur_quest = None
        cur_choice = None
        cur_is_quest = False
        questions = {}
        choices = {}
        for line in self.data_lines:
            if self.is_question(line):
                [n, txt] = line.split('.', 1)
                qtext = txt.rstrip() + " "
                q = Question.objects.create(text=qtext)
                q.save()
                cur_quest = q.pk
                questions[cur_quest] = q
                cur_is_quest = True
            elif self.is_choice(line):
                [n, txt] = line.split('.', 1)
                num = self.char2dig(n)
                ctext = txt.rstrip() + " "
                c = Choice.objects.create(text=ctext, order=num, question=questions[cur_quest])
                c.save()
                cur_choice = c.pk
                choices[cur_choice] = c
                cur_is_quest = False
            else:
                if cur_is_quest:
                    questions[cur_quest].text += line.rstrip() + " "
                    questions[cur_quest].save()
                else:
                    choices[cur_choice].text += line.rstrip() + " "
                    choices[cur_choice].save()
        self.stdout.write("----- FINISHED -----\n")
        return None

    def is_question(self, arg_str):
        if self.QUEST_RE.search(arg_str):
            return True
        else:
            return False

    def is_choice(self, arg_str):
        if self.CHOICE_RE.search(arg_str):
            return True
        else:
            return False

    def char2dig(self, x):
        if x == 'a':
            return 1
        if x == 'b':
            return 2
        if x == 'c':
            return 3
        if x == 'd':
            return 4
        if x == 'e':
            return 5

    def is_boilerplate(self, arg_str):
        boilerplate = [u'MFT PRACTICE EXAMINATIONS',
                       u'BERKELEY TRAINING ASSOCIATES ' + u'\u00A9' + u' 2009',
                       u'BERKELEY TRAINING ASSOCIATES',
                       u'MARRIAGE AND FAMILY THERAPY',
                       u'PRACTICE EXAMINATION 41',
                       u'Page 0', u'Page 1', u'Page 2', u'Page 3', u'Page 4',
                       u'Page 5', u'Page 6', u'Page 7', u'Page 8', u'Page 9',
                       ]
        for bp in boilerplate:
            if lev.distance(bp.encode('utf-8'), arg_str.encode('utf-8')) < 4:
                return True
        return False