quick and dirty test of PDF to text script

extract.py

from itertools import groupby
from operator import itemgetter

with open("tester2.txt") as f:
    content = f.readlines()

spoken = []
i = 1
for line in content:
	leading_space = len(line) - len(line.lstrip())
	print(leading_space)
	if leading_space < 9 or leading_space > 40:
		pass
	else:
		if leading_space > 19:
			i += 1
		spoken.append([line, i])


groups = groupby(spoken, itemgetter(1))
character_line = [[item[0] for item in data] for (key, data) in groups]

final = []
for xx in character_line:
	character_name = xx[0].strip(' ').strip('\n')
	lines = map(lambda x: x.strip(' ').strip('\n'), xx[1:])
	concat_line = " ".join(lines)
	out_line = character_name + " => " + concat_line