HTML

python split html header

from itertools import count

chapter_number = count(1)
output_file = open('000-intro.html', 'wb')

with open('index.html', 'rt') as input_file:
    for line in input_file:
        if '<h1' in line:
            output_file.close()
            output_file = open('{:03}-chapter'.format(next(chapter_number)), 'wb')
        output_file.write(line)

output_file.close()