parser.py

import json
import re
from collections import defaultdict

FIRST_NUMBER = re.compile('\s\d')

def main(file, type_name):
    connections = defaultdict(list)
    with open(file) as f:
        for line in f.readlines():

            if len(line) == 0:
                continue

            delimiter = FIRST_NUMBER.search(line)
            if not delimiter:
                continue
            delimiter = delimiter.start()

            station_name = line[:delimiter]
            times = line[delimiter+1:].strip().split(' ')
            connections[station_name].extend(times)
    print json.dumps({
        'type': type_name,
        'data': connections
    })



if __name__ == '__main__':
    import argparse
    parser = argparse.ArgumentParser(description='Generate JSON from pdfs')
    parser.add_argument('--type', type=str, required=True, help='Type of timetable')
    parser.add_argument('--file', type=str, required=True, help='Path of timetable file')
    args = parser.parse_args()
    main(args.file, args.type)