parser.add_argument('--timetables', dest='timetables', action='store_true', help='also save timetables')
parser.add_argument('--scheduled-stats', dest='scheduled_stats', action='store_true', help='also compute scheduled stats if the timetable has new dates (requires --timetables)')
parser.set_defaults(s3=False)
parser.set_defaults(timetables=False)
parser.set_defaults(scheduled_stats=False)
args = parser.parse_args()
agencies = [config.get_agency(args.agency)] if args.agency is not None else config.agencies
save_to_s3 = args.s3
d = date.today()
errors = []
for agency in agencies:
scraper = gtfs.GtfsScraper(agency)
scraper.save_routes(save_to_s3, d)
if args.timetables:
timetables_updated = scraper.save_timetables(save_to_s3=save_to_s3, skip_existing=True)
if timetables_updated and args.scheduled_stats:
dates = sorted(scraper.get_services_by_date().keys())
compute_stats_for_dates(dates, agency, scheduled=True, save_to_s3=save_to_s3)
errors += scraper.errors
if errors:
raise Exception("\n".join(errors))
parser.add_argument("--inpath",
required=True,
help="Path to directory containing GTFS data")
parser.add_argument("--s3",
dest="s3",
action="store_true",
help="Option to upload files to the s3 bucket")
parser.add_argument("--agency", help="Agency name - default is 'sf-muni'")
parser.add_argument("--version", help="Version number for timetable")
parser.set_defaults(s3=False)
parser.set_defaults(agency="sf-muni")
parser.set_defaults(version="v1")
args = parser.parse_args()
inpath = args.inpath
outpath = util.get_data_dir()
s3 = args.s3
agency = args.agency
version = args.version
gtfs_scraper = gtfs.GtfsScraper(inpath, agency, version)
start_time = datetime.now()
print(f"Begin scraping GTFS data: {start_time}")
gtfs_scraper.save_all_stops(s3)
gtfs_scraper.save_date_ranges(s3, version)
end_time = datetime.now()
print(f"Finished scraping GTFS data: {end_time}")
print(f"Elapsed time: {end_time - start_time}")
with zipfile.ZipFile(zip_path, 'r') as zip_ref:
zip_ref.extractall(gtfs_cache_dir)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Merge route information from Nextbus API and GTFS')
parser.add_argument('--s3', dest='s3', action='store_true', help='store in s3')
parser.set_defaults(s3=False)
args = parser.parse_args()
gtfs_cache_dir = f'{util.get_data_dir()}/gtfs-{agency_id}'
download_gtfs_data(agency_id, gtfs_url, gtfs_cache_dir)
gtfs_scraper = gtfs.GtfsScraper(gtfs_cache_dir, agency_id, 'v1')
routes = nextbus.get_route_list(agency_id)
routes_data = []
for route in routes:
route_id = route.id
try:
gtfs_route_id = gtfs_scraper.get_gtfs_route_id(route_id)
except gtfs.NoRouteError as ex:
print(ex)
gtfs_route_id = None
parser.add_argument('--scheduled',
dest='scheduled',
action='store_true',
help='compute scheduled stats from timetable')
parser.set_defaults(s3=False)
parser.set_defaults(scheduled=False)
args = parser.parse_args()
agencies = [config.get_agency(args.agency)
] if args.agency is not None else config.agencies
if args.date:
dates = util.get_dates_in_range(args.date, args.date)
elif args.start_date is not None and args.end_date is not None:
dates = util.get_dates_in_range(args.start_date, args.end_date)
elif args.scheduled and len(agencies) == 1:
# save all dates in current GTFS feed if no date range is provided
scraper = gtfs.GtfsScraper(agencies[0])
dates = sorted(scraper.get_services_by_date().keys())
else:
raise Exception('missing date, start-date, or end-date')
scheduled = args.scheduled
for agency in agencies:
compute_stats_for_dates(dates,
agency,
scheduled=scheduled,
save_to_s3=args.s3)