ref: 6a472fe3427cdf16857f62a4929861095be410a4
converter/converter.py
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 |
#!/bin/python3 # -*- coding: UTF-8 -*- import yaml import csv import sqlite3 import requests from bs4 import BeautifulSoup import re import os from datetime import date import zipfile import io from pathlib import Path import hashlib import gzip import shutil class TimetableDownloader: def __init__(self): self.__converter = TimetableConverter() def __call__(self): self.__download() self.__tidy_up() with open('metadata.yml', 'w') as metadata_file: yaml.dump(self.__metadata, metadata_file) def __download(self): self.__session = requests.session() html = self.__session.get( 'https://www.ztm.poznan.pl/pl/dla-deweloperow/gtfsFiles', verify='bundle.pem') soup = BeautifulSoup(html.text, 'html.parser') names_table = [x.string.replace('.zip', '') for x in soup.find_all('table')[-1] .tbody .find_all('td', string=re.compile('[0-9]{8}_[0-9]{8}'))] if not os.path.isfile('metadata.yml'): self.__metadata = [] else: with open('metadata.yml', 'r+') as metadata_file: self.__metadata = yaml.load(metadata_file.read()) to_download = [x for x in names_table if self.__is_valid(x) or self.__will_valid(x)] to_download = self.__clean_overlapping(to_download) to_download = self.__select_not_had(to_download) for file in to_download: print('getting {}.zip'.format(file)) self.__get_timetable(file) checksum = self.__converter() for p in Path('.').glob('*.txt'): p.unlink() size_u = os.path.getsize('timetable.db') self.__compress(checksum) self.__archive(file, checksum, size_u, os.path .getsize('{}.db.gz'.format(checksum))) def __is_valid(self, name): today = date.today().strftime('%Y%m%d') start, end = name.split('_') return start <= today and today <= end def __will_valid(self, name): today = date.today().strftime('%Y%m%d') start, end = name.split('_') return today < start def __clean_overlapping(self, names): names.sort() if len(names) == 1: return names return_names = [] i = 1 for name in names[1:]: this_start, this_end = name.split('_') prev_start, prev_end = names[i-1].split('_') if this_start <= prev_start or this_end > prev_end: return_names.append(names[i-1]) i = i + 1 return_names.append(names[-1]) return return_names def __select_not_had(self, names): had = ['_'.join((x['start'], x['end'])) for x in self.__metadata] return_names = [] for name in names: if name not in had: return_names.append(name) return return_names def __get_timetable(self, name): response = self.__session.get('https://www.ztm.poznan.pl/pl/\ dla-deweloperow/getGTFSFile?file={}.zip' .format(name), verify='bundle.pem') zip_bytes = io.BytesIO(response.content) with zipfile.ZipFile(zip_bytes, 'r') as zip_file: zip_file.extractall() def __compress(self, checksum): with open('timetable.db', 'rb') as f_in: with gzip.open('{}.db.gz'.format(checksum), 'wb') as f_out: shutil.copyfileobj(f_in, f_out) Path('timetable.db').unlink() def __archive(self, name, checksum, size_u, size_c): metadata = {'size_uncompressed': size_u, 'size_compressed': size_c, 'id': checksum} start_date, end_date = name.split('_') metadata['start'] = start_date metadata['end'] = end_date self.__metadata.append(metadata) def __tidy_up(self): names = ['_'.join((row['start'], row['end'])) for row in self.__metadata] to_stay = [name for name in names if self.__is_valid(name) or self.__will_valid(name)] to_stay = self.__clean_overlapping(to_stay) to_remove = [name for name in names if name not in to_stay] to_remove = [row['id'] for row in self.__metadata if '_'.join((row['start'], row['end'])) in to_remove] for name in to_remove: Path('{}.db.gz'.format(name)).unlink class TimetableConverter: __BUF_SIZE = 65536 def __call__(self): return self.__convert() def __convert(self): connection = sqlite3.connect('timetable.db') self.__cursor = connection.cursor() self.__create_tables() self.__insert_agency() self.__insert_stops() self.__insert_routes() self.__insert_trips() self.__insert_stop_times() self.__insert_calendar() self.__insert_calendar_dates() self.__insert_shapes() self.__insert_feed_info() self.__create_indexes() connection.commit() checksum = self.__hash_file('timetable.db') print(checksum) return checksum @classmethod def __hash_file(cls, file): checksum = hashlib.sha256() with open(file, 'rb') as f: while True: data = f.read(cls.__BUF_SIZE) if not data: break checksum.update(data) return checksum.hexdigest() def __insert_agency(self): with open('agency.txt', 'r') as csvfile: is_header_parsed = False reader = csv.reader(csvfile, delimiter=',', quotechar='"') for row in reader: if not is_header_parsed: is_header_parsed = True continue self.__cursor.execute('''insert into agency values(?, ?, ?, ?, ?, ?)''', row) def __insert_stops(self): with open('stops.txt', 'r') as csvfile: is_header_parsed = False reader = csv.reader(csvfile, delimiter=',', quotechar='"') for row in reader: if not is_header_parsed: is_header_parsed = True continue self.__cursor.execute('''insert into stops values(?, ?, ?, ?, ?, ?)''', row) def __insert_routes(self): with open('routes.txt', 'r') as csvfile: is_header_parsed = False reader = csv.reader(csvfile, delimiter=',', quotechar='"') for row in reader: if not is_header_parsed: is_header_parsed = True continue self.__cursor.execute('''insert into routes values(?, ?, ?, ?, ?, ?, ?, ?)''', row) def __insert_trips(self): with open('trips.txt', 'r') as csvfile: is_header_parsed = False reader = csv.reader(csvfile, delimiter=',', quotechar='"') for row in reader: if not is_header_parsed: is_header_parsed = True continue self.__cursor.execute('''insert into trips values(?, ?, ?, ?, ?, ?, ?)''', row) def __insert_stop_times(self): with open('stop_times.txt', 'r') as csvfile: is_header_parsed = False reader = csv.reader(csvfile, delimiter=',', quotechar='"') for row in reader: if not is_header_parsed: is_header_parsed = True continue self.__cursor.execute('''insert into stop_times values(?, ?, ?, ?, ?, ?, ?, ?)''', row) def __insert_calendar(self): with open('calendar.txt', 'r') as csvfile: is_header_parsed = False reader = csv.reader(csvfile, delimiter=',', quotechar='"') for row in reader: if not is_header_parsed: is_header_parsed = True continue self.__cursor.execute('''insert into calendar values(?, ?, ?, ?, ?, ?, ?, ?, ?, ?)''', row) def __insert_calendar_dates(self): with open('calendar_dates.txt', 'r') as csvfile: is_header_parsed = False reader = csv.reader(csvfile, delimiter=',', quotechar='"') for row in reader: if not is_header_parsed: is_header_parsed = True continue self.__cursor.execute('''insert into calendar_dates values(?, ?, ?)''', row) def __insert_shapes(self): with open('shapes.txt', 'r') as csvfile: is_header_parsed = False reader = csv.reader(csvfile, delimiter=',', quotechar='"') for row in reader: if not is_header_parsed: is_header_parsed = True continue self.__cursor.execute('''insert into shapes values(?, ?, ?, ?)''', row) def __insert_feed_info(self): with open('feed_info.txt', 'r') as csvfile: is_header_parsed = False reader = csv.reader(csvfile, delimiter=',', quotechar='"') for row in reader: if not is_header_parsed: is_header_parsed = True continue self.__cursor.execute('''insert into feed_info values(?, ?, ?, ?, ?)''', row) def __create_tables(self): self.__cursor.execute('''create table agency(agency_id TEXT PRIMARY KEY, agency_name TEXT, agency_url TEXT, agency_timezone TEXT, agency_phone TEXT, agency_lang TEXT)''') self.__cursor.execute('''create table stops(stop_id TEXT PRIMARY KEY, stop_code TEXT, stop_name TEXT, stop_lat DOUBLE, stop_lon DOUBLE, zone_id TEXT)''') self.__cursor.execute('''create table routes(route_id TEXT PRIMARY KEY, agency_id TEXT, route_short_name TEXT, route_long_name TEXT, route_desc TEXT, route_type INTEGER, route_color TEXT, route_text_color TEXT, FOREIGN KEY(agency_id) REFERENCES agency(agency_id))''') self.__cursor.execute('''create table trips(route_id TEXT, service_id TEXT, trip_id TEXT PRIMARY KEY, trip_headsign TEXT, direction_id INTEGER, shape_id TEXT, wheelchair_accessible BOOL, FOREIGN KEY(route_id) REFERENCES routes(route_id), FOREIGN KEY(service_id) REFERENCES calendar(service_id), FOREIGN KEY(shape_id) REFERENCES shapes(shape_id))''') self.__cursor.execute('''create table stop_times(trip_id TEXT, arrival_time TEXT, departure_time TEXT, stop_id TEXT, stop_sequence INTEGER, stop_headsign TEXT, pickup_type INTEGER, drop_off_type INTEGER, FOREIGN KEY(trip_id) REFERENCES trips(trip_id), FOREIGN KEY(stop_id) REFERENCES stops(stop_id))''') self.__cursor.execute('''create table calendar(service_id TEXT PRIMARY KEY, monday TEXT, tuesday TEXT, wednesday TEXT, thursday TEXT, friday TEXT, saturday TEXT, sunday TEXT, start_date TEXT, end_date TEXT)''') self.__cursor.execute('''create table calendar_dates(service_id TEXT, date TEXT, exception_type INTEGER, FOREIGN KEY(service_id) REFERENCES calendar(service_id))''') self.__cursor.execute('''create table shapes(shape_id TEXT, shape_pt_lat DOUBLE, shape_pt_lon DOUBLE, shape_pt_sequence INTEGER)''') self.__cursor.execute('''create table feed_info(feed_publisher_name TEXT, feed_publisher_url TEXT, feed_lang TEXT, feed_start_date TEXT, feed_end_date TEXT)''') def __create_indexes(self): self.__cursor.execute('''create index ix_stop_times__stop on stop_times(stop_id)''') self.__cursor.execute('''create index ix_stop_times__trip on stop_times(trip_id)''') self.__cursor.execute('''create index ix_shapes__shape on shapes(shape_id)''') if __name__ == '__main__': downloader = TimetableDownloader() downloader() |