ref: 8a3009decf76e430c0115d1513aa4826711ac21b
research/scraper.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 |
#!/bin/python """ js interface: http://www.ztm.poznan.pl/themes/ztm/dist/js/app.js nodes: http://www.ztm.poznan.pl/goeuropa-api/all-nodes stops in node: http://www.ztm.poznan.pl/goeuropa-api/node_stops/{node:symbol} stops: http://www.ztm.poznan.pl/goeuropa-api/stops-nodes bike stations: http://www.ztm.poznan.pl/goeuropa-api/bike-stations """ import json import os import re import sqlite3 import sys import requests from bs4 import BeautifulSoup class TimetableDownloader: """ downloader class """ def __init__(self, verbose): self.session = requests.session() self.verbose = verbose def __get_validity(self): """ get timetable validity """ index = self.__get('https://www.ztm.poznan.pl/goeuropa-api/index') option = re.search('<option value="[0-9]{8}" selected', index.text).group() return option.split('"')[1] def __get_nodes(self): """ get nodes """ index = self.__get('https://www.ztm.poznan.pl/goeuropa-api/all-nodes') return [(stop['symbol'], stop['name']) for stop in json.loads(index.text)] def __get_stops(self, node): """ get stops """ index = self.__get('https://www.ztm.poznan.pl/goeuropa-api/node_stops/{}'.format(node)) stops = [] for stop in json.loads(index.text): stop_id = stop['stop']['id'] number = re.findall("\\d+", stop['stop']['symbol'])[0] lat = stop['stop']['lat'] lon = stop['stop']['lon'] directions = ', '.join(['{} → {}'.format(transfer['name'], transfer['headsign']) for transfer in stop['transfers']]) stops.append((stop_id, node, number, lat, lon, directions)) return stops def __get_lines(self): """ get lines """ index = self.__get('https://www.ztm.poznan.pl/goeuropa-api/index') soup = BeautifulSoup(index.text, 'html.parser') lines = {line['data-lineid']: line.text for line in soup.findAll(attrs={'class': re.compile(r'.*\blineNo-bt\b.*')})} return lines def __get_route(self, line_id): """ get routes """ index = self.__get('https://www.ztm.poznan.pl/goeuropa-api/line-info/{}'.format(line_id)) soup = BeautifulSoup(index.text, 'html.parser') directions = soup.findAll(attrs={'class': re.compile(r'.*\baccordion-item\b.*')}) routes = {} for direction in directions: direction_id = direction['data-directionid'] route = [{'id': stop.find('a')['data-stopid'], 'name': stop['data-name'], 'onDemand': re.search('stop-onDemand', str(stop['class'])) != None} for stop in direction.findAll(attrs={'class': re.compile(r'.*\bstop-itm\b.*')})] routes[direction_id] = route return routes def __get_stop_times(self, stop_id, line_id, direction_id): """ get timetable """ index = self.__post('https://www.ztm.poznan.pl/goeuropa-api/stop-info/{}/{}'. format(stop_id, line_id), {'directionId': direction_id}) soup = BeautifulSoup(index.text, 'html.parser') legends = {} for row in soup.find(attrs={'class': re.compile(r'.*\blegend-box\b.*')}).findAll('li'): row = row.text.split('-') row[0] = row[0].rstrip() row[1] = row[1].lstrip() if row[0] != '_': legends[row[0]] = '-'.join(row[1:]) schedules = {} for mode in soup.findAll(attrs={'class': re.compile(r'.*\bmode-tab\b.*')}): mode_name = mode['data-mode'] schedule = {row.find('th').text: [ {'time': minute.text, 'lowFloor': re.search('n-line', str(minute['class'])) != None} for minute in row.findAll('a')] for row in mode.find(attrs={'class': re.compile(r'.*\bscheduler-hours\b.*')}). findAll('tr')} schedule_2 = {hour: times for hour, times in schedule.items() if times != []} schedule = [] for hour, deps in schedule_2.items(): for dep in deps: schedule.append((hour, *self.__describe(dep['time'], legends), dep['lowFloor'])) schedules[mode_name] = schedule return schedules @staticmethod def __describe(dep_time, legend): """ describe departure """ desc = [] while re.match('^\\d+$', dep_time) is None: try: if dep_time[-1] != ',': desc.append(legend[dep_time[-1]]) except KeyError: pass dep_time = dep_time[:-1] return (int(dep_time), '; '.join(desc)) def __get(self, url): try: return self.session.get(url, verify='bundle.pem') except: self.session = requests.session() return self.session.get(url, verify='bundle.pem') def __post(self, url, data): try: return self.session.post(url, data=data, verify='bundle.pem') except: self.session = requests.session() return self.session.post(url, data=data, verify='bundle.pem') def download(self): """ main function """ if os.path.exists('timetable.db'): connection = sqlite3.connect('timetable.db') cursor = connection.cursor() cursor.execute("select value from metadata where key = 'validFrom'") current_valid_from = cursor.fetchone()[0] cursor.close() connection.close() if self.__get_validity() <= current_valid_from: return 304 else: os.remove('timetable.db') with sqlite3.connect('timetable.db') as connection: try: cursor = connection.cursor() cursor.execute('create table metadata(key TEXT PRIMARY KEY, value TEXT)') cursor.execute('create table nodes(symbol TEXT PRIMARY KEY, name TEXT)') cursor.execute('create table stops(id TEXT PRIMARY KEY, symbol TEXT \ references node(symbol), number TEXT, lat REAL, lon REAL, \ headsigns TEXT)') cursor.execute('create table lines(id TEXT PRIMARY KEY, number TEXT)') cursor.execute('create table timetables(id TEXT PRIMARY KEY, stop_id TEXT references \ stop(id), line_id TEXT references line(id), headsign TEXT)') cursor.execute('create table departures(id INTEGER PRIMARY KEY, \ timetable_id TEXT references timetable(id), \ hour INTEGER, minute INTEGER, mode TEXT, \ lowFloor INTEGER, modification TEXT)') validity = self.__get_validity() print(validity) sys.stdout.flush() cursor.execute("insert into metadata values('validFrom', ?)", (validity,)) nodes = self.__get_nodes() cursor.executemany('insert into nodes values(?, ?)', nodes) node_i = 1 for symbol, _ in nodes: if self.verbose: print('node {}'.format(node_i)) stops = self.__get_stops(symbol) cursor.executemany('insert into stops values(?, ?, ?, ?, ?, ?)', stops) node_i += 1 lines = self.__get_lines() cursor.executemany('insert into lines values(?, ?)', lines.items()) timetable_id = 1 line_i = 1 for line_id, _ in lines.items(): route = self.__get_route(line_id) route_i = 1 for direction, stops in route.items(): stop_i = 1 for stop in stops: if self.verbose: print("stop {} in route {} in line {}".format(stop_i, route_i, line_i)) timetables = self.__get_stop_times(stop['id'], line_id, direction) cursor.execute('insert into timetables values(?, ?, ?, ?)', (timetable_id, stop['id'], line_id, stops[-1]['name'])) for mode, times in timetables.items(): cursor.executemany('insert into departures values(null, ?, ?, ?, ?, ?, \ ?)', [(timetable_id, hour, minute, mode, lowfloor, desc) for hour, minute, desc, lowfloor in times]) stop_i += 1 timetable_id += 1 route_i += 1 line_i += 1 except KeyboardInterrupt: return 404 return 0 if __name__ == '__main__': verbose = False try: if sys.argv[1] == '-v': verbose = True except IndexError: pass downloader = TimetableDownloader(verbose) exit(downloader.download()) |