UNKNOWN, CORRECTION, RESULT = range(3)
+def extract_city(station):
+ """ Extract city from string if present,
+ else return default city
+
+ >>> extract_city('Karlsplatz, Wien')
+ 'Wien'
+ """
+ if len(station.split(',')) > 1:
+ return station.split(',')[-1].strip()
+ else:
+ return 'Wien'
+
+def extract_station(station):
+ """ Remove city from string
+
+ >>> extract_station('Karlsplatz, Wien')
+ 'Karlsplatz'
+ """
+ if len(station.split(',')) > 1:
+ return station[:station.rindex(',')].strip()
+ else:
+ return station
+
+def split_station(station):
+ """ >>> split_station('Karlsplatz, Wien')
+ ('Karlsplatz', 'Wien')
+ >>> split_station('Karlsplatz')
+ ('Karlsplatz', 'Wien')
+ """
+ print "split:", station
+ if len(station.split(',')) > 1:
+ return (station[:station.rindex(',')].strip(), station.split(',')[-1].strip())
+ else:
+ return (station, 'Wien')
+
def search(origin_tuple, destination_tuple, dtime=None):
""" build route request
returns html result (as urllib response)
dtime = datetime.now()
origin, origin_type = origin_tuple
+ origin, origin_city = split_station(origin)
+
destination, destination_type = destination_tuple
+ destination, destination_city = split_station(destination)
+
+
if not origin_type in POSITION_TYPES or\
not destination_type in POSITION_TYPES:
raise ParserError('Invalid position type')
post['type_destination'] = destination_type
post['itdDateDayMonthYear'] = dtime.strftime('%d.%m.%Y')
post['itdTime'] = dtime.strftime('%H:%M')
+ post['place_origin'] = origin_city
+ post['place_destination'] = destination_city
params = urlencode(post)
url = '%s?%s' % (settings.action, params)
return PageType.UNKNOWN
def get_correction(self):
- nlo = self.soup.find('select', {'id': 'nameList_origin'})
- nld = self.soup.find('select', {'id': 'nameList_destination'})
-
- if not nlo and not nld:
- raise ParserError('Unable to parse html')
-
- if nlo:
- origin = map(lambda x: x.text, nlo.findAll('option'))
+ names_origin = self.soup.find('select', {'id': 'nameList_origin'})
+ names_destination = self.soup.find('select', {'id': 'nameList_destination'})
+ places_origin = self.soup.find('select', {'id': 'placeList_origin'})
+ places_destination = self.soup.find('select', {'id': 'placeList_destination'})
+
+
+ if names_origin or names_destination or places_origin or places_destination:
+ dict = {}
+
+ if names_origin:
+ dict['origin'] = map(lambda x: x.text, names_origin.findAll('option'))
+ if names_destination:
+ dict['destination'] = map(lambda x: x.text, names_destination.findAll('option'))
+
+ if places_origin:
+ dict['place_origin'] = map(lambda x: x.text, names_origin.findAll('option'))
+ if names_destination:
+ dict['place_destination'] = map(lambda x: x.text, names_destination.findAll('option'))
+
+ return dict
+
else:
- origin = []
- if nld:
- destination = map(lambda x: x.text, nld.findAll('option'))
- else:
- destination = []
-
- return (origin, destination)
+ raise ParserError('Unable to parse html')
def get_result(self):
return rParser(str(self.soup))
parser.add_argument('destination')
args = parser.parse_args()
-html = search((args.origin, args.ot), (args.destination, args.dt)).read()
-parser = sParser(html)
-state = parser.check_page()
-
-if state == PageType.CORRECTION:
- try:
- cor = parser.get_correction()
- if cor[0]:
- print
- print '* Origin ambiguous:'
- lo = None
- while not lo or not lo.isdigit() or int(lo) > len(cor[0]):
- i = 1
- for c in cor[0]:
- print '%d. %s' % (i, c)
- i += 1
- lo = sys.stdin.readline().strip()
-
- args.origin = cor[0][int(lo) - 1]
-
- if cor[1]:
- print
- print '* Destination ambiguous:'
- ld = None
- while not ld or not ld.isdigit() or int(ld) > len(cor[1]):
- j = 1
- for c in cor[1]:
- print '%d. %s' % (j, c)
- j += 1
- ld = sys.stdin.readline().strip()
-
- args.destination = cor[1][int(ld) - 1]
-
- html = search((args.origin.encode('UTF-8'), args.ot), (args.destination.encode('UTF-8'), args.dt)).read()
-
- parser = sParser(html)
- state = parser.check_page()
-
- except ParserError:
- print 'PANIC at correction page'
-
-if state == PageType.RESULT:
- parser = rParser(html)
- try:
- overviews = parser.overview
- details = parser.details
- l = ''
- while not l == 'q':
- for idx, overview in enumerate(overviews):
- if not overview['date'] or not overview['time']:
- # XXX: Bogus data for e.g. Pilgramgasse->Karlsplatz?!
- continue
-
- print '%d. [%s] %s-%s (%s)' % (idx + 1,
- overview['date'],
- overview['time'][0],
- overview['time'][1],
- overview['duration'])
- print 'q. Quit'
- l = sys.stdin.readline().strip()
- print
- print '~' * 100
-
- if l.isdigit() and int(l) <= len(details):
- for detail in details[int(l) - 1]:
- if detail['time'] and detail['station']:
- time = '%s - %s' % (detail['time'][0].strftime(TIMEFORMAT), detail['time'][1].strftime(TIMEFORMAT))
- print '[%s] %s\n%s' % (time, ' -> '.join(detail['station']), '\n'.join(detail['info']))
- else:
- print '\n'.join(detail['info'])
- print '-' * 100
- print
-
- except ParserError:
- print 'parsererror'
-
-elif state == PageType.UNKNOWN:
- print 'PANIC unknown result'
+finished = False
+while not finished:
+
+ html = search((args.origin, args.ot), (args.destination, args.dt)).read()
+
+ parser = sParser(html)
+ state = parser.check_page()
+
+ if state == PageType.CORRECTION:
+ try:
+ cor = parser.get_correction()
+ print "A", args.origin, args.destination
+ origin, origin_place = split_station(args.origin)
+ destination, destination_place = split_station(args.destination)
+
+ print "B", origin, origin_place, destination, destination_place
+
+ # FIXME refactoring
+
+ if cor.has_key('origin'):
+ print
+ print '* Origin ambiguous:'
+ l = None
+ while not l or not l.isdigit() or int(l) > len(cor['origin']):
+ i = 1
+ for c in cor['origin']:
+ print '%d. %s' % (i, c)
+ i += 1
+ l = sys.stdin.readline().strip()
+
+ origin = cor['origin'][int(l) - 1]
+
+ if cor.has_key('destination'):
+ print
+ print '* Destination ambiguous:'
+ l = None
+ while not l or not l.isdigit() or int(l) > len(cor['destination']):
+ i = 1
+ for c in cor['destination']:
+ print '%d. %s' % (i, c)
+ i += 1
+ l = sys.stdin.readline().strip()
+
+ destination = cor['destination'][int(l) - 1]
+
+ if cor.has_key('origin_place'):
+ print
+ print '* Origin place ambiguous:'
+ l = None
+ while not l or not l.isdigit() or int(l) > len(cor['origin_place']):
+ i = 1
+ for c in cor['origin_place']:
+ print '%d. %s' % (i, c)
+ i += 1
+ l = sys.stdin.readline().strip()
+
+ origin_place = cor['origin_place'][int(l) - 1]
+
+ if cor.has_key('destination_place'):
+ print
+ print '* Destination place ambiguous:'
+ l = None
+ while not l or not l.isdigit() or int(l) > len(cor['destination_place']):
+ i = 1
+ for c in cor['destination_place']:
+ print '%d. %s' % (i, c)
+ i += 1
+ l = sys.stdin.readline().strip()
+
+ destination_place = cor['destination_place'][int(l) - 1]
+
+ print origin, origin_place, destination, destination_place
+ args.origin = '%s, %s' % (origin, origin_place)
+ args.destination = '%s, %s' %(destination, destination_place)
+
+ except ParserError:
+ print 'PANIC at correction page'
+ finished = True
+
+ elif state == PageType.RESULT:
+ parser = rParser(html)
+ try:
+ overviews = parser.overview
+ details = parser.details
+ l = ''
+ while not l == 'q':
+ for idx, overview in enumerate(overviews):
+ if not overview['date'] or not overview['time']:
+ # XXX: Bogus data for e.g. Pilgramgasse->Karlsplatz?!
+ continue
+
+ print '%d. [%s] %s-%s (%s)' % (idx + 1,
+ overview['date'],
+ overview['time'][0],
+ overview['time'][1],
+ overview['duration'])
+ print 'q. Quit'
+ l = sys.stdin.readline().strip()
+ print
+ print '~' * 80
+
+ if l.isdigit() and int(l) <= len(details):
+ for detail in details[int(l) - 1]:
+ if detail['time'] and detail['station']:
+ time = '%s - %s' % (detail['time'][0].strftime(TIMEFORMAT), detail['time'][1].strftime(TIMEFORMAT))
+ print '[%s] %s\n%s' % (time, ' -> '.join(detail['station']), '\n'.join(detail['info']))
+ else:
+ print '\n'.join(detail['info'])
+ print '-' * 80
+ print
+
+ finished = True
+
+ except ParserError:
+ print 'parsererror'
+
+ elif state == PageType.UNKNOWN:
+ print 'PANIC unknown result'