vcs.maemo.org Git - pywienerlinien/blob - iTip.py

   1 from BeautifulSoup import BeautifulSoup
   2 from urllib2 import urlopen
   3 import settings
   4 from datetime import time
   5 import argparse
   6 import re
   7
   8 class iParser:
   9
  10     def __init__(self):
  11         self._stations = {}
  12         self._lines = {}
  13
  14     def get_stations(self, name):
  15         """ Get station by direction
  16         {'Directionname': [('Station name', 'url')]}
  17         """
  18         if not self._stations.has_key(name):
  19             st = {}
  20
  21             if not self.lines.has_key(name):
  22                 return None
  23
  24             bs = BeautifulSoup(urlopen(self.lines[name]))
  25             tables = bs.findAll('table', {'class': 'text_10pix'})
  26             for i in range(2):
  27                 dir = tables[i].div.contents[-1].strip('&nbsp;')
  28
  29                 sta = []
  30                 for tr in tables[i].findAll('tr', {'onmouseout': 'obj_unhighlight(this);'}):
  31                     if tr.a:
  32                         sta.append((tr.a.text, settings.line_overview + tr.a['href']))
  33                     else:
  34                         sta.append((tr.text.strip('&nbsp;'), None))
  35
  36                 st[dir] = sta
  37             self._stations[name] = st
  38
  39         return self._stations[name]
  40
  41     @property
  42     def lines(self):
  43         """ Dictionary of Line names with url as value
  44         """
  45         if not self._lines:
  46             bs = BeautifulSoup(urlopen(settings.line_overview))
  47             # get tables
  48             lines = bs.findAll('td', {'class': 'linie'})
  49
  50             for line in lines:
  51                 if line.a:
  52                     href = settings.line_overview + line.a['href']
  53                     if line.text:
  54                         self._lines[line.text] = href
  55                     elif line.img:
  56                         self._lines[line.img['alt']] = href
  57
  58         return self._lines
  59
  60     def get_departures(self, url):
  61         """ Get list of next departures
  62         integer if time until next departure
  63         time if time of next departure
  64         """
  65
  66         #TODO parse line name and direction for station site parsing
  67
  68         bs = BeautifulSoup(urlopen(url))
  69         result_lines = bs.findAll('table')[-1].findAll('tr')
  70
  71         dep = []
  72         for tr in result_lines[1:]:
  73             th = tr.findAll('th')
  74             if len(th) < 2:
  75                 #TODO replace with logger
  76                 print "[DEBUG] Unable to find th in:\n%s" % str(tr)
  77                 continue
  78
  79             # parse time
  80             time = th[-2].text.split(' ')
  81             if len(time) < 2:
  82                 print 'Invalid time: %s' % time
  83                 continue
  84
  85             time = time[1]
  86
  87             if time.find('rze...') >= 0:
  88                     dep.append(0)
  89             elif time.isdigit():
  90                 # if time to next departure in cell convert to int
  91                 dep.append(int(time))
  92             else:
  93                 # check if time of next departue in cell
  94                 t = time.strip('&nbsp;').split(':')
  95                 if len(t) == 2 and all(map(lambda x: x.isdigit(), t)):
  96                     t = map(int, t)
  97                     dep.append(time(*t))
  98                 else:
  99                     # Unexpected content
 100                     #TODO replace with logger
 101                     print "[DEBUG] Invalid data:\n%s" % time
 102
 103         return dep
 104
 105 if __name__ == '__main__':
 106     parser = argparse.ArgumentParser(description='Get realtime public transport information for Vienna')
 107     parser.add_argument('-l', metavar='name', type=str, help='line name')
 108     parser.add_argument('-s', metavar='name', type=str, help='station name')
 109
 110     args = parser.parse_args()
 111
 112     itip = iParser()
 113     lines = itip.lines
 114     if args.l:
 115         l = args.l.upper()
 116     else:
 117         l = None
 118     if args.s:
 119         s = args.s.decode('UTF-8')
 120     else:
 121         s = ''
 122
 123     if l and l in lines:
 124         stations = itip.get_stations(l)
 125         for key in stations.keys():
 126             if not s:
 127                 print '* %s:' % key
 128             for station in stations[key]:
 129                 if s:
 130                     if s.startswith(station[0]) or station[0].startswith(s):
 131                         # FIXME
 132                         print '* %s\n  %s .....' % (key, station[0]), itip.get_departures(station[1])
 133                 else:
 134                     print '    %s' % station[0]
 135
 136     elif not l:
 137         line = {'U-Bahn': '|', 'Strassenbahn': '|', 'Bus': '|', 'Andere': '|', 'Nightline': '|'}
 138         lines_sorted = lines.keys()
 139         lines_sorted.sort()
 140         for li in lines_sorted:
 141             if li.isdigit():
 142                 type = 'Strassenbahn'
 143             elif li.endswith('A') or li.endswith('B') and li[1].isdigit():
 144                 type = 'Bus'
 145             elif li.startswith('U'):
 146                 type = 'U-Bahn'
 147             elif li.startswith('N'):
 148                 type = 'Nightline'
 149             else:
 150                 type = 'Andere'
 151
 152             line[type] += ' %s |' % li
 153         for kv in line.items():
 154             print "%s:\n%s" % kv