def parse_stations(self, html):
bs = BeautifulSoup(html)
tables = bs.findAll('table', {'class':'show_fw'})
st = {}
for i in range(2):
trs = tables[i].findAll('tr')
direction = clean_text(trs[0].text.replace('Fahrtrichtung', ''))
sta = []
for tr in trs[2:-1]:
if tr.a:
sta.append((clean_text(tr.a.text), defaults.base_url + tr.a['href']))
else:
sta.append((clean_text(tr.text), None))
st[direction] = sta
return st
def parse_lines(self, html):
""" Parse lines from html
"""
bs = BeautifulSoup(html)
# get tables
lines = bs.findAll('td', {'class':'auswahl'})
l = {}
for line in lines:
if line.a:
hr = line.a['href'].split('?', 1)[-1]
href = defaults.station_base + hr
if line.text:
l[line.text] = href
elif line.img:
l[line.img['alt']] = href
return l
class sParser:
""" Parser for search response
"""
def __init__(self, html):
self.soup = BeautifulSoup(html)
def check_page(self):
if self.soup.find('form', {'id': 'form_efaresults'}):
return PageType.RESULT
if self.soup.find('div', {'class':'form_error'}):
return PageType.CORRECTION
return PageType.UNKNOWN
state = property(check_page)
def get_correction(self):
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 any([names_origin, names_destination, places_origin, 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:
raise ParserError('Unable to parse html')
def get_result(self):
return rParser(str(self.soup))
def parse_departures(self, html):
bs = BeautifulSoup(html)
dep = []
# Check for error messages
msg = bs.findAll('span', {'class': 'rot fett'})
if msg and len(msg) > 0 and unicode(msg[0].text).find(u'technischen St') > 0:
print '\n'.join(map(lambda x: x.text.replace(' ', ''), msg))
return []
errtable = bs.find('table', {'class':'errortable'})
if errtable and clean_text(errtable.text):
print "Errortable found"
print errtable.text
return []
if bs.table and bs.table.tr:
st_td = bs.table.tr.findAll('td')
if st_td:
station = clean_text(st_td[-1].text)
else:
print "Unexpected Error: Stationname not found"
print "Debug:", st_td.encode('UTF-8')
else:
print "Unexpected Error: table or tr not found"
print bs
return []
# zusatztext crap
zt = bs.find('td', {'class':'zusatztext'})
if zt:
ma = ZUSATZTEXT_REGEX.search(zt.text)
if ma:
line = ma.group(1)
direction = ma.group(2)
if direction == direction.upper():
direction = direction.capitalize()
tim = int(ma.group(3))
d = Departure(line=line, direction=direction,
lowfloor=True, station=station, time=tim)
dep.append(d)
else:
print zt.text
table = bs.find('table', {'class':'imagetable'})
if not table:
print "table not found"
return []
if errtable:
print "Warning: Empty errortable found"
return dep
trs = table.findAll('tr')
for tr in trs[1:]:
tds = tr.findAll('td')
line = clean_text(tds[0].text)
direction = clean_text(tds[1].text)
if direction.startswith(line):
direction = direction.lstrip(line).strip()
if direction == direction.upper():
direction = direction.capitalize()
lf_img = tds[-1].img
lowfloor = lf_img and lf_img.has_key('alt')
d = {'line': line,
'direction': direction,
'lowfloor': lowfloor,
'station': station}
# parse time
tim = clean_text(tds[2].text)
dts = DELTATIME_REGEX.search(tim)
abs = ABSTIME_REGEX.search(tim)
if tim.find(u'...in K\xfcrze') >= 0:
d['time'] = 0
elif abs:
d['time'] = calc_datetime(abs.group(1))
elif tim.isdigit():
d['time'] = int(tim)
elif dts:
# is timedelta
d['time'] = int(dts.group(1))
else:
print "Error parsing time:", tim
continue
dep.append(Departure(**d))
return dep
def __init__(self, html):
self.soup = BeautifulSoup(html)
self._overview = None
self._details = None
class rParser:
""" Parser for routing results
"""
def __init__(self, html):
self.soup = BeautifulSoup(html)
self._overview = None
self._details = None
@classmethod
def get_tdtext(cls, x, cl):
return x.find('td', {'class': cl}).text
@classmethod
def get_change(cls, x):
y = rParser.get_tdtext(x, 'col_change')
if y:
return int(y)
else:
return 0
@classmethod
def get_price(cls, x):
y = rParser.get_tdtext(x, 'col_price')
if y == '*':
return 0.0
if y.find(','):
return float(y.replace(',', '.'))
else:
return 0.0
@classmethod
def get_date(cls, x):
y = rParser.get_tdtext(x, 'col_date')
if y:
return datetime.strptime(y, '%d.%m.%Y').date()
else:
return None
@classmethod
def get_datetime(cls, x):
y = rParser.get_tdtext(x, 'col_time')
if y:
if (y.find("-") > 0):
# overview mode
times = map(lambda z: time(*map(int, z.split(':'))), y.split('-'))
d = rParser.get_date(x)
from_dtime = datetime.combine(d, times[0])
if times[0] > times[1]:
# dateline crossing
to_dtime = datetime.combine(d + timedelta(1), times[1])
else:
to_dtime = datetime.combine(d, times[1])
return [from_dtime, to_dtime]
else:
dtregex = {'date' : '\d\d\.\d\d',
'time': '\d\d:\d\d'}
regex = "\s*(?P<date1>{date})?\s*(?P<time1>{time})\s*(?P<date2>{date})?\s*(?P<time2>{time})\s*".format(**dtregex)
ma = re.match(regex, y)
if not ma:
return []
gr = ma.groupdict()
def extract_datetime(gr, n):
if 'date%d' % n in gr and gr['date%d' % n]:
if gr['time%d' % n] == '24:00':
gr['time%d' % n] = '0:00'
from_dtime = datetime.strptime(str(datetime.today().year) + gr['date%d' % n] + gr['time%d' % n], '%Y%d.%m.%H:%M')
else:
d = datetime.today().date()
# Strange times possible at wienerlinien
if gr['time%d' % n] == '24:00':
gr['time%d' % n] = '0:00'
d += timedelta(days=1)
t = datetime.strptime(gr['time%d' % n], '%H:%M').time()
return datetime.combine(d, t)
# detail mode
from_dtime = extract_datetime(gr, 1)
to_dtime = extract_datetime(gr, 2)
return [from_dtime, to_dtime]
else:
return []
def __iter__(self):
for detail in self.details():
yield detail
def _parse_details(self):
tours = self.soup.findAll('div', {'class': 'data_table tourdetail'})
trips = map(lambda x: map(lambda y: {
'timespan': rParser.get_datetime(y),
'station': map(lambda z: z[2:].strip(),
filter(lambda x: type(x) == NavigableString, y.find('td', {'class': 'col_station'}).contents)), # filter non NaviStrings
'info': map(lambda x: x.strip(),
filter(lambda z: type(z) == NavigableString, y.find('td', {'class': 'col_info'}).contents)),
}, x.find('tbody').findAll('tr')),
tours) # all routes
return trips
@property
def details(self):
"""returns list of trip details
[ [ { 'time': [datetime.time, datetime.time] if time else [],
'station': [u'start', u'end'] if station else [],
'info': [u'start station' if station else u'details for walking', u'end station' if station else u'walking duration']
}, ... # next trip step
], ... # next trip possibility
]
"""
if not self._details:
self._details = self._parse_details()
return self._details
def _parse_overview(self):
# get overview table
table = self.soup.find('table', {'id': 'tbl_fahrten'})
# check if there is an overview table
if table and table.findAll('tr'):
# get rows
rows = table.findAll('tr')[1:] # cut off headline
overview = map(lambda x: {
'timespan': rParser.get_datetime(x),
'change': rParser.get_change(x),
'price': rParser.get_price(x),
},
rows)
else:
raise ParserError('Unable to parse overview')
return overview
@property
def overview(self):
"""dict containing
date: datetime
time: [time, time]
duration: time
change: int
price: float
"""
if not self._overview:
try:
self._overview = self._parse_overview()
except AttributeError:
f = open(DEBUGLOG, 'w')
f.write(str(self.soup))
f.close()
return self._overview
def __init__(self, html):
self.soup = BeautifulSoup(html)
