fix unicode issues
This commit is contained in:
parent
e789bb52e7
commit
c9debbc619
3 changed files with 55 additions and 15 deletions
|
|
@ -20,6 +20,7 @@ Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
||||||
|
|
||||||
from datetime import datetime, date, time
|
from datetime import datetime, date, time
|
||||||
from weboob.tools.browser import Browser
|
from weboob.tools.browser import Browser
|
||||||
|
from weboob.tools.misc import toUnicode
|
||||||
|
|
||||||
class CanalTP(Browser):
|
class CanalTP(Browser):
|
||||||
DOMAIN = 'widget.canaltp.fr'
|
DOMAIN = 'widget.canaltp.fr'
|
||||||
|
|
@ -37,11 +38,11 @@ class CanalTP(Browser):
|
||||||
except ValueError:
|
except ValueError:
|
||||||
continue
|
continue
|
||||||
else:
|
else:
|
||||||
yield _id, name
|
yield _id, toUnicode(name)
|
||||||
|
|
||||||
def iter_station_departures(self, station_id):
|
def iter_station_departures(self, station_id):
|
||||||
result = self.openurl(u"http://widget.canaltp.fr/Prochains_departs_15122009/dev/index.php?gare=%s" % unicode(station_id)).read()
|
result = self.openurl(u"http://widget.canaltp.fr/Prochains_departs_15122009/dev/index.php?gare=%s" % unicode(station_id)).read()
|
||||||
result = unicode(result, "utf8")
|
result = result
|
||||||
departure = ''
|
departure = ''
|
||||||
for line in result.split('&'):
|
for line in result.split('&'):
|
||||||
key, value = line.split('=', 1)
|
key, value = line.split('=', 1)
|
||||||
|
|
@ -49,12 +50,12 @@ class CanalTP(Browser):
|
||||||
departure = value
|
departure = value
|
||||||
elif key.startswith('ligne'):
|
elif key.startswith('ligne'):
|
||||||
_type, unknown, _time, arrival, served, late, late_reason = value.split(';', 6)
|
_type, unknown, _time, arrival, served, late, late_reason = value.split(';', 6)
|
||||||
yield {'type': _type,
|
yield {'type': toUnicode(_type),
|
||||||
'time': datetime.combine(date.today(), time(*[int(x) for x in _time.split(':')])),
|
'time': datetime.combine(date.today(), time(*[int(x) for x in _time.split(':')])),
|
||||||
'departure': departure,
|
'departure': toUnicode(departure),
|
||||||
'arrival': arrival,
|
'arrival': toUnicode(arrival).strip(),
|
||||||
'late': late and time(0, int(late.split()[0])) or time(),
|
'late': late and time(0, int(late.split()[0])) or time(),
|
||||||
'late_reason': late_reason}
|
'late_reason': toUnicode(late_reason).replace('\n', '').strip()}
|
||||||
|
|
||||||
def home(self):
|
def home(self):
|
||||||
pass
|
pass
|
||||||
|
|
|
||||||
|
|
@ -78,21 +78,21 @@ class Application(BaseApplication):
|
||||||
print ' departures <station> List all departures on a special station'
|
print ' departures <station> List all departures on a special station'
|
||||||
|
|
||||||
def command_stations(self, pattern):
|
def command_stations(self, pattern):
|
||||||
print ".-----------------.----------------------------------------."
|
print ".--------------------------------.---------------------------------------------."
|
||||||
print '| ID | Name |'
|
print '| ID | Name |'
|
||||||
print '+-----------------+----------------------------------------+'
|
print '+--------------------------------+---------------------------------------------+'
|
||||||
count = 0
|
count = 0
|
||||||
for name, backend, in self.weboob.iter_backends():
|
for name, backend, in self.weboob.iter_backends():
|
||||||
for station in backend.iter_station_search(pattern):
|
for station in backend.iter_station_search(pattern):
|
||||||
print '| %-15s | %-38s |' % (station.id, station.name)
|
print '| %-30s | %-43s |' % (station.id, station.name)
|
||||||
count += 1
|
count += 1
|
||||||
print "+-----------------'----------------------------------------+"
|
print "+--------------------------------'---------------------------------------------+"
|
||||||
print "| %3d stations listed |" % count
|
print "| %3d stations listed |" % count
|
||||||
print "'----------------------------------------------------------'"
|
print "'------------------------------------------------------------------------------'"
|
||||||
|
|
||||||
def command_departures(self, station):
|
def command_departures(self, station):
|
||||||
print ".-----.-----------.-------.-----------------------.-------.--------------------."
|
print ".-----.-----------.-------.-----------------------.-------.--------------------."
|
||||||
print "| ID | Type | Time | Arrival | Late | Info |"
|
print "| ID | Type | Time | Arrival | Late | Info |"
|
||||||
print "+-----+-----------+-------+-----------------------+-------+--------------------+"
|
print "+-----+-----------+-------+-----------------------+-------+--------------------+"
|
||||||
count = 0
|
count = 0
|
||||||
for name, backend, in self.weboob.iter_backends():
|
for name, backend, in self.weboob.iter_backends():
|
||||||
|
|
@ -102,7 +102,7 @@ class Application(BaseApplication):
|
||||||
departure.time.strftime("%H:%M"),
|
departure.time.strftime("%H:%M"),
|
||||||
departure.arrival_station,
|
departure.arrival_station,
|
||||||
departure.late and departure.late.strftime("%H:%M") or '',
|
departure.late and departure.late.strftime("%H:%M") or '',
|
||||||
departure.information.replace('\n', '').strip())
|
departure.information)
|
||||||
count += 1
|
count += 1
|
||||||
print "+-----'-----------'-------'-----------------------'-------'--------------------+"
|
print "+-----'-----------'-------'-----------------------'-------'--------------------+"
|
||||||
print "| %3d departures listed |" % count
|
print "| %3d departures listed |" % count
|
||||||
|
|
|
||||||
39
weboob/tools/misc.py
Normal file
39
weboob/tools/misc.py
Normal file
|
|
@ -0,0 +1,39 @@
|
||||||
|
# -*- coding: utf-8 -*-
|
||||||
|
|
||||||
|
"""
|
||||||
|
Copyright(C) 2010 Romain Bignon
|
||||||
|
|
||||||
|
This program is free software; you can redistribute it and/or modify
|
||||||
|
it under the terms of the GNU General Public License as published by
|
||||||
|
the Free Software Foundation, version 3 of the License.
|
||||||
|
|
||||||
|
This program is distributed in the hope that it will be useful,
|
||||||
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||||
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||||
|
GNU General Public License for more details.
|
||||||
|
|
||||||
|
You should have received a copy of the GNU General Public License
|
||||||
|
along with this program; if not, write to the Free Software
|
||||||
|
Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
||||||
|
|
||||||
|
"""
|
||||||
|
|
||||||
|
def toUnicode(text):
|
||||||
|
r"""
|
||||||
|
>>> toUnicode('ascii')
|
||||||
|
u'ascii'
|
||||||
|
>>> toUnicode(u'utf\xe9'.encode('UTF-8'))
|
||||||
|
u'utf\xe9'
|
||||||
|
>>> toUnicode(u'unicode')
|
||||||
|
u'unicode'
|
||||||
|
"""
|
||||||
|
if isinstance(text, unicode):
|
||||||
|
return text
|
||||||
|
if not isinstance(text, str):
|
||||||
|
text = str(text)
|
||||||
|
try:
|
||||||
|
return unicode(text, "utf8")
|
||||||
|
except UnicodeError:
|
||||||
|
pass
|
||||||
|
return unicode(text, "ISO-8859-1")
|
||||||
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue