def parseSeries(self, data):
serieslist = []
for line in json.loads(data):
id = line['id']
idname = line['value']
splog(id, idname)
if not idname.endswith("/person"):
serieslist.append( ( id, idname ) )
serieslist.reverse()
return serieslist
def parseSeries(self, data):
serieslist = []
for line in json.loads(data):
id = line['id']
idname = line['value']
splog(id, idname)
if not idname.endswith("/person"):
serieslist.append((id, idname))
serieslist.reverse()
return serieslist
def getSeries(self, name):
#url = SERIESLISTURL + urlencode({ 'q' : re.sub("[^a-zA-Z0-9-*]", " ", name) })
url = SERIESLISTURL + urlencode({'q': name})
data = self.getPage(url)
if data and isinstance(data, basestring):
data = self.parseSeries(data)
self.doCacheList(url, data)
if data and isinstance(data, list):
splog("WunschlisteFeed ids", data)
return self.filterKnownIds(data)
def getSeries(self, name):
parameter = urlencode({'term': re.sub("[^a-zA-Z0-9*]", " ", name)})
url = SERIESLISTURL + parameter
data = self.getPage(url, Headers)
if data and isinstance(data, basestring):
data = self.parseSeries(data)
self.doCacheList(url, data)
if data and isinstance(data, list):
splog("Fernsehserien ids", data)
return self.filterKnownIds(data)
def parseSeries(self, data):
serieslist = []
for line in data.splitlines():
values = line.split("|")
if len(values) == 4:
idname, countryyear, id, temp = values
splog(id, idname)
serieslist.append( (id, idname) )
else:
splog("WunschlisteFeed: ParseError: " + str(line))
serieslist.reverse()
return serieslist
def getSeries(self, name):
#url = SERIESLISTURL + urlencode({ 'q' : re.sub("[^a-zA-Z0-9-*]", " ", name) })
url = SERIESLISTURL + urlencode({ 'q' : name })
data = self.getPage( url )
if data and isinstance(data, basestring):
data = self.parseSeries(data)
self.doCacheList(url, data)
if data and isinstance(data, list):
splog("WunschlisteFeed ids", data)
return self.filterKnownIds(data)
def getSeries(self, name):
parameter = urlencode({ 'term' : re.sub("[^a-zA-Z0-9*]", " ", name) })
url = SERIESLISTURL + parameter
data = self.getPage(url)
if data and isinstance(data, basestring):
data = self.parseSeries(data)
self.doCacheList(url, data)
if data and isinstance(data, list):
splog("Fernsehserien ids", data)
return self.filterKnownIds(data)
def parseSeries(self, data):
serieslist = []
for line in data.splitlines():
values = line.split("|")
if len(values) == 4:
idname, countryyear, id, temp = values
splog(id, idname)
serieslist.append((id, idname))
else:
splog("WunschlisteFeed: ParseError: " + str(line))
serieslist.reverse()
return serieslist
def getEpisode(self, name, begin, end=None, service=None):
# On Success: Return a single season, episode, title tuple
# On Failure: Return a empty list or String or None
self.begin = begin
self.end = end
self.service = service
self.knownids = []
self.returnvalue = None
# Check preconditions
if not name:
splog(_("Skip Wunschliste: No show name specified"))
return _("Skip Wunschliste: No show name specified")
if not begin:
splog(_("Skip Wunschliste: No begin timestamp specified"))
return _("Skip Wunschliste: No begin timestamp specified")
splog("WunschlisteFeed getEpisode")
while name:
ids = self.getSeries(name)
while ids:
idserie = ids.pop()
if idserie and len(idserie) == 2:
id, idname = idserie
# Handle encodings
self.series = str_to_utf8(idname)
result = self.getNextPage( id )
if result:
return result
else:
name = self.getAlternativeSeries(name)
else:
return ( self.returnvalue or _("No matching series found") )
def getEpisode(self, name, begin, end=None, service=None):
# On Success: Return a single season, episode, title tuple
# On Failure: Return a empty list or String or None
self.begin = begin
self.end = end
self.service = service
self.knownids = []
self.returnvalue = None
# Check preconditions
if not name:
splog(_("Skip Wunschliste: No show name specified"))
return _("Skip Wunschliste: No show name specified")
if not begin:
splog(_("Skip Wunschliste: No begin timestamp specified"))
return _("Skip Wunschliste: No begin timestamp specified")
splog("WunschlisteFeed getEpisode")
while name:
ids = self.getSeries(name)
while ids:
idserie = ids.pop()
if idserie and len(idserie) == 2:
id, idname = idserie
# Handle encodings
self.series = str_to_utf8(idname)
result = self.getNextPage(id)
if result:
return result
else:
name = self.getAlternativeSeries(name)
else:
return (self.returnvalue or _("No matching series found"))
def str_to_utf8(s):
# Convert a byte string with unicode escaped characters
splog("WL: str_to_utf8: s: ", repr(s))
#unicode_str = s.decode('unicode-escape')
#splog("WL: str_to_utf8: s: ", repr(unicode_str))
## Python 2.x can't convert the special chars nativly
#utf8_str = utf8_encoder(unicode_str)[0]
#splog("WL: str_to_utf8: s: ", repr(utf8_str))
#return utf8_str #.decode("utf-8").encode("ascii", "ignore")
if type(s) == unicode:
# Default shoud be here
try:
s = s.encode('utf-8')
splog("WL: str_to_utf8 encode utf8: s: ", repr(s))
except:
s = s.encode('utf-8', 'ignore')
splog("WL: str_to_utf8 except encode utf8 ignore: s: ", repr(s))
else:
try:
s = s.decode('utf-8')
splog("WL: str_to_utf8 decode utf8: s: ", repr(s))
except:
try:
s = unicode(s, 'ISO-8859-1')
s = s.encode('utf-8')
splog("WL: str_to_utf8 decode ISO-8859-1: s: ", repr(s))
except:
try:
s = unicode(s, 'cp1252')
s = s.encode('utf-8')
splog("WL: str_to_utf8 decode cp1252: s: ", repr(s))
except:
s = unicode(s, 'ISO-8859-1', 'ignore')
s = s.encode('utf-8')
splog("WL: str_to_utf8 decode ISO-8859-1 ignore: s: ",
repr(s))
s = s.replace('\xe2\x80\x93', '-').replace('\xe2\x80\x99',
"'").replace('\xc3\x9f', 'ß')
return CompiledRegexpNonASCII.sub('', s)
def parseNextPage(self, data):
trs = []
#parser = FSParser()
#parser.feed(data)
#return parser.list
# Handle malformed HTML issues
data = data.replace('\\"','"') # target=\"_blank\"
data = data.replace('\'+\'','') # document.write('<scr'+'ipt
soup = BeautifulSoup(data)
div = soup.find('div', 'gray-bar-header nicht-nochmal')
if div and div.string:
year = div.string[-4:]
splog( "FS year by div", year)
else:
year = self.year
splog( "FS year not found", year)
table = soup.find('table', 'sendetermine')
if table:
for trnode in table.find_all('tr'):
# TODO skip first header row
tdnodes = trnode and trnode.find_all('td')
if tdnodes:
# Filter for known rows
if len(tdnodes) >= 11: # >= 6 and tdnodes[COL_DATE].string and len(tdnodes[COL_DATE].string) >= 10:
tds = []
for idx, tdnode in enumerate(tdnodes):
if idx == COL_TIME:
tds.append( tdnode.string[0:5] )
elif idx == COL_DATE:
tds.append( tdnode.string[0:11] )
elif idx == COL_CHANNEL:
#tds[COL_CHANNEL] = tdnode[COL_CHANNEL]['title']
spans = tdnode.find('span')
if spans:
splog( "spans", len(spans), spans)
tds.append( spans.get('title', '') )
else:
tds.append(tdnode.string or "")
else:
tds.append(tdnode.string or "")
if tds[COL_TIME].find('\xc2\xa0') != -1:
splog( "tdnodes xc2xa0", len(tdnodes), tdnodes)
continue
if tds[COL_DATE].find('\xc2\xa0') != -1:
splog( "tdnodes xc2xa0", len(tdnodes), tdnodes)
continue
tds.append( year )
splog( "FS table tds", tds)
trs.append( tds )
# This row belongs to the previous
#TODO
#elif trs and len(tdnodes) == 5:
# trs[-1][5] += ' ' + (tdnodes[3].string or "")
# trs[-1][6] += ' ' + (tdnodes[4].string or "")
#else:
# splog( "tdnodes", len(tdnodes), tdnodes)
#else:
# splog( "tdnodes", tdnodes )
#http://www.fernsehserien.de/weisst-du-eigentlich-wie-lieb-ich-dich-hab/sendetermine/-1
for idx,tds in enumerate(trs):
if tds[COL_TIME] == " ":
if idx > 0:
tds[COL_TIME] = trs[idx-1][COL_TIME]
if tds[COL_DATE] == " ":
if idx > 0:
tds[COL_DATE] = trs[idx-1][COL_DATE]
else:
splog( "FS table not found")
#splog(trs)
return trs
def parseNextPage(self, data):
trs = []
#parser = FSParser()
#parser.feed(data)
#return parser.list
# Handle malformed HTML issues
data = data.replace('\\"', '"') # target=\"_blank\"
data = data.replace('\'+\'', '') # document.write('<scr'+'ipt
soup = BeautifulSoup(data)
div = soup.find('div', 'gray-bar-header nicht-nochmal')
if div and div.string:
year = div.string[-4:]
splog("FS year by div", year)
else:
year = self.year
splog("FS year not found", year)
table = soup.find('table', 'sendetermine')
if table:
for trnode in table.find_all('tr'):
# TODO skip first header row
tdnodes = trnode and trnode.find_all('td')
if tdnodes:
# Filter for known rows
if len(
tdnodes
) >= 11: # >= 6 and tdnodes[COL_DATE].string and len(tdnodes[COL_DATE].string) >= 10:
tds = []
for idx, tdnode in enumerate(tdnodes):
if idx == COL_TIME:
tds.append(tdnode.string[0:5])
elif idx == COL_DATE:
tds.append(tdnode.string[0:11])
elif idx == COL_CHANNEL:
#tds[COL_CHANNEL] = tdnode[COL_CHANNEL]['title']
spans = tdnode.find('span')
if spans:
splog("spans", len(spans), spans)
tds.append(spans.get('title', ''))
else:
tds.append(tdnode.string or "")
else:
tds.append(tdnode.string or "")
if tds[COL_TIME].find('\xc2\xa0') != -1:
splog("tdnodes xc2xa0", len(tdnodes), tdnodes)
continue
if tds[COL_DATE].find('\xc2\xa0') != -1:
splog("tdnodes xc2xa0", len(tdnodes), tdnodes)
continue
tds.append(year)
splog("FS table tds", tds)
trs.append(tds)
# This row belongs to the previous
#TODO
#elif trs and len(tdnodes) == 5:
# trs[-1][5] += ' ' + (tdnodes[3].string or "")
# trs[-1][6] += ' ' + (tdnodes[4].string or "")
#else:
# splog( "tdnodes", len(tdnodes), tdnodes)
#else:
# splog( "tdnodes", tdnodes )
#http://www.fernsehserien.de/weisst-du-eigentlich-wie-lieb-ich-dich-hab/sendetermine/-1
for idx, tds in enumerate(trs):
if tds[COL_TIME] == " ":
if idx > 0:
tds[COL_TIME] = trs[idx - 1][COL_TIME]
if tds[COL_DATE] == " ":
if idx > 0:
tds[COL_DATE] = trs[idx - 1][COL_DATE]
else:
splog("FS table not found")
#splog(trs)
return trs
def getNextPage(self, id):
url = EPISODEIDURL % (id, self.page)
data = self.getPage(url, Headers)
if data and isinstance(data, basestring):
splog("getNextPage: basestring")
data = self.parseNextPage(data)
self.doCacheList(url, data)
if data and isinstance(data, list):
splog("getNextPage: list")
trs = data
yepisode = None
ydelta = maxint
#first = trs[0][2]
#last = trs[-1][2]
#print first[0:5]
#print last[6:11]
# trs[0] first line [2] second element = timestamps [a:b] use first time
cust_date = trs[0][COL_TIME] + trs[0][COL_DATE]
if len(cust_date) == 11:
cust_date += trs[0][-1]
splog(cust_date)
if len(cust_date) != 15:
return
first = datetime.strptime(cust_date, "%H:%M%d.%m.%Y")
# trs[-1] last line [2] second element = timestamps [a:b] use second time
cust_date = trs[-1][COL_TIME] + trs[-1][COL_DATE]
if len(cust_date) == 11:
cust_date += trs[-1][-1]
splog(cust_date)
if len(cust_date) != 15:
return
last = datetime.strptime(cust_date, "%H:%M%d.%m.%Y")
#first = first - self.td_max_time_drift
#last = last + self.td_max_time_drift
if self.page != 0:
new_page = (self.first != first or self.last != last)
splog(
"getNextPage: first_on_prev_page, first, last_on_prev_page, last, if: ",
self.first, first, self.last, last, new_page)
self.first = first
self.last = last
else:
new_page = True
if new_page:
test_future_timespan = (
(first - self.td_max_time_drift) <= self.begin
and self.begin <= (last + self.td_max_time_drift))
test_past_timespan = (
(first + self.td_max_time_drift) >= self.begin
and self.begin >= (last - self.td_max_time_drift))
splog("first_on_page, self.begin, last_on_page, if, if:",
first, self.begin, last, test_future_timespan,
test_past_timespan)
if (test_future_timespan or test_past_timespan):
#search in page for matching datetime
for tds in trs:
if tds and len(tds) >= 11:
# Grey's Anathomy
#OLD [None, u'31.10.2012', u'20:15\u201321:15 Uhr', u'ProSieben', u'8.', u'15', u'Richtungswechsel']
#
# Gute Zeiten
#OLD [None, u'20.11.2012', u'06:40\u201307:20 Uhr', u'NDR', None, u'4187', u'Folge 4187']
#OLD [None, u'\xa0', None, u'5132', u'Folge 5132']
# Wahnfried
#OLD [u'Sa', u'26.12.1987', u'\u2013', u'So', u'27.12.1987', u'1Plus', None]
# First part: date, times, channel
xdate = tds[COL_DATE]
xbegin = tds[COL_TIME]
#splog( "tds", tds )
#xend = xbegin[6:11]
#xbegin = xbegin[0:5]
cust_date = xbegin + xdate
if len(cust_date) == 11:
cust_date += tds[-1]
splog(cust_date)
if len(cust_date) != 15:
continue
xbegin = datetime.strptime(cust_date,
"%H:%M%d.%m.%Y")
#xend = datetime.strptime( xend+xdate, "%H:%M%d.%m.%Y" )
#print "xbegin", xbegin
#Py2.6
delta = abs(self.begin - xbegin)
delta = delta.seconds + delta.days * 24 * 3600
#Py2.7 delta = abs(self.begin - xbegin).total_seconds()
splog(self.begin, xbegin, delta,
self.max_time_drift)
if delta <= self.max_time_drift:
if self.compareChannels(
self.service, tds[COL_CHANNEL]):
if delta < ydelta:
splog("tds", len(tds), tds)
if len(tds) >= 10:
# Second part: s1e1, s1e2,
xseason = tds[COL_SEASON] or "1"
xepisode = tds[COL_EPISODE]
xtitle = tds[COL_TITLE]
elif len(tds) >= 7:
#TODO
# Second part: s1e1, s1e2,
xseason = tds[4]
xepisode = tds[5]
if xseason and xseason.find(
".") != -1:
xseason = xseason[:-1]
xtitle = tds[6]
else:
xseason = "1"
xtitle = tds[6]
elif len(tds) == 6:
xseason = "0"
xepisode = "0"
xtitle = tds[5]
if xseason and xepisode and xtitle and self.series:
# Handle encodings
xtitle = str_to_utf8(xtitle)
yepisode = (xseason, xepisode,
xtitle, self.series)
ydelta = delta
else: #if delta >= ydelta:
break
else:
self.returnvalue = _(
"Check the channel name")
elif yepisode:
break
if yepisode:
return (yepisode)
else:
# TODO calculate next page : use firstrow lastrow datetime
if not self.future:
if first > self.begin:
self.page -= 1
return
else:
if self.begin > last:
self.page += 1
return
self.page = None
return
def str_to_utf8(s):
# Convert a byte string with unicode escaped characters
splog("WL: str_to_utf8: s: ", repr(s))
#unicode_str = s.decode('unicode-escape')
#splog("WL: str_to_utf8: s: ", repr(unicode_str))
## Python 2.x can't convert the special chars nativly
#utf8_str = utf8_encoder(unicode_str)[0]
#splog("WL: str_to_utf8: s: ", repr(utf8_str))
#return utf8_str #.decode("utf-8").encode("ascii", "ignore")
if type(s) != unicode:
# Default shoud be here
try:
s = s.decode('ISO-8859-1')
splog("WL: str_to_utf8 decode ISO-8859-1: s: ", repr(s))
except:
try:
s = unicode(s, 'utf-8')
s = s.encode('ISO-8859-1')
splog("WL: str_to_utf8 decode utf-8: s: ", repr(s))
except:
try:
s = unicode(s, 'cp1252')
s = s.encode('ISO-8859-1')
splog("WL: str_to_utf8 decode cp1252: s: ", repr(s))
except:
s = unicode(s, 'utf-8', 'ignore')
s = s.encode('ISO-8859-1')
splog("WL: str_to_utf8 decode utf-8 ignore: s: ", repr(s))
else:
try:
s = s.encode('ISO-8859-1')
splog("WL: str_to_utf8 encode ISO-8859-1: s: ", repr(s))
except:
s = s.encode('ISO-8859-1', 'ignore')
splog("WL: str_to_utf8 except encode ISO-8859-1 ignore: s: ", repr(s))
return s
def getNextPage(self, id):
splog("WunschlisteFeed getNextPage")
url = EPISODEIDURLATOM + urlencode({ 's' : id })
data = self.getPage( url )
if data and isinstance(data, basestring):
data = self.parseNextPage(data)
self.doCacheList(url, data)
if data and isinstance(data, list):
trs = data
yepisode = None
ydelta = maxint
for tds in trs:
if tds and len(tds) == 2:
xtitle, xupdated = tds
if xtitle is not None and xupdated is not None:
#import iso8601
#http://code.google.com/p/pyiso8601/
xbegin = parse_date(xupdated)
xbegin = xbegin.replace(tzinfo=None)
#"2014-11-10T20:15:00+01:00"
#xbegin = datetime.strptime(xupdated[0:-6], "%Y-%m-%dT%H:%M:%S");
#Py2.6
delta = abs(self.begin - xbegin)
delta = delta.seconds + delta.days * 24 * 3600
#Py2.7 delta = abs(self.begin - xbegin).total_seconds()
splog(self.begin, xbegin, delta, self.max_time_drift)
if delta <= self.max_time_drift:
result = CompiledRegexpAtomChannel.search(xtitle)
if result and len(result.groups()) >= 1:
if self.compareChannels(self.service, result.group(1)):
if delta < ydelta:
# Slice string to remove channel
xtitle = xtitle[:result.start()]
result = CompiledRegexpAtomDate.search(xtitle)
if result and len(result.groups()) >= 1:
# Slice string to remove date
xtitle = xtitle[:result.start()]
result = CompiledRegexpAtomEpisode.search(xtitle)
if result and len(result.groups()) >= 1:
# Extract season and episode
xepisode = result.group(1)
# Slice string to remove season and episode
xtitle = xtitle[:result.start()]
result = CompiledRegexpEpisode.search(xepisode)
if result and len(result.groups()) >= 3:
xseason = result and result.group(2) or "1"
xepisode = result and result.group(3) or "0"
else:
splog("WunschlisteFeed wrong episode format", xepisode)
xseason = "1"
xepisode = "0"
else:
splog("WunschlisteFeed wrong title format", xtitle)
xseason = "0"
xepisode = "0"
result = CompiledRegexpAtomTitle.search(xtitle)
if result and len(result.groups()) >= 1:
# Extract episode title
xtitle = result.group(1)
# Handle encodings
xtitle = str_to_utf8(xtitle)
yepisode = (xseason, xepisode, xtitle, self.series)
ydelta = delta
else: #if delta >= ydelta:
break
else:
self.returnvalue = _("Check the channel name")
elif yepisode:
break
if yepisode:
return ( yepisode )
def getEpisode(self, name, begin, end=None, service=None):
# On Success: Return a single season, episode, title tuple
# On Failure: Return a empty list or String or None
self.begin = begin
self.year = begin.year
self.end = end
self.service = service
self.series = ""
self.first = None
self.last = None
self.page = 0
self.td_max_time_drift = timedelta(seconds=self.max_time_drift)
self.knownids = []
self.returnvalue = None
# Check preconditions
if not name:
splog(_("Skip Fernsehserien: No show name specified"))
return _("Skip Fernsehserien: No show name specified")
if not begin:
splog(_("Skip Fernsehserien: No begin timestamp specified"))
return _("Skip Fernsehserien: No begin timestamp specified")
if self.begin > datetime.now():
self.future = True
else:
self.future = False
splog("Fernsehserien getEpisode future", self.future)
while name:
ids = self.getSeries(name)
while ids:
idserie = ids.pop()
if idserie and len(idserie) == 2:
id, idname = idserie
# Handle encodings
self.series = str_to_utf8(idname)
#self.page = 0
if self.future:
self.page = 0
else:
if self.actual_year == self.year:
#if self.begin > self.now-timedelta(seconds=3600):
self.page = 0
#else:
# self.page = -1
else:
self.page = 0
year_base_url = EPISODEIDURL % (id, '')
splog("year_base_url: ", year_base_url)
year_url = year_base_url + "jahr-" + str(
self.year + 1)
splog("year_url: ", year_url)
#/sendetermine/jahr-2014
# Increment year by one, because we want to start at the end of the year
response = urlopen(year_url)
#redirecturl = http://www.fernsehserien.de/criminal-intent-verbrechen-im-visier/sendetermine/-14
redirect_url = response.geturl()
splog("redirect_url: ", redirect_url)
try:
self.page = int(
redirect_url.replace(year_base_url, ''))
except:
self.page = 0
self.first = None
self.last = None
while self.page is not None:
result = self.getNextPage(id)
if result:
return result
else:
name = self.getAlternativeSeries(name)
else:
return (self.returnvalue or _("No matching series found"))
def getNextPage(self, id):
splog("WunschlistePrint getNextPage")
url = EPISODEIDURLPRINT + urlencode({ 's' : id })
data = self.getPage( url, Headers )
if data and isinstance(data, basestring):
data = self.parseNextPage(data)
self.doCacheList(url, data)
if data and isinstance(data, list):
trs = data
yepisode = None
ydelta = maxint
actual_year = self.actual_year
for tds in trs:
if tds and len(tds) >= 5:
#print tds
xchannel, xday, xdate, xbegin, xend = tds[:5]
xtitle = "".join(tds[4:])
if self.actual_month == 12 and xdate.endswith(".01."):
year = str(self.actual_year+1)
else:
year = str(self.actual_year)
xbegin = datetime.strptime( xdate+year+" "+xbegin, "%d.%m.%Y %H.%M Uhr" )
#xend = datetime.strptime( xdate+xend, "%d.%m.%Y%H.%M Uhr" )
#splog(xchannel, xdate, xbegin, xend, xtitle)
#splog(datebegin, xbegin, abs((datebegin - xbegin)))
#Py2.6
delta = abs(self.begin - xbegin)
delta = delta.seconds + delta.days * 24 * 3600
#Py2.7 delta = abs(self.begin - xbegin).total_seconds()
splog(self.begin, xbegin, delta, self.max_time_drift)
if delta <= self.max_time_drift:
if self.compareChannels(self.service, xchannel):
if delta < ydelta:
print len(tds), tds
if len(tds) >= 7:
xepisode, xtitle = tds[5:7]
if xepisode:
result = CompiledRegexpEpisode.search(xepisode)
if result and len(result.groups()) >= 3:
xseason = result and result.group(2) or "1"
xepisode = result and result.group(3) or "0"
else:
xseason = "1"
xepisode = "0"
else:
xseason = "1"
xepisode = "0"
elif len(tds) == 6:
xtitle = tds[5]
xseason = "0"
xepisode = "0"
# Handle encodings
xtitle = str_to_utf8(xtitle)
yepisode = (xseason, xepisode, xtitle, self.series)
ydelta = delta
else: #if delta >= ydelta:
break
else:
self.returnvalue = _("Check the channel name")
elif yepisode:
break
if yepisode:
return ( yepisode )
def getNextPage(self, id):
url = EPISODEIDURL % (id, self.page)
data = self.getPage(url, Headers)
if data and isinstance(data, basestring):
splog("getNextPage: basestring")
data = self.parseNextPage(data)
self.doCacheList(url, data)
if data and isinstance(data, list):
splog("getNextPage: list")
trs = data
# trs[x] = [None, u'31.10.2012', u'20:15\u201321:15 Uhr', u'ProSieben', u'8.', u'15', u'Richtungswechsel']
yepisode = None
ydelta = maxint
# first = trs[0][2]
# last = trs[-1][2]
# print first[0:5]
# print last[6:11]
# trs[0] first line [2] second element = timestamps [a:b] use first time
first = datetime.strptime(trs[0][2][0:5] + trs[0][1], "%H:%M%d.%m.%Y")
# trs[-1] last line [2] second element = timestamps [a:b] use second time
# last = datetime.strptime( trs[-1][2][6:11] + trs[-1][1], "%H:%M%d.%m.%Y" )
# Problem with wrap around use also start time
# Sa 30.11.2013 23:35 - 01:30 Uhr ProSieben 46 3. 13 Showdown 3
last = datetime.strptime(trs[-1][2][0:5] + trs[-1][1], "%H:%M%d.%m.%Y")
# first = first - self.td_max_time_drift
# last = last + self.td_max_time_drift
if self.page != 0:
new_page = self.first != first or self.last != last
splog(
"getNextPage: first_on_prev_page, first, last_on_prev_page, last, if: ",
self.first,
first,
self.last,
last,
new_page,
)
self.first = first
self.last = last
else:
new_page = True
if new_page:
test_future_timespan = (first - self.td_max_time_drift) <= self.begin and self.begin <= (
last + self.td_max_time_drift
)
test_past_timespan = (first + self.td_max_time_drift) >= self.begin and self.begin >= (
last - self.td_max_time_drift
)
splog(
"first_on_page, self.begin, last_on_page, if, if:",
first,
self.begin,
last,
test_future_timespan,
test_past_timespan,
)
if test_future_timespan or test_past_timespan:
# search in page for matching datetime
for tds in trs:
if tds and len(tds) >= 6: # 7:
# Grey's Anathomy
# [None, u'31.10.2012', u'20:15\u201321:15 Uhr', u'ProSieben', u'8.', u'15', u'Richtungswechsel']
#
# Gute Zeiten
# [None, u'20.11.2012', u'06:40\u201307:20 Uhr', u'NDR', None, u'4187', u'Folge 4187']
# [None, u'01.12.2012', u'10:45\u201313:15 Uhr', u'RTL', None, u'5131', u'Folge 5131']
# [None, u'\xa0', None, u'5132', u'Folge 5132']
# [None, u'\xa0', None, u'5133', u'Folge 5133']
# [None, u'\xa0', None, u'5134', u'Folge 5134']
# [None, u'\xa0', None, u'5135', u'Folge 5135']
# Wahnfried
# [u'Sa', u'26.12.1987', u'\u2013', u'So', u'27.12.1987', u'1Plus', None]
# First part: date, times, channel
xdate, xbegin = tds[1:3]
# splog( "tds", tds )
# xend = xbegin[6:11]
xbegin = xbegin[0:5]
xbegin = datetime.strptime(xbegin + xdate, "%H:%M%d.%m.%Y")
# xend = datetime.strptime( xend+xdate, "%H:%M%d.%m.%Y" )
# print "xbegin", xbegin
# Py2.6
delta = abs(self.begin - xbegin)
delta = delta.seconds + delta.days * 24 * 3600
# Py2.7 delta = abs(self.begin - xbegin).total_seconds()
splog(self.begin, xbegin, delta, self.max_time_drift)
if delta <= self.max_time_drift:
if self.compareChannels(self.service, tds[3]):
if delta < ydelta:
splog("tds", len(tds), tds)
if len(tds) >= 10:
# Second part: s1e1, s1e2,
xseason = tds[7] or "1"
xepisode = tds[8]
xtitle = " ".join(tds[10:]) # Use all available titles
elif len(tds) >= 7:
# Second part: s1e1, s1e2,
xseason = tds[4]
xepisode = tds[5]
if xseason and xseason.find(".") != -1:
xseason = xseason[:-1]
xtitle = " ".join(tds[6:]) # Use all available titles
else:
xseason = "1"
xtitle = " ".join(tds[6:]) # Use all available titles
elif len(tds) == 6:
xseason = "0"
xepisode = "0"
xtitle = tds[5]
if xseason and xepisode and xtitle and self.series:
# Handle encodings
xtitle = str_to_utf8(xtitle)
yepisode = (xseason, xepisode, xtitle, self.series)
ydelta = delta
else: # if delta >= ydelta:
break
else:
self.returnvalue = _("Check the channel name")
elif yepisode:
break
if yepisode:
return yepisode
else:
# TODO calculate next page : use firstrow lastrow datetime
if not self.future:
if first > self.begin:
self.page -= 1
return
else:
if self.begin > last:
self.page += 1
return
self.page = None
return
def getNextPage(self, id):
splog("WunschlisteFeed getNextPage")
url = EPISODEIDURLATOM + urlencode({'s': id})
data = self.getPage(url)
if data and isinstance(data, basestring):
data = self.parseNextPage(data)
self.doCacheList(url, data)
if data and isinstance(data, list):
trs = data
yepisode = None
ydelta = maxint
for tds in trs:
if tds and len(tds) == 2:
xtitle, xupdated = tds
if xtitle is not None and xupdated is not None:
#import iso8601
#http://code.google.com/p/pyiso8601/
xbegin = parse_date(xupdated)
xbegin = xbegin.replace(tzinfo=None)
#"2014-11-10T20:15:00+01:00"
#xbegin = datetime.strptime(xupdated[0:-6], "%Y-%m-%dT%H:%M:%S");
#Py2.6
delta = abs(self.begin - xbegin)
delta = delta.seconds + delta.days * 24 * 3600
#Py2.7 delta = abs(self.begin - xbegin).total_seconds()
splog(self.begin, xbegin, delta, self.max_time_drift)
if delta <= self.max_time_drift:
result = CompiledRegexpAtomChannel.search(xtitle)
if result and len(result.groups()) >= 1:
if self.compareChannels(
self.service, result.group(1)):
if delta < ydelta:
# Slice string to remove channel
xtitle = xtitle[:result.start()]
result = CompiledRegexpAtomDate.search(
xtitle)
if result and len(
result.groups()) >= 1:
# Slice string to remove date
xtitle = xtitle[:result.start()]
result = CompiledRegexpAtomEpisode.search(
xtitle)
if result and len(
result.groups()) >= 1:
# Extract season and episode
xepisode = result.group(1)
# Slice string to remove season and episode
xtitle = xtitle[:result.start(
)]
result = CompiledRegexpEpisode.search(
xepisode)
if result and len(
result.groups()) >= 3:
xseason = result and result.group(
2) or "1"
xepisode = result and result.group(
3) or "0"
else:
splog(
"WunschlisteFeed wrong episode format",
xepisode)
xseason = "1"
xepisode = "0"
else:
splog(
"WunschlisteFeed wrong title format",
xtitle)
xseason = "0"
xepisode = "0"
result = CompiledRegexpAtomTitle.search(
xtitle)
if result and len(
result.groups()) >= 1:
# Extract episode title
xtitle = result.group(1)
# Handle encodings
xtitle = str_to_utf8(xtitle)
yepisode = (xseason, xepisode,
xtitle,
self.series)
ydelta = delta
else: #if delta >= ydelta:
break
else:
self.returnvalue = _(
"Check the channel name")
elif yepisode:
break
if yepisode:
return (yepisode)
def getEpisode(self, name, begin, end=None, service=None):
# On Success: Return a single season, episode, title tuple
# On Failure: Return a empty list or String or None
self.begin = begin
self.year = begin.year
self.end = end
self.service = service
self.series = ""
self.first = None
self.last = None
self.page = 0
self.td_max_time_drift = timedelta(seconds=self.max_time_drift)
self.knownids = []
self.returnvalue = None
# Check preconditions
if not name:
splog(_("Skip Fernsehserien: No show name specified"))
return _("Skip Fernsehserien: No show name specified")
if not begin:
splog(_("Skip Fernsehserien: No begin timestamp specified"))
return _("Skip Fernsehserien: No begin timestamp specified")
if self.begin > datetime.now():
self.future = True
else:
self.future = False
splog("Fernsehserien getEpisode future", self.future)
while name:
ids = self.getSeries(name)
while ids:
idserie = ids.pop()
if idserie and len(idserie) == 2:
id, idname = idserie
# Handle encodings
self.series = str_to_utf8(idname)
#self.page = 0
if self.future:
self.page = 0
else:
if self.actual_year == self.year:
#if self.begin > self.now-timedelta(seconds=3600):
self.page = 0
#else:
# self.page = -1
else:
self.page = 0
year_base_url = EPISODEIDURL % (id, '')
splog("year_base_url: ", year_base_url)
year_url = year_base_url+"jahr-"+str(self.year+1)
splog("year_url: ", year_url)
#/sendetermine/jahr-2014
# Increment year by one, because we want to start at the end of the year
from plugin import PROXY
response = urlopen( PROXY + year_url )
#redirecturl = http://www.fernsehserien.de/criminal-intent-verbrechen-im-visier/sendetermine/-14
redirect_url = response.geturl()
splog("redirect_url: ", redirect_url)
try:
self.page = int( redirect_url.replace(year_base_url,'') )
except:
self.page = 0
self.first = None
self.last = None
while self.page is not None:
result = self.getNextPage(id)
if result:
return result
else:
name = self.getAlternativeSeries(name)
else:
return ( self.returnvalue or _("No matching series found") )
def getNextPage(self, id):
url = EPISODEIDURL % (id, self.page)
data = self.getPage(url)
if data and isinstance(data, basestring):
splog("getNextPage: basestring")
data = self.parseNextPage(data)
self.doCacheList(url, data)
if data and isinstance(data, list):
splog("getNextPage: list")
trs = data
yepisode = None
ydelta = maxint
#first = trs[0][2]
#last = trs[-1][2]
#print first[0:5]
#print last[6:11]
# trs[0] first line [2] second element = timestamps [a:b] use first time
cust_date = trs[0][COL_TIME] + trs[0][COL_DATE]
if len(cust_date) == 11:
cust_date += trs[0][-1]
splog(cust_date)
if len(cust_date) != 15:
return
first = datetime.strptime( cust_date, "%H:%M%d.%m.%Y" )
# trs[-1] last line [2] second element = timestamps [a:b] use second time
cust_date = trs[-1][COL_TIME] + trs[-1][COL_DATE]
if len(cust_date) == 11:
cust_date += trs[-1][-1]
splog(cust_date)
if len(cust_date) != 15:
return
last = datetime.strptime( cust_date, "%H:%M%d.%m.%Y" )
#first = first - self.td_max_time_drift
#last = last + self.td_max_time_drift
if self.page != 0:
new_page = (self.first != first or self.last != last)
splog("getNextPage: first_on_prev_page, first, last_on_prev_page, last, if: ", self.first, first, self.last, last, new_page)
self.first = first
self.last = last
else:
new_page = True
if new_page:
test_future_timespan = ( (first-self.td_max_time_drift) <= self.begin and self.begin <= (last+self.td_max_time_drift) )
test_past_timespan = ( (first+self.td_max_time_drift) >= self.begin and self.begin >= (last-self.td_max_time_drift) )
splog("first_on_page, self.begin, last_on_page, if, if:", first, self.begin, last, test_future_timespan, test_past_timespan )
if ( test_future_timespan or test_past_timespan ):
#search in page for matching datetime
for tds in trs:
if tds and len(tds) >= 11:
# Grey's Anathomy
#OLD [None, u'31.10.2012', u'20:15\u201321:15 Uhr', u'ProSieben', u'8.', u'15', u'Richtungswechsel']
#
# Gute Zeiten
#OLD [None, u'20.11.2012', u'06:40\u201307:20 Uhr', u'NDR', None, u'4187', u'Folge 4187']
#OLD [None, u'\xa0', None, u'5132', u'Folge 5132']
# Wahnfried
#OLD [u'Sa', u'26.12.1987', u'\u2013', u'So', u'27.12.1987', u'1Plus', None]
# First part: date, times, channel
xdate = tds[COL_DATE]
xbegin = tds[COL_TIME]
#splog( "tds", tds )
#xend = xbegin[6:11]
#xbegin = xbegin[0:5]
cust_date = xbegin+xdate
if len(cust_date) == 11:
cust_date += tds[-1]
splog(cust_date)
if len(cust_date) != 15:
continue
xbegin = datetime.strptime( cust_date, "%H:%M%d.%m.%Y" )
#xend = datetime.strptime( xend+xdate, "%H:%M%d.%m.%Y" )
#print "xbegin", xbegin
#Py2.6
delta = abs(self.begin - xbegin)
delta = delta.seconds + delta.days * 24 * 3600
#Py2.7 delta = abs(self.begin - xbegin).total_seconds()
splog(self.begin, xbegin, delta, self.max_time_drift)
if delta <= self.max_time_drift:
if self.compareChannels(self.service, tds[COL_CHANNEL]):
if delta < ydelta:
splog( "tds", len(tds), tds )
if len(tds) >= 10:
# Second part: s1e1, s1e2,
xseason = tds[COL_SEASON] or "1"
xepisode = tds[COL_EPISODE]
xtitle = tds[COL_TITLE]
elif len(tds) >= 7:
#TODO
# Second part: s1e1, s1e2,
xseason = tds[4]
xepisode = tds[5]
if xseason and xseason.find(".") != -1:
xseason = xseason[:-1]
xtitle = tds[6]
else:
xseason = "1"
xtitle = tds[6]
elif len(tds) == 6:
xseason = "0"
xepisode = "0"
xtitle = tds[5]
if xseason and xepisode and xtitle and self.series:
# Handle encodings
xtitle = str_to_utf8(xtitle)
yepisode = (xseason, xepisode, xtitle, self.series)
ydelta = delta
else: #if delta >= ydelta:
break
else:
self.returnvalue = _("Check the channel name")
elif yepisode:
break
if yepisode:
return ( yepisode )
else:
# TODO calculate next page : use firstrow lastrow datetime
if not self.future:
if first > self.begin:
self.page -= 1
return
else:
if self.begin > last:
self.page += 1
return
self.page = None
return
def str_to_utf8(s):
# Convert a byte string with unicode escaped characters
splog("WL: str_to_utf8: s: ", repr(s))
#unicode_str = s.decode('unicode-escape')
#splog("WL: str_to_utf8: s: ", repr(unicode_str))
## Python 2.x can't convert the special chars nativly
#utf8_str = utf8_encoder(unicode_str)[0]
#splog("WL: str_to_utf8: s: ", repr(utf8_str))
#return utf8_str #.decode("utf-8").encode("ascii", "ignore")
if type(s) == unicode:
# Default shoud be here
try:
s = s.encode('utf-8')
splog("WL: str_to_utf8 encode utf8: s: ", repr(s))
except:
s = s.encode('utf-8', 'ignore')
splog("WL: str_to_utf8 except encode utf8 ignore: s: ", repr(s))
else:
try:
s = s.decode('utf-8')
splog("WL: str_to_utf8 decode utf8: s: ", repr(s))
except:
try:
s = unicode(s, 'ISO-8859-1')
s = s.encode('utf-8')
splog("WL: str_to_utf8 decode ISO-8859-1: s: ", repr(s))
except:
try:
s = unicode(s, 'cp1252')
s = s.encode('utf-8')
splog("WL: str_to_utf8 decode cp1252: s: ", repr(s))
except:
s = unicode(s, 'ISO-8859-1', 'ignore')
s = s.encode('utf-8')
splog("WL: str_to_utf8 decode ISO-8859-1 ignore: s: ", repr(s))
s = s.replace('\xe2\x80\x93','-').replace('\xe2\x80\x99',"'").replace('\xc3\x9f','ß')
return CompiledRegexpNonASCII.sub('', s)
def str_to_utf8(s):
# Convert a byte string with unicode escaped characters
splog("WL: str_to_utf8: s: ", repr(s))
#unicode_str = s.decode('unicode-escape')
#splog("WL: str_to_utf8: s: ", repr(unicode_str))
## Python 2.x can't convert the special chars nativly
#utf8_str = utf8_encoder(unicode_str)[0]
#splog("WL: str_to_utf8: s: ", repr(utf8_str))
#return utf8_str #.decode("utf-8").encode("ascii", "ignore")
if type(s) != unicode:
# Default shoud be here
try:
s = s.decode('ISO-8859-1')
splog("WL: str_to_utf8 decode ISO-8859-1: s: ", repr(s))
except:
try:
s = unicode(s, 'utf-8')
s = s.encode('ISO-8859-1')
splog("WL: str_to_utf8 decode utf-8: s: ", repr(s))
except:
try:
s = unicode(s, 'cp1252')
s = s.encode('ISO-8859-1')
splog("WL: str_to_utf8 decode cp1252: s: ", repr(s))
except:
s = unicode(s, 'utf-8', 'ignore')
s = s.encode('ISO-8859-1')
splog("WL: str_to_utf8 decode utf-8 ignore: s: ", repr(s))
else:
try:
s = s.encode('ISO-8859-1')
splog("WL: str_to_utf8 encode ISO-8859-1: s: ", repr(s))
except:
s = s.encode('ISO-8859-1', 'ignore')
splog("WL: str_to_utf8 except encode ISO-8859-1 ignore: s: ",
repr(s))
return s
def getNextPage(self, id):
splog("WunschlistePrint getNextPage")
url = EPISODEIDURLPRINT + urlencode({ 's' : id })
data = self.getPage( url )
if data and isinstance(data, basestring):
data = self.parseNextPage(data)
self.doCacheList(url, data)
if data and isinstance(data, list):
trs = data
yepisode = None
ydelta = maxint
actual_year = self.actual_year
for tds in trs:
if tds and len(tds) >= 5:
#print tds
xchannel, xday, xdate, xbegin, xend = tds[:5]
xtitle = "".join(tds[4:])
if self.actual_month == 12 and xdate.endswith(".01."):
year = str(self.actual_year+1)
else:
year = str(self.actual_year)
xbegin = datetime.strptime( xdate+year+" "+xbegin, "%d.%m.%Y %H.%M Uhr" )
#xend = datetime.strptime( xdate+xend, "%d.%m.%Y%H.%M Uhr" )
#splog(xchannel, xdate, xbegin, xend, xtitle)
#splog(datebegin, xbegin, abs((datebegin - xbegin)))
#Py2.6
delta = abs(self.begin - xbegin)
delta = delta.seconds + delta.days * 24 * 3600
#Py2.7 delta = abs(self.begin - xbegin).total_seconds()
splog(self.begin, xbegin, delta, self.max_time_drift)
if delta <= self.max_time_drift:
if self.compareChannels(self.service, xchannel):
if delta < ydelta:
print len(tds), tds
if len(tds) >= 7:
xepisode, xtitle = tds[5:7]
if xepisode:
result = CompiledRegexpEpisode.search(xepisode)
if result and len(result.groups()) >= 3:
xseason = result and result.group(2) or "1"
xepisode = result and result.group(3) or "0"
else:
xseason = "1"
xepisode = "0"
else:
xseason = "1"
xepisode = "0"
elif len(tds) == 6:
xtitle = tds[5]
xseason = "0"
xepisode = "0"
# Handle encodings
xtitle = str_to_utf8(xtitle)
yepisode = (xseason, xepisode, xtitle, self.series)
ydelta = delta
else: #if delta >= ydelta:
break
else:
self.returnvalue = _("Check the channel name")
elif yepisode:
break
if yepisode:
return ( yepisode )