def _get_title_and_url(self, item):
"""
Retrieves the title and URL data from the item XML node.
Overridden here so that we can have a preference for magnets.
item: An xml.dom.minidom.Node representing the <item> tag of the RSS feed
Returns: A tuple containing two strings representing title and URL respectively
"""
title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
url = None
try:
if sickbeard.PREFER_MAGNETS:
try:
url = helpers.get_xml_text(item.getElementsByTagName('magnetURI')[0])
torrent_hash = self.getHashFromMagnet(url)
if not torrent_hash:
logger.log(u'magnetURI "%s" found for "%s", but it has no valid hash - ignoring' % (url, title),
logger.WARNING)
url = None
except Exception:
pass
if url is None:
url = helpers.get_xml_text(item.getElementsByTagName('link')[0])
if url:
url = url.replace('&','&')
except IndexError:
url = None
return (title, url)
def _get_title_and_url(self, item):
title, url = None, None
self.cache._remove_namespace(item)
title = helpers.get_xml_text(item.find('title'))
attempt_list = [lambda: helpers.get_xml_text(item.find('magnetURI')),
lambda: item.find('enclosure').get('url'),
lambda: helpers.get_xml_text(item.find('link'))]
for cur_attempt in attempt_list:
try:
url = cur_attempt()
except:
continue
if title and url:
return (title, url)
return (title, url)
def _get_title_and_url(self, item):
"""
Retrieves the title and URL data from the item XML node.
Overridden here so that we can have a preference for magnets.
item: An xml.dom.minidom.Node representing the <item> tag of the RSS feed
Returns: A tuple containing two strings representing title and URL respectively
"""
title = helpers.get_xml_text(item.getElementsByTagName("title")[0])
url = None
try:
if sickbeard.PREFER_MAGNETS:
try:
url = helpers.get_xml_text(item.getElementsByTagName("magnetURI")[0])
torrent_hash = self.getHashFromMagnet(url)
if not torrent_hash:
logger.log(
u'magnetURI "%s" found for "%s", but it has no valid hash - ignoring' % (url, title),
logger.WARNING,
)
url = None
except Exception:
pass
if url is None:
url = helpers.get_xml_text(item.getElementsByTagName("link")[0])
if url:
url = url.replace("&", "&")
except IndexError:
url = None
return (title, url)
def _get_title_and_url(self, item):
title, url = None, None
self.cache._remove_namespace(item)
title = helpers.get_xml_text(item.find('title'))
attempt_list = [lambda: helpers.get_xml_text(item.find('magnetURI')),
lambda: item.find('enclosure').get('url'),
lambda: helpers.get_xml_text(item.find('link'))]
for cur_attempt in attempt_list:
try:
url = cur_attempt()
except:
continue
if title and url:
return (title, url)
return (title, url)
def _get_title_and_url(self, item):
title = helpers.get_xml_text(item.find('title'))
# logger.log('publichd got title' + title)
url = None
if sickbeard.PREFER_MAGNETS:
magnetURI = helpers.get_xml_text(item.find('{http://xmlns.ezrss.it/0.1/}torrent/{http://xmlns.ezrss.it/0.1/}magnetURI'))
# logger.log('publichd got magnetURI' + magnetURI)
if magnetURI:
url = magnetURI
if not url:
enclos = item.find('enclosure')
if enclos is not None:
url = enclos.get('url')
# logger.log('publichd got enclosure url ' + url)
if url:
url = url.replace('&', '&')
if title.startswith('[TORRENT] '):
title = title[10:]
# these guys also get creative with the torrent names, adding crud at the
# end like "[PublicHD]", "[P2PDL]" etc. which confuses sb. Best to
# just remove it if present
crudAtEndMatch = re.match(r'(.*) \[\w+\]$', title)
if crudAtEndMatch:
title = crudAtEndMatch.group(1)
return (title, url)
def _get_title_and_url(self, item):
title = helpers.get_xml_text(item.find('title'))
# logger.log('publichd got title' + title)
url = None
if sickbeard.PREFER_MAGNETS:
magnetURI = helpers.get_xml_text(
item.find(
'{http://xmlns.ezrss.it/0.1/}torrent/{http://xmlns.ezrss.it/0.1/}magnetURI'
))
# logger.log('publichd got magnetURI' + magnetURI)
if magnetURI:
url = magnetURI
if not url:
enclos = item.find('enclosure')
if enclos is not None:
url = enclos.get('url')
# logger.log('publichd got enclosure url ' + url)
if url:
url = url.replace('&', '&')
if title.startswith('[TORRENT] '):
title = title[10:]
# these guys also get creative with the torrent names, adding crud at the
# end like "[PublicHD]", "[P2PDL]" etc. which confuses sb. Best to
# just remove it if present
crudAtEndMatch = re.match(r'(.*) \[\w+\]$', title)
if crudAtEndMatch:
title = crudAtEndMatch.group(1)
return (title, url)
def _doSearch(self, searchString, show=None, season=None, french=None):
results = []
searchUrl = self.url+'rdirect.php?type=search&'+searchString.replace('!','')
logger.log(u"Search URL: " + searchUrl, logger.DEBUG)
data = self.getURL(searchUrl)
if "bad key" in str(data).lower() :
logger.log(u"GKS key invalid, check your config", logger.ERROR)
return []
parsedXML = parseString(data)
channel = parsedXML.getElementsByTagName('channel')[0]
description = channel.getElementsByTagName('description')[0]
description_text = helpers.get_xml_text(description).lower()
if "user can't be found" in description_text:
logger.log(u"GKS invalid digest, check your config", logger.ERROR)
return []
elif "invalid hash" in description_text:
logger.log(u"GKS invalid hash, check your config", logger.ERROR)
return []
else :
items = channel.getElementsByTagName('item')
for item in items:
title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
if "aucun resultat" in title.lower() :
logger.log(u"No results found in " + searchUrl, logger.DEBUG)
return []
count=1
if season:
count=0
if show:
if show.audio_lang=='fr' or french:
for frword in['french', 'truefrench', 'multi']:
if frword in title.lower():
count+=1
else:
count +=1
else:
count +=1
if count==0:
continue
else :
downloadURL = helpers.get_xml_text(item.getElementsByTagName('link')[0])
quality = Quality.nameQuality(title)
if quality==Quality.UNKNOWN and title:
if '720p' not in title.lower() and '1080p' not in title.lower():
quality=Quality.SDTV
if show and french==None:
results.append( GksSearchResult( self.opener, title, downloadURL, quality, str(show.audio_lang) ) )
elif show and french:
results.append( GksSearchResult( self.opener, title, downloadURL, quality, 'fr' ) )
else:
results.append( GksSearchResult( self.opener, title, downloadURL, quality ) )
return results
def _parseItem(self, item):
title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
url = helpers.get_xml_text(item.getElementsByTagName('link')[0])
if not title or not url:
logger.log("The XML returned from the FreshOnTV RSS feed is incomplete, this result is unusable", logger.ERROR)
return
logger.log("Adding item from RSS to cache: " + title, logger.DEBUG)
self._addCacheEntry(title, url,
quality=common.Quality.nameQuality(title))
def _get_title_and_url(self, item):
"""
Retrieves the title and URL data from the item XML node
item: An xml.dom.minidom.Node representing the <item> tag of the RSS feed
Returns: A tuple containing two strings representing title and URL respectively
"""
title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
url = helpers.get_xml_text(item.getElementsByTagName('link')[0])
if url:
url = url.replace('&','&')
return (title, url)
def _get_title_and_url(self, item):
"""
Retrieves the title and URL data from the item XML node
item: An xml.dom.minidom.Node representing the <item> tag of the RSS feed
Returns: A tuple containing two strings representing title and URL respectively
"""
title = helpers.get_xml_text(item.getElementsByTagName("title")[0])
try:
url = helpers.get_xml_text(item.getElementsByTagName("link")[0])
if url:
url = url.replace("&", "&")
except IndexError:
url = None
return (title, url)
def _get_title_and_url(self, item):
"""
Retrieves the title and URL data from the item XML node
item: An xml.dom.minidom.Node representing the <item> tag of the RSS feed
Returns: A tuple containing two strings representing title and URL respectively
"""
title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
try:
url = helpers.get_xml_text(item.getElementsByTagName('link')[0])
if url:
url = url.replace('&','&')
except IndexError:
url = None
return (title, url)
def _get_title_and_url(self, item):
title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
url = item.getElementsByTagName('enclosure')[0].getAttribute('url').replace('&','&')
if title.startswith('[TORRENT] '):
title = title[10:]
return (title, url)
def _get_title_and_url(self, item):
(title, url) = generic.TorrentProvider._get_title_and_url(self, item)
if url and url.startswith(('http://twitter.com/', 'https://twitter.com/')):
# this feed came from twitter
#
# we need to extract the filename and url from the twitter message (the url we have currently is just that of the twitter message,
# which is of little use to us).
# The message looks something like this:
# eztv_it: History Ch The Universe Season 4 08of12 Space Wars XviD AC3 [MVGroup org] - http://t.co/mGTrhB4a
#
# Start by splitting the (real) url from the filename
title, url = title.rsplit(' - http', 1)
url = 'http' + url
# Then strip off the leading eztv_it:
if title.startswith('eztv_it:'):
title = title[8:]
# For safety we remove any whitespace too.
title = title.strip()
logger.log(u"Extracted the name %s and url %s from the twitter link"%(title, url), logger.DEBUG)
else:
# this feed came from ezrss
torrent_node = item.getElementsByTagName('torrent')[0]
filename_node = torrent_node.getElementsByTagName('fileName')[0]
filename = get_xml_text(filename_node)
new_title = self._extract_name_from_filename(filename)
if new_title:
title = new_title
logger.log(u"Extracted the name "+title+" from the torrent link", logger.DEBUG)
return (title, url)
def _get_title_and_url(self, item):
description_node = item.getElementsByTagName("description")[0]
title = get_xml_text(description_node).replace("_", ".").split(" (")[0]
url = item.getElementsByTagName("enclosure")[0].getAttribute("url")
return (title, url)
def findPropers(self, date=None):
results = []
for curString in (".PROPER.", ".REPACK."):
for curResult in self._doSearch(curString):
(title, url) = self._get_title_and_url(curResult)
pubDate_node = curResult.getElementsByTagName('pubDate')[0]
pubDate = helpers.get_xml_text(pubDate_node)
match = re.search(
'(\w{3}, \d{1,2} \w{3} \d{4} \d\d:\d\d:\d\d) [\+\-]\d{4}',
pubDate)
if not match:
continue
resultDate = datetime.datetime.strptime(
match.group(1), "%a, %d %b %Y %H:%M:%S")
if date == None or resultDate > date:
results.append(classes.Proper(title, url, resultDate))
return results
def _get_title_and_url(self, item):
(title, url) = generic.TorrentProvider._get_title_and_url(self, item)
filename = helpers.get_xml_text(item.find('{http://xmlns.ezrss.it/0.1/}torrent/{http://xmlns.ezrss.it/0.1/}fileName'))
magnet = helpers.get_xml_text(item.find('{http://xmlns.ezrss.it/0.1/}torrent/{http://xmlns.ezrss.it/0.1/}magnetURI'))
if filename:
new_title = self._extract_name_from_filename(filename)
if new_title:
title = new_title
logger.log(u"Extracted the name " + title + " from the torrent link", logger.DEBUG)
if self.useMagnet() and magnet:
url = magnet
return (title, url)
def findPropers(self, date=None):
results = []
for curResult in self._doSearch("(PROPER,REPACK)"):
(title, url) = self._get_title_and_url(curResult)
description_node = curResult.getElementsByTagName('description')[0]
descriptionStr = helpers.get_xml_text(description_node)
dateStr = re.search(
'<b>Added:</b> (\d{4}-\d\d-\d\d \d\d:\d\d:\d\d)',
descriptionStr).group(1)
if not dateStr:
logger.log(u"Unable to figure out the date for entry " +
title + ", skipping it")
continue
else:
resultDate = datetime.datetime.strptime(
dateStr, "%Y-%m-%d %H:%M:%S")
if date == None or resultDate > date:
results.append(classes.Proper(title, url, resultDate))
return results
def getQuality(self, item):
attributes = item.report[0]
attr_dict = {}
for attribute in attributes.getElementsByTagName('report:attribute'):
cur_attr = attribute.getAttribute('type')
cur_attr_value = helpers.get_xml_text(attribute)
if cur_attr not in attr_dict:
attr_dict[cur_attr] = [cur_attr_value]
else:
attr_dict[cur_attr].append(cur_attr_value)
logger.log("Finding quality of item based on attributes " + str(attr_dict), logger.DEBUG)
if self._is_SDTV(attr_dict):
quality = Quality.SDTV
elif self._is_SDDVD(attr_dict):
quality = Quality.SDDVD
elif self._is_HDTV(attr_dict):
quality = Quality.HDTV
elif self._is_WEBDL(attr_dict):
quality = Quality.HDWEBDL
elif self._is_720pBluRay(attr_dict):
quality = Quality.HDBLURAY
elif self._is_1080pBluRay(attr_dict):
quality = Quality.FULLHDBLURAY
else:
quality = Quality.UNKNOWN
logger.log("Resulting quality: " + str(quality), logger.DEBUG)
return quality
def _get_title_and_url(self, item):
(title, url) = generic.TorrentProvider._get_title_and_url(self, item)
filename = helpers.get_xml_text(
item.find(
'{http://xmlns.ezrss.it/0.1/}torrent/{http://xmlns.ezrss.it/0.1/}fileName'
))
new_title = self._extract_name_from_filename(filename)
if new_title:
title = new_title
logger.log(
u"Extracted the name " + title + " from the torrent link",
logger.DEBUG)
# feedburner adds "[eztv] " to the start of all titles, so trim it off
if title and title[:7] == "[eztv] ":
title = title[7:]
logger.log(u"Trimmed [eztv] from title to get %s" % title,
logger.DEBUG)
# ditto VTV:
if title and title[:6] == "[VTV] ":
title = title[6:]
logger.log(u"Trimmed [VTV] from title to get %s" % title,
logger.DEBUG)
return (title, url)
def _get_title_and_url(self, item):
# (title, url) = generic.TorrentProvider._get_title_and_url(self, item)
title = helpers.get_xml_text(item.getElementsByTagName("title")[0])
url = item.getElementsByTagName("enclosure")[0].getAttribute("url").replace("&", "&")
return (title, url)
def _parseItem(self, item):
title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
url = helpers.get_xml_text(item.getElementsByTagName('link')[0])
self._checkItemAuth(title, url)
if not title or not url:
logger.log(u"The XML returned from the "+self.provider.name+" feed is incomplete, this result is unusable", logger.ERROR)
return
url = self._translateLinkURL(url)
logger.log(u"Adding item from RSS to cache: "+title, logger.DEBUG)
self._addCacheEntry(title, url)
def getQuality(self, item):
filename = helpers.get_xml_text(
item.find('{http://xmlns.ezrss.it/0.1/}torrent/{http://xmlns.ezrss.it/0.1/}fileName'))
quality = Quality.nameQuality(filename)
return quality
def _get_title_and_url(self, item):
description_node = item.getElementsByTagName('description')[0]
title = get_xml_text(description_node).replace('_', '.').split(' (')[0]
url = item.getElementsByTagName('enclosure')[0].getAttribute('url')
return (title, url)
def findPropers(self, search_date=None):
search_terms = ['.proper.', '.repack.']
cache_results = self.cache.listPropers(search_date)
results = [classes.Proper(x['name'], x['url'], datetime.datetime.fromtimestamp(x['time'])) for x in cache_results]
for term in search_terms:
for item in self._doSearch({'q': term}, max_age=4):
(title, url) = self._get_title_and_url(item)
description_node = item.find('pubDate')
description_text = helpers.get_xml_text(description_node)
try:
# we could probably do dateStr = descriptionStr but we want date in this format
date_text = re.search('(\w{3}, \d{1,2} \w{3} \d{4} \d\d:\d\d:\d\d) [\+\-]\d{4}', description_text).group(1)
except:
date_text = None
if not date_text:
logger.log(u"Unable to figure out the date for entry " + title + ", skipping it")
continue
else:
result_date = email.utils.parsedate(date_text)
if result_date:
result_date = datetime.datetime(*result_date[0:6])
if not search_date or result_date > search_date:
search_result = classes.Proper(title, url, result_date)
results.append(search_result)
return results
def _get_title_and_url(self, item):
(title, url) = generic.TorrentProvider._get_title_and_url(self, item)
try:
# ezrss feed will have a 'torrent' node
torrent_node = item.getElementsByTagName('torrent')[0]
filename_node = torrent_node.getElementsByTagName('fileName')[0]
filename = get_xml_text(filename_node)
new_title = self._extract_name_from_filename(filename)
if new_title:
title = new_title
logger.log(u"Extracted the name "+title+" from the torrent link", logger.DEBUG)
except IndexError:
# we'll get an IndexError above when there's no 'torrent' node,
# which likely means that this isn't in the special ezrss format.
# So assume we're working with with a standard rss feed.
logger.log(u"IndexError while parsing the ezrss feed, maybe it's just standard RSS? Trying that ...", logger.DEBUG)
(title, url) = generic.TorrentProvider._get_title_and_url(self, item)
# feedburner adds "[eztv] " to the start of all titles, so trim it off
if title and title[:7] == "[eztv] ":
title = title[7:]
logger.log(u"Trimmed [eztv] from title to get %s" % title, logger.DEBUG)
# ditto VTV:
if title and title[:6] == "[VTV] ":
title = title[6:]
logger.log(u"Trimmed [VTV] from title to get %s" % title, logger.DEBUG)
return (title, url)
def _get_title_and_url(self, item):
description_node = item.getElementsByTagName('description')[0]
title = get_xml_text(description_node).replace('_', '.').split(' (')[0]
url = item.getElementsByTagName('enclosure')[0].getAttribute('url')
return (title, url)
def getQuality(self, item, anime=False):
attributes = item.getElementsByTagName('report:attributes')[0]
attr_dict = {}
for attribute in attributes.getElementsByTagName('report:attribute'):
cur_attr = attribute.getAttribute('type')
cur_attr_value = helpers.get_xml_text(attribute)
if cur_attr not in attr_dict:
attr_dict[cur_attr] = [cur_attr_value]
else:
attr_dict[cur_attr].append(cur_attr_value)
logger.log(
"Finding quality of item based on attributes " + str(attr_dict),
logger.DEBUG)
if self._is_SDTV(attr_dict, anime):
quality = Quality.SDTV
elif self._is_SDDVD(attr_dict, anime):
quality = Quality.SDDVD
elif self._is_HDTV(attr_dict, anime):
quality = Quality.HDTV
elif self._is_WEBDL(attr_dict, anime):
quality = Quality.HDWEBDL
elif self._is_720pBluRay(attr_dict, anime):
quality = Quality.HDBLURAY
elif self._is_1080pBluRay(attr_dict, anime):
quality = Quality.FULLHDBLURAY
else:
quality = Quality.UNKNOWN
logger.log("Resulting quality: " + str(quality), logger.DEBUG)
return quality
def _parseItem(self, item):
title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
url = helpers.get_xml_text(item.getElementsByTagName('link')[0])
self._checkItemAuth(title, url)
if not title or not url:
logger.log(u"The XML returned from the "+self.provider.name+" feed is incomplete, this result is unusable", logger.ERROR)
return
url = self._translateLinkURL(url)
logger.log(u"Adding item from RSS to cache: "+title, logger.DEBUG)
self._addCacheEntry(title, url)
def getQuality(self, item):
filename = helpers.get_xml_text(
item.find('{http://xmlns.ezrss.it/0.1/}torrent/{http://xmlns.ezrss.it/0.1/}fileName'))
quality = Quality.nameQuality(filename)
return quality
def _get_title_and_url(self, item):
#(title, url) = generic.TorrentProvider._get_title_and_url(self, item)
title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
url = None
# if we have a preference for magnets, go straight for the throat...
try:
url = helpers.get_xml_text(item.getElementsByTagName('magnetURI')[0])
except Exception:
pass
if url is None:
url = item.getElementsByTagName('enclosure')[0].getAttribute('url').replace('&','&')
return (title, url)
def _get_seeders(self, item):
try:
return int(
helpers.get_xml_text(
item.find('{http://xmlns.ezrss.it/0.1/}seeds')))
except ValueError:
return 1 # safer to return 1 than 0, otherwise if this breaks all torrents would be ignored!
def findPropers(self, search_date=None):
search_terms = ['.proper.', '.repack.']
cache_results = self.cache.listPropers(search_date)
results = [classes.Proper(x['name'], x['url'], datetime.datetime.fromtimestamp(x['time'])) for x in cache_results]
for term in search_terms:
for item in self._doSearch({'q': term}, max_age=4):
(title, url) = self._get_title_and_url(item)
description_node = item.find('pubDate')
description_text = helpers.get_xml_text(description_node)
try:
# we could probably do dateStr = descriptionStr but we want date in this format
date_text = re.search('(\w{3}, \d{1,2} \w{3} \d{4} \d\d:\d\d:\d\d) [\+\-]\d{4}', description_text).group(1)
except:
date_text = None
if not date_text:
logger.log(u"Unable to figure out the date for entry " + title + ", skipping it")
continue
else:
result_date = email.utils.parsedate(date_text)
if result_date:
result_date = datetime.datetime(*result_date[0:6])
if not search_date or result_date > search_date:
search_result = classes.Proper(title, url, result_date)
results.append(search_result)
return results
def _get_title_and_url(self, item):
#(title, url) = generic.TorrentProvider._get_title_and_url(self, item)
title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
url = item.getElementsByTagName('enclosure')[0].getAttribute('url').replace('&','&')
return (title, url)
def _parseItem(self, item):
title = helpers.get_xml_text(item.find('title'))
url = helpers.get_xml_text(item.find('link'))
self._checkItemAuth(title, url)
if title and url:
title = self._translateTitle(title)
url = self._translateLinkURL(url)
logger.log(u"Adding item from RSS to cache: " + title, logger.DEBUG)
self._addCacheEntry(title, url)
else:
logger.log(u"The XML returned from the " + self.provider.name + " feed is incomplete, this result is unusable", logger.DEBUG)
return
def _parseItem(self, item):
try:
title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
torrentz_url = helpers.get_xml_text(item.getElementsByTagName('guid')[0])
url = self.provider._getTorrentzCache(torrentz_url)
if not title or not url:
#logger.log(u"The XML returned from the " + self.provider.name + " RSS feed is incomplete, this result is unusable: " + torrentz_url, logger.ERROR)
return
logger.log(u"Adding item from " + self.provider.name + " RSS to cache: "+title, logger.DEBUG)
self._addCacheEntry(title, url)
except Exception, e:
logger.log(u"Error trying to parse " + self.provider.name + " cache: "+str(e).decode('utf-8'), logger.ERROR)
raise
def _parseItem(self, item):
try:
title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
url = helpers.get_xml_text(item.getElementsByTagName('torrentLink')[0]).replace('&','&')
if not title or not url:
logger.log(u"The XML returned from the KICKASS RSS feed is incomplete, this result is unusable", logger.ERROR)
return
logger.log(u"Adding item from KICKASS RSS to cache: "+title, logger.DEBUG)
self._addCacheEntry(title, url)
except Exception, e:
logger.log(u"Error trying to parse KICKASS cache: "+str(e).decode('utf-8'), logger.ERROR)
traceback.print_exc()
raise
def _parseItem(self, item):
title = helpers.get_xml_text(item.find('title'))
url = helpers.get_xml_text(item.find('link'))
self._checkItemAuth(title, url)
if title and url:
title = self._translateTitle(title)
url = self._translateLinkURL(url)
logger.log(u"Adding item from RSS to cache: " + title, logger.DEBUG)
self._addCacheEntry(title, url)
else:
logger.log(u"The XML returned from the " + self.provider.name + " feed is incomplete, this result is unusable", logger.DEBUG)
return
def _get_title_and_url(self, item):
"""
Retrieves the title and URL data from the item XML node
item: An elementtree.ElementTree element representing the <item> tag of the RSS feed
Returns: A tuple containing two strings representing title and URL respectively
"""
title = helpers.get_xml_text(item.find('title'))
if title:
title = title.replace(' ', '.')
url = helpers.get_xml_text(item.find('link'))
if url:
url = url.replace('&', '&')
return (title, url)
def _parseItem(self, item):
try:
title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
torrentz_url = helpers.get_xml_text(item.getElementsByTagName('guid')[0])
url = self.provider._getTorrentzCache(torrentz_url)
if not title or not url:
#logger.log(u"The XML returned from the " + self.provider.name + " RSS feed is incomplete, this result is unusable: " + torrentz_url, logger.ERROR)
return
logger.log(u"Adding item from " + self.provider.name + " RSS to cache: "+title, logger.DEBUG)
self._addCacheEntry(title, url)
except Exception, e:
logger.log(u"Error trying to parse " + self.provider.name + " cache: "+str(e).decode('utf-8'), logger.ERROR)
raise
def _get_title_and_url(self, item):
#(title, url) = generic.TorrentProvider._get_title_and_url(self, item)
title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
url = item.getElementsByTagName('enclosure')[0].getAttribute(
'url').replace('&', '&')
return (title, url)
def _get_title_and_url(self, item):
title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
# Finding the url for the torrent can be a bit tricky, as everyone seems to have their own
# ideas as to where it should be.
# cf. http://www.bittorrent.org/beps/bep_0036.html (but note that this isn't entirely reliable,
# or indeed correct).
# If there's an 'enclosure' tag, then we can be reasonably confident that
# its url attribute will be the torrent url.
url = None
try:
url = item.getElementsByTagName('enclosure')[0].getAttribute('url').replace('&','&')
except IndexError:
# next port-of-call is the 'link' tag, we use this if it looks like
# a torrent link
url = helpers.get_xml_text(item.getElementsByTagName('link')[0])
if url.startswith('magnet:') or url.endswith('.torrent'):
# found!
pass
else:
# link tag doesn't look like a torrent, look for a torrent tag
try:
torrTag = item.getElementsByTagName('torrent')[0]
try:
url = helpers.get_xml_text(torrTag.getElementsByTagName('magnetURI')[0])
except IndexError:
# No magnetURI? then use the infoHash
infoHash = helpers.get_xml_text(torrTag.getElementsByTagName('infoHash')[0])
url = 'magnet:?xt=urn:btih:' + infoHash
except IndexError:
# no torrent tag? They I guess we just have to use the link
# tag, even if it doesn't look like a torrent
url = helpers.get_xml_text(item.getElementsByTagName('link')[0])
if title:
# Badly formed rss sometimes will wrap the title in newlines, which
# of course throws off the regex's. This should fix it.
title = title.strip()
if url:
# Ditto, badly formed rss can have newlines and other crap around the
# url, and even spaces in the url.
url = url.replace('&','&').strip().replace(' ', '%20')
return (title, url)
def _get_title_and_url(self, item):
"""
Retrieves the title and URL data from the item XML node
item: An elementtree.ElementTree element representing the <item> tag of the RSS feed
Returns: A tuple containing two strings representing title and URL respectively
"""
title = helpers.get_xml_text(item.find('title'))
if title:
title = title.replace(' ', '.')
url = helpers.get_xml_text(item.find('link'))
if url:
url = url.replace('&', '&')
return (title, url)
def getQuality(self, item):
torrent_node = item.getElementsByTagName("torrent")[0]
filename_node = torrent_node.getElementsByTagName("fileName")[0]
filename = get_xml_text(filename_node)
quality = Quality.nameQuality(filename)
return quality
def getQuality(self, item, anime=False):
torrent_node = item.getElementsByTagName('torrent')[0]
filename_node = torrent_node.getElementsByTagName('fileName')[0]
filename = get_xml_text(filename_node)
quality = Quality.nameQuality(filename, anime)
return quality
def getQuality(self, item):
torrent_node = item.getElementsByTagName('torrent')[0]
filename_node = torrent_node.getElementsByTagName('fileName')[0]
filename = get_xml_text(filename_node)
quality = Quality.sceneQuality(filename)
return quality
def _doSearch(self, searchString, show=None, season=None):
results = []
searchUrl = self.url + 'rdirect.php?type=search&' + searchString
logger.log(u"Search URL: " + searchUrl, logger.DEBUG)
data = self.getURL(searchUrl)
if "bad key" in str(data).lower():
logger.log(u"GKS key invalid, check your config", logger.ERROR)
return []
parsedXML = parseString(data)
channel = parsedXML.getElementsByTagName('channel')[0]
description = channel.getElementsByTagName('description')[0]
description_text = helpers.get_xml_text(description).lower()
if "user can't be found" in description_text:
logger.log(u"GKS invalid digest, check your config", logger.ERROR)
return []
elif "invalid hash" in description_text:
logger.log(u"GKS invalid hash, check your config", logger.ERROR)
return []
else:
items = channel.getElementsByTagName('item')
for item in items:
title = helpers.get_xml_text(
item.getElementsByTagName('title')[0])
if "aucun resultat" in title.lower():
logger.log(u"No results found in " + searchUrl,
logger.DEBUG)
return []
else:
downloadURL = helpers.get_xml_text(
item.getElementsByTagName('link')[0])
quality = Quality.nameQuality(title)
if show:
results.append(
GksSearchResult(self.opener, title, downloadURL,
quality, str(show.audio_lang)))
else:
results.append(
GksSearchResult(self.opener, title, downloadURL,
quality))
return results
def _get_title_and_url(self, item):
# <item>
# <title>The Dealership S01E03 HDTV x264 C4TV</title>
# <category>TV</category>
# <link>http://kickass.to/the-dealership-s01e03-hdtv-x264-c4tv-t7739376.html</link>
# <guid>http://kickass.to/the-dealership-s01e03-hdtv-x264-c4tv-t7739376.html</guid>
# <pubDate>Thu, 15 Aug 2013 20:54:03 +0000</pubDate>
# <torrent:contentLength>311302749</torrent:contentLength>
# <torrent:infoHash>F94F9B44A03DDA439E5818E2C2F18342103522EF</torrent:infoHash>
# <torrent:magnetURI><![CDATA[magnet:?xt=urn:btih:F94F9B44A03DDA439E5818E2C2F18342103522EF&dn=the+dealership+s01e03+hdtv+x264+c4tv&tr=udp%3A%2F%2Ftracker.publicbt.com%3A80&tr=udp%3A%2F%2Fopen.demonii.com%3A1337]]></torrent:magnetURI>
# <torrent:seeds>0</torrent:seeds>
# <torrent:peers>0</torrent:peers>
# <torrent:verified>0</torrent:verified>
# <torrent:fileName>the.dealership.s01e03.hdtv.x264.c4tv.torrent</torrent:fileName>
# <enclosure url="http://torcache.net/torrent/F94F9B44A03DDA439E5818E2C2F18342103522EF.torrent?title=[kickass.to]the.dealership.s01e03.hdtv.x264.c4tv" length="311302749" type="application/x-bittorrent" />
# </item>
title = helpers.get_xml_text(item.find('title'))
url = None
if sickbeard.PREFER_MAGNETS:
# if we have a preference for magnets, go straight for the throat...
url = helpers.get_xml_text(
item.find(
'{http://xmlns.ezrss.it/0.1/}torrent/{http://xmlns.ezrss.it/0.1/}magnetURI'
))
if not url:
# The above, although standard, is unlikely in kat. They kinda screw up their namespaces, so we get
# this instead...
url = helpers.get_xml_text(
item.find('{http://xmlns.ezrss.it/0.1/}magnetURI'))
if not url:
enclos = item.find('enclosure')
if enclos is not None:
url = enclos.get('url')
if url:
url = url.replace('&', '&')
if not url:
url = None # this should stop us returning empty strings as urls
return (title, url)
def _parseItem(self, item):
"""Return None
parse a single rss feed item and add its info to the chache
will check for needed infos
"""
title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
url = helpers.get_xml_text(item.getElementsByTagName('link')[0])
self._checkItemAuth(title, url)
# we at least need a title and url, if one is missing stop
if not title or not url:
logger.log(u"The XML returned from the "+self.provider.name+" feed is incomplete, this result is unusable", logger.ERROR)
return
url = self._translateLinkURL(url)
logger.log(u"Adding item from RSS to cache: "+title, logger.DEBUG)
self._addCacheEntry(title, url)
def _parseItem(self, item):
"""Return None
parse a single rss feed item and add its info to the chache
will check for needed infos
"""
title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
url = helpers.get_xml_text(item.getElementsByTagName('link')[0])
self._checkItemAuth(title, url)
# we at least need a title and url, if one is missing stop
if not title or not url:
logger.log(u"The XML returned from the "+self.provider.name+" feed is incomplete, this result is unusable", logger.ERROR)
return
url = self._translateLinkURL(url)
logger.log(u"Adding item from RSS to cache: "+title, logger.DEBUG)
self._addCacheEntry(title, url)
def isValidCategory(self, item):
"""
Decides if the category of an item (from the rss feed) could be a valid
tv show.
@param item: An elementTree Node representing the <item> tag of the RSS feed
@return: boolean
"""
category = helpers.get_xml_text(item.find('category'))
return category in ('BluRay 720p', 'BluRay 1080p', 'BluRay Remux',
'BluRay', 'BluRay 3D', 'XviD', 'BRRip', 'HDTV',
'SDTV', 'TV WEB-DL', 'TV Packs')
def isValidCategory(self, item):
"""
Decides if the category of an item (from the rss feed) could be a valid
tv show.
@param item: An xml.dom.minidom.Node representing the <item> tag of the RSS feed
@return: boolean
"""
category = helpers.get_xml_text(item.getElementsByTagName('category')[0])
return category in ('BluRay 720p', 'BluRay 1080p', 'BluRay Remux',
'BluRay', 'BluRay 3D', 'XviD', 'BRRip',
'HDTV', 'SDTV', 'TV WEB-DL', 'TV Packs')
def _checkAuthFromData(self, parsedXML):
if parsedXML is None:
return self._checkAuth()
description_text = helpers.get_xml_text(parsedXML.find('.//channel/item/description'))
if "Your RSS key is invalid" in description_text:
logger.log(u"Incorrect authentication credentials for " + self.name + " : " + str(description_text), logger.DEBUG)
raise AuthException(u"Your authentication credentials for " + self.name + " are incorrect, check your config")
return True
def _checkAuthFromData(self, parsedXML):
if parsedXML is None:
return self._checkAuth()
description_text = helpers.get_xml_text(parsedXML.find('.//channel/description'))
if "User can't be found" in description_text or "Invalid Hash" in description_text:
logger.log(u"Incorrect authentication credentials for " + self.name + " : " + str(description_text), logger.DEBUG)
raise AuthException(u"Your authentication credentials for " + self.name + " are incorrect, check your config")
return True
def _get_title_and_url(self, item):
(title, url) = generic.TorrentProvider._get_title_and_url(self, item)
filename = helpers.get_xml_text(item.find('{http://xmlns.ezrss.it/0.1/}torrent/{http://xmlns.ezrss.it/0.1/}fileName'))
if filename:
new_title = self._extract_name_from_filename(filename)
if new_title:
title = new_title
logger.log(u"Extracted the name " + title + " from the torrent link", logger.DEBUG)
return (title, url)
def getQuality(self, item):
#torrent_node = item.getElementsByTagName('torrent')[0]
#filename_node = torrent_node.getElementsByTagName('title')[0]
#filename = get_xml_text(filename_node)
# I think the only place we can get anything resembing the filename is in
# the title
filename = helpers.get_xml_text(item.getElementsByTagName('title')[0])
quality = Quality.nameQuality(filename)
return quality
def _get_title_and_url(self, item):
"""
Retrieves the title and URL data from the item XML node
item: An xml.dom.minidom.Node representing the <item> tag of the RSS feed
Returns: A tuple containing two strings representing title and URL respectively
"""
"""we are here in the search provider it is ok to delete the /.
i am doing this because some show get posted with a / in the name
and during qulaity check it is reduced to the base name
"""
title = helpers.get_xml_text(
item.getElementsByTagName('title')[0]).replace("/", " ")
try:
url = helpers.get_xml_text(item.getElementsByTagName('link')[0])
if url:
url = url.replace('&', '&')
except IndexError:
url = None
return (title, url)
def _get_title_and_url(self, item):
(title, url) = generic.TorrentProvider._get_title_and_url(self, item)
torrent_node = item.getElementsByTagName('torrent')[0]
filename_node = torrent_node.getElementsByTagName('fileName')[0]
filename = get_xml_text(filename_node)
new_title = self._extract_name_from_filename(filename)
if new_title:
title = new_title
logger.log(u"Extracted the name "+title+" from the torrent link", logger.DEBUG)
return (title, url)
def _get_title_and_url(self, item):
"""
Retrieves the title and URL data from the item XML node.
Some Einstein decided to change `item` from a xml.dom.minidom.Node to
an elementtree.ElementTree element upstream, without taking into
account that this is the base for *LOTS* of classes, so it will
basically break every one of them unless they are all changed.
Why does python even allow this crap? Strong typing is a good thing
for a language Guido!
(so, rant over, we now need to cater for both cases here)
@param item: An xml.dom.minidom.Node (or an elementtree.ElementTree
element) representing the <item> tag of the RSS feed.
@return: A tuple containing two strings representing title and URL
respectively.
"""
if isinstance(item, xml.dom.minidom.Node):
title = helpers.get_xml_text(item.getElementsByTagName('title')[0],
mini_dom=True)
try:
url = helpers.get_xml_text(
item.getElementsByTagName('link')[0], mini_dom=True)
if url:
url = url.replace('&', '&')
except IndexError:
url = None
else:
title = helpers.get_xml_text(item.find('title'))
if title:
title = title.replace(' ', '.')
url = helpers.get_xml_text(item.find('link'))
if url:
url = url.replace('&', '&')
return (title, url)