Select Git revision
newznab.py 11.90 KiB
# Author: Nic Wolfe <nic@wolfeden.ca>
# URL: http://code.google.com/p/sickbeard/
#
# This file is part of Sick Beard.
#
# Sick Beard 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, either version 3 of the License, or
# (at your option) any later version.
#
# Sick Beard 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 Sick Beard. If not, see <http://www.gnu.org/licenses/>.
import urllib
import email.utils
import datetime
import re
import os
from xml.dom.minidom import parseString
import sickbeard
import generic
from sickbeard import classes, show_name_helpers
from sickbeard import helpers
from sickbeard import scene_exceptions
from sickbeard import encodingKludge as ek
from sickbeard import exceptions
from sickbeard import logger
from sickbeard import tvcache
from sickbeard.exceptions import ex
from sickbeard.name_parser.parser import NameParser, InvalidNameException
class NewznabProvider(generic.NZBProvider):
def __init__(self, name, url, key=''):
generic.NZBProvider.__init__(self, name)
self.cache = NewznabCache(self)
self.url = url
self.key = key
# if a provider doesn't need an api key then this can be false
self.needs_auth = True
self.enabled = True
self.supportsBacklog = True
self.default = False
def configStr(self):
return self.name + '|' + self.url + '|' + self.key + '|' + str(int(self.enabled))
def imageName(self):
if ek.ek(os.path.isfile, ek.ek(os.path.join, sickbeard.PROG_DIR, 'data', 'images', 'providers', self.getID() + '.png')):
return self.getID() + '.png'
return 'newznab.png'
def isEnabled(self):
return self.enabled
def _get_season_search_strings(self, show, season=None):
if not show:
return [{}]
to_return = []
# add new query strings for exceptions
name_exceptions = scene_exceptions.get_scene_exceptions(show.tvdbid) + [show.name]
for cur_exception in name_exceptions:
cur_params = {}
# search directly by tvrage id
if show.tvrid:
cur_params['rid'] = show.tvrid
# if we can't then fall back on a very basic name search
else:
if show.audio_lang=="fr":
cur_params['q'] = helpers.sanitizeSceneName(cur_exception)+ " french"
else:
cur_params['q'] = helpers.sanitizeSceneName(cur_exception)
if season != None:
# air-by-date means &season=2010&q=2010.03, no other way to do it atm
if show.air_by_date:
cur_params['season'] = season.split('-')[0]
if 'q' in cur_params:
cur_params['q'] += '.' + season.replace('-', '.')
else:
cur_params['q'] = season.replace('-', '.')
else:
cur_params['season'] = season
# hack to only add a single result if it's a rageid search
if not ('rid' in cur_params and to_return):
to_return.append(cur_params)
return to_return
def _get_episode_search_strings(self, ep_obj, french=None):
showNames = show_name_helpers.allPossibleShowNames(ep_obj.show)
for show_name in showNames:
ep_obj.show.sname=show_name
params = {}
if not ep_obj:
return [params]
# search directly by tvrage id
if ep_obj.show.tvrid:
params['rid'] = ep_obj.show.tvrid
if ep_obj.show.audio_lang=="fr" or french:
params['q'] = "french"
else:
params['q'] = helpers.sanitizeSceneName(ep_obj.show.sname)
# if we can't then fall back on a very basic name search
else:
if ep_obj.show.audio_lang=="fr" or french:
params['q'] = helpers.sanitizeSceneName(ep_obj.show.sname) + " french"
else:
params['q'] = helpers.sanitizeSceneName(ep_obj.show.sname)
if ep_obj.show.air_by_date:
date_str = str(ep_obj.airdate)
params['season'] = date_str.partition('-')[0]
params['ep'] = date_str.partition('-')[2].replace('-', '/')
else:
params['season'] = ep_obj.scene_season
params['ep'] = ep_obj.scene_episode
to_return = [params]
# only do exceptions if we are searching by name
if 'q' in params:
# add new query strings for exceptions
name_exceptions = scene_exceptions.get_scene_exceptions(ep_obj.show.tvdbid)
for cur_exception in name_exceptions:
# don't add duplicates
if cur_exception == ep_obj.show.sname:
continue
cur_return = params.copy()
cur_return['q'] = helpers.sanitizeSceneName(cur_exception)
to_return.append(cur_return)
return to_return
def _get_language(self, title=None, item=None):
if not title:
return 'en'
else:
try:
myParser = NameParser()
parse_result = myParser.parse(title)
except InvalidNameException:
logger.log(u"Unable to parse the filename "+title+" into a valid episode", logger.WARNING)
return 'en'
return parse_result.audio_langs
def _doGeneralSearch(self, search_string):
return self._doSearch({'q': search_string.replace('!','')})
def _checkAuthFromData(self, data):
try:
parsedXML = parseString(data)
except Exception:
return False
if parsedXML.documentElement.tagName == 'error':
code = parsedXML.documentElement.getAttribute('code')
if code == '100':
raise exceptions.AuthException("Your API key for " + self.name + " is incorrect, check your config.")
elif code == '101':
raise exceptions.AuthException("Your account on " + self.name + " has been suspended, contact the administrator.")
elif code == '102':
raise exceptions.AuthException("Your account isn't allowed to use the API on " + self.name + ", contact the administrator")
else:
logger.log(u"Unknown error given from " + self.name + ": "+parsedXML.documentElement.getAttribute('description'), logger.ERROR)
return False
return True
def _doSearch(self, search_params, show=None, max_age=0, season=None, french=None):
cat = '5030,5040'
if (show and show.audio_lang != u"en") or french:
cat = '5020'
params = {"t": "tvsearch",
"maxage": sickbeard.USENET_RETENTION,
"limit": 100,
"cat": cat}
# if max_age is set, use it, don't allow it to be missing
if max_age or not params['maxage']:
params['maxage'] = max_age
# hack this in for now
if self.getID() == 'nzbs_org':
params['cat'] += ',5070,5090'
if search_params:
params.update(search_params)
if self.key:
params['apikey'] = self.key
searchURL = self.url + 'api?' + urllib.urlencode(params)
logger.log(u"Search url: " + searchURL, logger.DEBUG)
data = self.getURL(searchURL)
if not data:
return []
# hack this in until it's fixed server side
if not data.startswith('<?xml'):
data = '<?xml version="1.0" encoding="ISO-8859-1" ?>' + data
try:
parsedXML = parseString(data)
items = parsedXML.getElementsByTagName('item')
except Exception, e:
logger.log(u"Error trying to load " + self.name + " RSS feed: " + ex(e), logger.ERROR)
logger.log(u"RSS data: " + data, logger.DEBUG)
return []
if not self._checkAuthFromData(data):
return []
if parsedXML.documentElement.tagName != 'rss':
logger.log(u"Resulting XML from " + self.name + " isn't RSS, not parsing it", logger.ERROR)
return []
results = []
for curItem in items:
(title, url) = self._get_title_and_url(curItem)
if not title or not url:
logger.log(u"The XML returned from the " + self.name + " RSS feed is incomplete, this result is unusable: " + data, logger.ERROR)
continue
results.append(curItem)
return results
def findPropers(self, date=None):
search_terms = ['.proper.', '.repack.']
results = []
cache_results = self.cache.listPropers(date)
results = [classes.Proper(x['name'], x['url'], datetime.datetime.fromtimestamp(x['time'])) for x in cache_results]
for term in search_terms:
for curResult in self._doSearch({'q': term}, max_age=4):
(title, url) = self._get_title_and_url(curResult)
description_node = curResult.getElementsByTagName('pubDate')[0]
descriptionStr = helpers.get_xml_text(description_node)
try:
# we could probably do dateStr = descriptionStr but we want date in this format
dateStr = re.search('(\w{3}, \d{1,2} \w{3} \d{4} \d\d:\d\d:\d\d) [\+\-]\d{4}', descriptionStr).group(1)
except:
dateStr = None
if not dateStr:
logger.log(u"Unable to figure out the date for entry " + title + ", skipping it")
continue
else:
resultDate = email.utils.parsedate(dateStr)
if resultDate:
resultDate = datetime.datetime(*resultDate[0:6])
if date == None or resultDate > date:
search_result = classes.Proper(title, url, resultDate)
results.append(search_result)
return results
class NewznabCache(tvcache.TVCache):
def __init__(self, provider):
tvcache.TVCache.__init__(self, provider)
# only poll newznab providers every 15 minutes max
self.minTime = 15
def _getRSSData(self):
languages = helpers.getAllLanguages()
languages = filter(lambda x: not x == u"en", languages)
cat = '5030,5040'
if len(languages) > 0:
cat = '5020'
params = {"t": "tvsearch",
"cat": cat}
# hack this in for now
if self.provider.getID() == 'nzbs_org':
params['cat'] += ',5070,5090'
if self.provider.key:
params['apikey'] = self.provider.key
url = self.provider.url + 'api?' + urllib.urlencode(params)
logger.log(self.provider.name + " cache update URL: " + url, logger.DEBUG)
data = self.provider.getURL(url)
# hack this in until it's fixed server side
if data and not data.startswith('<?xml'):
data = '<?xml version="1.0" encoding="ISO-8859-1" ?>' + data
return data
def _checkAuth(self, data):
return self.provider._checkAuthFromData(data)