1
0
mirror of https://github.com/moparisthebest/SickRage synced 2024-12-14 12:02:21 -05:00
SickRage/sickbeard/providers/generic.py

474 lines
18 KiB
Python
Raw Normal View History

2014-04-22 04:02:43 -04:00
# coding=utf-8
# Author: Nic Wolfe <nic@wolfeden.ca>
# URL: http://code.google.com/p/sickbeard/
#
2014-05-23 08:37:22 -04:00
# This file is part of SickRage.
#
2014-05-23 08:37:22 -04:00
# SickRage 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.
#
2014-05-23 08:37:22 -04:00
# SickRage 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
2014-05-23 08:37:22 -04:00
# along with SickRage. If not, see <http://www.gnu.org/licenses/>.
from __future__ import with_statement
import datetime
import os
import re
import itertools
import sickbeard
import requests
from sickbeard import helpers, classes, logger, db
from sickbeard.common import MULTI_EP_RESULT, SEASON_RESULT, USER_AGENT
from sickbeard import tvcache
from sickbeard import encodingKludge as ek
from sickbeard.exceptions import ex
from sickbeard.name_parser.parser import NameParser, InvalidNameException, InvalidShowException
from sickbeard.common import Quality
from sickbeard import clients
from hachoir_parser import createParser
2014-09-11 13:26:17 -04:00
from base64 import b16encode, b32decode
class GenericProvider:
NZB = "nzb"
TORRENT = "torrent"
def __init__(self, name):
# these need to be set in the subclass
self.providerType = None
self.name = name
self.url = ''
self.show = None
self.supportsBacklog = False
self.supportsAbsoluteNumbering = False
self.anime_only = False
self.search_mode = None
self.search_fallback = False
self.enable_daily = False
self.enable_backlog = False
self.cache = tvcache.TVCache(self)
self.session = requests.session()
self.headers = {
# Using USER_AGENT instead of Mozilla to keep same user agent along authentication and download phases,
#otherwise session might be broken and download fail, asking again for authentication
#'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1700.107 Safari/537.36'}
'User-Agent': USER_AGENT}
def getID(self):
return GenericProvider.makeID(self.name)
@staticmethod
def makeID(name):
return re.sub("[^\w\d_]", "_", name.strip().lower())
def imageName(self):
return self.getID() + '.png'
def _checkAuth(self):
return True
def _doLogin(self):
return True
def isActive(self):
if self.providerType == GenericProvider.NZB and sickbeard.USE_NZBS:
return self.isEnabled()
elif self.providerType == GenericProvider.TORRENT and sickbeard.USE_TORRENTS:
return self.isEnabled()
else:
return False
def isEnabled(self):
"""
This should be overridden and should return the config setting eg. sickbeard.MYPROVIDER
"""
return False
def getResult(self, episodes):
"""
Returns a result of the correct type for this provider
"""
if self.providerType == GenericProvider.NZB:
result = classes.NZBSearchResult(episodes)
elif self.providerType == GenericProvider.TORRENT:
result = classes.TorrentSearchResult(episodes)
else:
result = classes.SearchResult(episodes)
result.provider = self
return result
def getURL(self, url, post_data=None, params=None, timeout=30, json=False):
"""
By default this is just a simple urlopen call but this method should be overridden
for providers with special URL requirements (like cookies)
"""
# check for auth
if not self._doLogin():
return
return helpers.getURL(url, post_data=post_data, params=params, headers=self.headers, timeout=timeout,
session=self.session, json=json)
def downloadResult(self, result):
"""
Save the result to disk.
"""
# check for auth
if not self._doLogin():
return False
if self.providerType == GenericProvider.TORRENT:
try:
torrent_hash = re.findall('urn:btih:([\w]{32,40})', result.url)[0].upper()
2014-09-11 13:26:17 -04:00
if len(torrent_hash) == 32:
torrent_hash = b16encode(b32decode(torrent_hash)).lower()
if not torrent_hash:
logger.log("Unable to extract torrent hash from link: " + ex(result.url), logger.ERROR)
return False
urls = [
'http://torcache.net/torrent/' + torrent_hash + '.torrent',
'http://torrage.com/torrent/' + torrent_hash + '.torrent',
'http://zoink.it/torrent/' + torrent_hash + '.torrent',
]
except:
urls = [result.url]
filename = ek.ek(os.path.join, sickbeard.TORRENT_DIR,
helpers.sanitizeFileName(result.name) + '.' + self.providerType)
elif self.providerType == GenericProvider.NZB:
urls = [result.url]
filename = ek.ek(os.path.join, sickbeard.NZB_DIR,
helpers.sanitizeFileName(result.name) + '.' + self.providerType)
else:
return
for url in urls:
if helpers.download_file(url, filename, session=self.session):
logger.log(u"Downloading a result from " + self.name + " at " + url)
if self.providerType == GenericProvider.TORRENT:
logger.log(u"Saved magnet link to " + filename, logger.MESSAGE)
else:
logger.log(u"Saved result to " + filename, logger.MESSAGE)
if self._verify_download(filename):
return True
logger.log(u"Failed to download result", logger.ERROR)
return False
def _verify_download(self, file_name=None):
"""
Checks the saved file to see if it was actually valid, if not then consider the download a failure.
"""
# primitive verification of torrents, just make sure we didn't get a text file or something
if self.providerType == GenericProvider.TORRENT:
parser = createParser(file_name)
if parser:
mime_type = parser._getMimeType()
try:
parser.stream._input.close()
except:
pass
if mime_type == 'application/x-bittorrent':
return True
logger.log(u"Result is not a valid torrent file", logger.WARNING)
return False
return True
def searchRSS(self, episodes):
return self.cache.findNeededEpisodes(episodes)
def getQuality(self, item, anime=False):
"""
Figures out the quality of the given RSS item node
item: An elementtree.ElementTree element representing the <item> tag of the RSS feed
Returns a Quality value obtained from the node's data
"""
(title, url) = self._get_title_and_url(item)
quality = Quality.sceneQuality(title, anime)
return quality
def _doSearch(self, search_params, search_mode='eponly', epcount=0, age=0):
return []
def _get_season_search_strings(self, episode):
return []
def _get_episode_search_strings(self, eb_obj, add_string=''):
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 = item.get('title')
if title:
title = u'' + title.replace(' ', '.')
url = item.get('link')
if url:
url = url.replace('&amp;', '&')
return title, url
def findSearchResults(self, show, episodes, search_mode, manualSearch=False):
self._checkAuth()
self.show = show
results = {}
itemList = []
searched_scene_season = None
for epObj in episodes:
# search cache for episode result
cacheResult = self.cache.searchCache(epObj, manualSearch)
if cacheResult:
if epObj.episode not in results:
results[epObj.episode] = cacheResult
else:
results[epObj.episode].extend(cacheResult)
# found result, search next episode
continue
# skip if season already searched
if len(episodes) > 1 and searched_scene_season == epObj.scene_season:
continue
# mark season searched for season pack searches so we can skip later on
searched_scene_season = epObj.scene_season
if len(episodes) > 1:
# get season search results
for curString in self._get_season_search_strings(epObj):
itemList += self._doSearch(curString, search_mode, len(episodes))
else:
# get single episode search results
for curString in self._get_episode_search_strings(epObj):
itemList += self._doSearch(curString, 'eponly', len(episodes))
# if we found what we needed already from cache then return results and exit
if len(results) == len(episodes):
return results
# sort list by quality
if len(itemList):
items = {}
itemsUnknown = []
for item in itemList:
quality = self.getQuality(item, anime=show.is_anime)
if quality == Quality.UNKNOWN:
itemsUnknown += [item]
else:
if quality not in items:
items[quality] = [item]
else:
items[quality].append(item)
itemList = list(itertools.chain(*[v for (k, v) in sorted(items.items(), reverse=True)]))
itemList += itemsUnknown if itemsUnknown else []
# filter results
cl = []
for item in itemList:
(title, url) = self._get_title_and_url(item)
# parse the file name
try:
2014-07-25 00:29:03 -04:00
myParser = NameParser(False, convert=True)
parse_result = myParser.parse(title)
except InvalidNameException:
logger.log(u"Unable to parse the filename " + title + " into a valid episode", logger.DEBUG)
continue
except InvalidShowException:
logger.log(u"Unable to parse the filename " + title + " into a valid show", logger.DEBUG)
continue
showObj = parse_result.show
quality = parse_result.quality
release_group = parse_result.release_group
2014-07-22 00:53:32 -04:00
version = parse_result.version
addCacheEntry = False
if not (showObj.air_by_date or showObj.sports):
if search_mode == 'sponly':
if len(parse_result.episode_numbers):
logger.log(
u"This is supposed to be a season pack search but the result " + title + " is not a valid season pack, skipping it",
logger.DEBUG)
addCacheEntry = True
if len(parse_result.episode_numbers) and (
parse_result.season_number not in set([ep.season for ep in episodes]) or not [ep for ep in episodes if
ep.scene_episode in parse_result.episode_numbers]):
logger.log(
u"The result " + title + " doesn't seem to be a valid episode that we are trying to snatch, ignoring",
logger.DEBUG)
addCacheEntry = True
else:
if not len(parse_result.episode_numbers) and parse_result.season_number and not [ep for ep in
episodes if
ep.season == parse_result.season_number and ep.episode in parse_result.episode_numbers]:
logger.log(
u"The result " + title + " doesn't seem to be a valid season that we are trying to snatch, ignoring",
logger.DEBUG)
addCacheEntry = True
elif len(parse_result.episode_numbers) and not [ep for ep in episodes if
ep.season == parse_result.season_number and ep.episode in parse_result.episode_numbers]:
logger.log(
u"The result " + title + " doesn't seem to be a valid episode that we are trying to snatch, ignoring",
logger.DEBUG)
addCacheEntry = True
if not addCacheEntry:
# we just use the existing info for normal searches
actual_season = parse_result.season_number
actual_episodes = parse_result.episode_numbers
else:
if not (parse_result.is_air_by_date):
logger.log(
u"This is supposed to be a date search but the result " + title + " didn't parse as one, skipping it",
logger.DEBUG)
addCacheEntry = True
else:
airdate = parse_result.air_date.toordinal()
myDB = db.DBConnection()
sql_results = myDB.select(
"SELECT season, episode FROM tv_episodes WHERE showid = ? AND airdate = ?",
[showObj.indexerid, airdate])
if len(sql_results) != 1:
logger.log(
u"Tried to look up the date for the episode " + title + " but the database didn't give proper results, skipping it",
logger.WARNING)
addCacheEntry = True
if not addCacheEntry:
actual_season = int(sql_results[0]["season"])
actual_episodes = [int(sql_results[0]["episode"])]
# add parsed result to cache for usage later on
if addCacheEntry:
logger.log(u"Adding item from search to cache: " + title, logger.DEBUG)
ci = self.cache._addCacheEntry(title, url, parse_result=parse_result)
if ci is not None:
cl.append(ci)
continue
# make sure we want the episode
wantEp = True
for epNo in actual_episodes:
if not showObj.wantEpisode(actual_season, epNo, quality, manualSearch):
wantEp = False
break
if not wantEp:
logger.log(
u"Ignoring result " + title + " because we don't want an episode that is " +
Quality.qualityStrings[
quality], logger.DEBUG)
continue
logger.log(u"Found result " + title + " at " + url, logger.DEBUG)
# make a result object
epObj = []
for curEp in actual_episodes:
epObj.append(showObj.getEpisode(actual_season, curEp))
result = self.getResult(epObj)
result.show = showObj
result.url = url
result.name = title
result.quality = quality
result.release_group = release_group
result.content = None
2014-07-22 00:53:32 -04:00
result.version = version
if len(epObj) == 1:
epNum = epObj[0].episode
logger.log(u"Single episode result.", logger.DEBUG)
elif len(epObj) > 1:
epNum = MULTI_EP_RESULT
logger.log(u"Separating multi-episode result to check for later - result contains episodes: " + str(
parse_result.episode_numbers), logger.DEBUG)
elif len(epObj) == 0:
epNum = SEASON_RESULT
logger.log(u"Separating full season result to check for later", logger.DEBUG)
if epNum not in results:
results[epNum] = [result]
else:
results[epNum].append(result)
# check if we have items to add to cache
if len(cl) > 0:
myDB = self.cache._getDB()
myDB.mass_action(cl)
return results
def findPropers(self, search_date=None):
results = self.cache.listPropers(search_date)
Fixed issues with editing/saving custom scene exceptions. Fixed charmap issues for anime show names. Fixed issues with display show page and epCat key errors. Fixed duplicate log messages for clearing provider caches. Fixed issues with email notifier ep names not properly being encoded to UTF-8. TVDB<->TVRAGE Indexer ID mapping is now performed on demand to be used when needed such as newznab providers can be searched with tvrage_id's and some will return tvrage_id's that later can be used to create show objects from for faster and more accurate name parsing, mapping is done via Trakt API calls. Added stop event signals to schedualed tasks, SR now waits indefinate till task has been fully stopped before completing a restart or shutdown event. NameParserCache is now persistent and stores 200 parsed results at any given time for quicker lookups and better performance, this helps maintain results between updates or shutdown/startup events. Black and White lists for anime now only get used for anime shows as intended, performance gain for non-anime shows that dont need to load these lists. Internal name cache now builds it self on demand when needed per show request plus checks if show is already in cache and if true exits routine to save time. Schedualer and QueueItems classes are now a sub-class of threading.Thread and a stop threading event signal has been added to each. If I forgot to list something it doesn't mean its not fixed so please test and report back if anything is wrong or has been corrected by this new release.
2014-07-14 22:00:53 -04:00
return [classes.Proper(x['name'], x['url'], datetime.datetime.fromtimestamp(x['time']), self.show) for x in
results]
2014-05-08 18:28:28 -04:00
def seedRatio(self):
'''
Provider should override this value if custom seed ratio enabled
It should return the value of the provider seed ratio
'''
return ''
class NZBProvider(GenericProvider):
def __init__(self, name):
GenericProvider.__init__(self, name)
self.providerType = GenericProvider.NZB
Fixed issues with editing/saving custom scene exceptions. Fixed charmap issues for anime show names. Fixed issues with display show page and epCat key errors. Fixed duplicate log messages for clearing provider caches. Fixed issues with email notifier ep names not properly being encoded to UTF-8. TVDB<->TVRAGE Indexer ID mapping is now performed on demand to be used when needed such as newznab providers can be searched with tvrage_id's and some will return tvrage_id's that later can be used to create show objects from for faster and more accurate name parsing, mapping is done via Trakt API calls. Added stop event signals to schedualed tasks, SR now waits indefinate till task has been fully stopped before completing a restart or shutdown event. NameParserCache is now persistent and stores 200 parsed results at any given time for quicker lookups and better performance, this helps maintain results between updates or shutdown/startup events. Black and White lists for anime now only get used for anime shows as intended, performance gain for non-anime shows that dont need to load these lists. Internal name cache now builds it self on demand when needed per show request plus checks if show is already in cache and if true exits routine to save time. Schedualer and QueueItems classes are now a sub-class of threading.Thread and a stop threading event signal has been added to each. If I forgot to list something it doesn't mean its not fixed so please test and report back if anything is wrong or has been corrected by this new release.
2014-07-14 22:00:53 -04:00
class TorrentProvider(GenericProvider):
def __init__(self, name):
GenericProvider.__init__(self, name)
2014-07-25 00:29:03 -04:00
self.providerType = GenericProvider.TORRENT