2014-03-10 01:18:05 -04:00
|
|
|
# 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.
|
2014-03-10 01:18:05 -04:00
|
|
|
#
|
2014-05-23 08:37:22 -04:00
|
|
|
# SickRage is free software: you can redistribute it and/or modify
|
2014-03-10 01:18:05 -04:00
|
|
|
# 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,
|
2014-03-10 01:18:05 -04:00
|
|
|
# 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/>.
|
2014-03-10 01:18:05 -04:00
|
|
|
import fnmatch
|
|
|
|
import os
|
|
|
|
|
|
|
|
import re
|
|
|
|
import datetime
|
|
|
|
|
|
|
|
import sickbeard
|
2014-05-26 02:29:22 -04:00
|
|
|
from sickbeard import common
|
2014-03-10 01:18:05 -04:00
|
|
|
from sickbeard.helpers import sanitizeSceneName
|
|
|
|
from sickbeard.scene_exceptions import get_scene_exceptions
|
|
|
|
from sickbeard import logger
|
|
|
|
from sickbeard import db
|
|
|
|
from sickbeard import encodingKludge as ek
|
|
|
|
from name_parser.parser import NameParser, InvalidNameException
|
|
|
|
from lib.unidecode import unidecode
|
2014-05-28 17:13:29 -04:00
|
|
|
from sickbeard.blackandwhitelist import BlackAndWhiteList
|
2014-03-10 01:18:05 -04:00
|
|
|
|
2014-05-12 09:24:45 -04:00
|
|
|
resultFilters = ["sub(bed|ed|pack|s)", "(dk|fin|heb|kor|nor|nordic|pl|swe)sub(bed|ed|s)?",
|
2014-03-25 01:57:24 -04:00
|
|
|
"(dir|sample|sub|nfo)fix", "sample", "(dvd)?extras",
|
2014-03-10 01:18:05 -04:00
|
|
|
"dub(bed)?"]
|
|
|
|
|
|
|
|
def filterBadReleases(name):
|
|
|
|
"""
|
|
|
|
Filters out non-english and just all-around stupid releases by comparing them
|
|
|
|
to the resultFilters contents.
|
|
|
|
|
|
|
|
name: the release name to check
|
|
|
|
|
|
|
|
Returns: True if the release name is OK, False if it's bad.
|
|
|
|
"""
|
|
|
|
|
|
|
|
try:
|
|
|
|
fp = NameParser()
|
2014-05-02 06:09:17 -04:00
|
|
|
parse_result = fp.parse(name)
|
2014-03-10 01:18:05 -04:00
|
|
|
except InvalidNameException:
|
|
|
|
logger.log(u"Unable to parse the filename " + name + " into a valid episode", logger.WARNING)
|
|
|
|
return False
|
|
|
|
|
|
|
|
# if any of the bad strings are in the name then say no
|
2014-04-26 02:26:53 -04:00
|
|
|
if sickbeard.IGNORE_WORDS:
|
2014-04-26 07:54:33 -04:00
|
|
|
resultFilters.extend(sickbeard.IGNORE_WORDS.split(','))
|
2014-04-26 02:33:02 -04:00
|
|
|
filters = [re.compile('(^|[\W_])%s($|[\W_])' % filter.strip(), re.I) for filter in resultFilters]
|
2014-04-26 02:26:53 -04:00
|
|
|
for regfilter in filters:
|
|
|
|
if regfilter.search(name):
|
2014-05-28 17:13:29 -04:00
|
|
|
logger.log(u"Invalid scene release: " + name + " contains pattern: " + regfilter.pattern + ", ignoring it",
|
|
|
|
logger.DEBUG)
|
2014-03-10 01:18:05 -04:00
|
|
|
return False
|
|
|
|
|
|
|
|
return True
|
|
|
|
|
2014-03-25 01:57:24 -04:00
|
|
|
|
2014-03-10 01:18:05 -04:00
|
|
|
def sceneToNormalShowNames(name):
|
|
|
|
"""
|
2014-04-26 02:26:53 -04:00
|
|
|
Takes a show name from a scene dirname and converts it to a more "human-readable" format.
|
2014-03-10 01:18:05 -04:00
|
|
|
|
|
|
|
name: The show name to convert
|
|
|
|
|
|
|
|
Returns: a list of all the possible "normal" names
|
|
|
|
"""
|
|
|
|
|
|
|
|
if not name:
|
|
|
|
return []
|
|
|
|
|
|
|
|
name_list = [name]
|
2014-03-25 01:57:24 -04:00
|
|
|
|
2014-03-10 01:18:05 -04:00
|
|
|
# use both and and &
|
|
|
|
new_name = re.sub('(?i)([\. ])and([\. ])', '\\1&\\2', name, re.I)
|
|
|
|
if new_name not in name_list:
|
|
|
|
name_list.append(new_name)
|
|
|
|
|
|
|
|
results = []
|
|
|
|
|
|
|
|
for cur_name in name_list:
|
|
|
|
# add brackets around the year
|
|
|
|
results.append(re.sub('(\D)(\d{4})$', '\\1(\\2)', cur_name))
|
2014-03-25 01:57:24 -04:00
|
|
|
|
2014-03-10 01:18:05 -04:00
|
|
|
# add brackets around the country
|
2014-05-26 02:29:22 -04:00
|
|
|
country_match_str = '|'.join(common.countryList.values())
|
2014-03-10 01:18:05 -04:00
|
|
|
results.append(re.sub('(?i)([. _-])(' + country_match_str + ')$', '\\1(\\2)', cur_name))
|
|
|
|
|
|
|
|
results += name_list
|
|
|
|
|
|
|
|
return list(set(results))
|
|
|
|
|
|
|
|
|
2014-05-26 02:29:22 -04:00
|
|
|
def makeSceneShowSearchStrings(show, season=-1):
|
|
|
|
showNames = allPossibleShowNames(show, season=season)
|
2014-03-10 01:18:05 -04:00
|
|
|
|
|
|
|
# scenify the names
|
|
|
|
return map(sanitizeSceneName, showNames)
|
|
|
|
|
|
|
|
|
2014-04-30 09:49:50 -04:00
|
|
|
def makeSceneSeasonSearchString(show, ep_obj, extraSearchType=None):
|
2014-03-10 01:18:05 -04:00
|
|
|
|
2014-05-03 23:16:26 -04:00
|
|
|
if show.air_by_date or show.sports:
|
2014-04-28 05:15:29 -04:00
|
|
|
numseasons = 0
|
2014-03-25 01:57:24 -04:00
|
|
|
|
2014-04-28 05:15:29 -04:00
|
|
|
# the search string for air by date shows is just
|
2014-05-26 02:29:22 -04:00
|
|
|
seasonStrings = [str(ep_obj.airdate).split('-')[0]]
|
|
|
|
elif show.is_anime:
|
|
|
|
numseasons = 0
|
|
|
|
seasonEps = show.getAllEpisodes(ep_obj.season)
|
|
|
|
|
|
|
|
# get show qualities
|
|
|
|
anyQualities, bestQualities = common.Quality.splitQuality(show.quality)
|
|
|
|
|
|
|
|
# compile a list of all the episode numbers we need in this 'season'
|
2014-05-03 23:16:26 -04:00
|
|
|
seasonStrings = []
|
2014-05-26 02:29:22 -04:00
|
|
|
for episode in seasonEps:
|
|
|
|
|
|
|
|
# get quality of the episode
|
|
|
|
curCompositeStatus = episode.status
|
|
|
|
curStatus, curQuality = common.Quality.splitCompositeStatus(curCompositeStatus)
|
|
|
|
|
|
|
|
if bestQualities:
|
|
|
|
highestBestQuality = max(bestQualities)
|
|
|
|
else:
|
|
|
|
highestBestQuality = 0
|
|
|
|
|
|
|
|
# if we need a better one then add it to the list of episodes to fetch
|
|
|
|
if (curStatus in (
|
2014-05-28 17:13:29 -04:00
|
|
|
common.DOWNLOADED,
|
|
|
|
common.SNATCHED) and curQuality < highestBestQuality) or curStatus == common.WANTED:
|
2014-05-26 02:29:22 -04:00
|
|
|
ab_number = episode.scene_absolute_number
|
|
|
|
if ab_number > 0:
|
|
|
|
seasonStrings.append("%d" % ab_number)
|
|
|
|
|
2014-03-10 01:18:05 -04:00
|
|
|
else:
|
2014-06-21 18:46:59 -04:00
|
|
|
myDB = db.DBConnection()
|
|
|
|
numseasonsSQlResult = myDB.select(
|
|
|
|
"SELECT COUNT(DISTINCT season) as numseasons FROM tv_episodes WHERE showid = ? and season != 0",
|
|
|
|
[show.indexerid])
|
2014-03-10 01:18:05 -04:00
|
|
|
|
2014-05-26 02:29:22 -04:00
|
|
|
numseasons = int(numseasonsSQlResult[0][0])
|
|
|
|
seasonStrings = ["S%02d" % int(ep_obj.scene_season)]
|
2014-03-10 01:18:05 -04:00
|
|
|
|
2014-05-28 17:13:29 -04:00
|
|
|
bwl = BlackAndWhiteList(show.indexerid)
|
2014-05-26 02:29:22 -04:00
|
|
|
showNames = set(makeSceneShowSearchStrings(show, ep_obj.scene_season))
|
2014-03-10 01:18:05 -04:00
|
|
|
|
|
|
|
toReturn = []
|
|
|
|
|
|
|
|
# search each show name
|
|
|
|
for curShow in showNames:
|
|
|
|
# most providers all work the same way
|
|
|
|
if not extraSearchType:
|
|
|
|
# if there's only one season then we can just use the show name straight up
|
|
|
|
if numseasons == 1:
|
|
|
|
toReturn.append(curShow)
|
|
|
|
# for providers that don't allow multiple searches in one request we only search for Sxx style stuff
|
|
|
|
else:
|
|
|
|
for cur_season in seasonStrings:
|
2014-05-28 17:13:29 -04:00
|
|
|
if len(bwl.whiteList) > 0:
|
|
|
|
for keyword in bwl.whiteList:
|
|
|
|
toReturn.append(keyword + '.' + curShow+ "." + cur_season)
|
|
|
|
else:
|
|
|
|
toReturn.append(curShow + "." + cur_season)
|
|
|
|
|
2014-03-25 01:57:24 -04:00
|
|
|
|
2014-03-10 01:18:05 -04:00
|
|
|
return toReturn
|
|
|
|
|
|
|
|
|
2014-04-30 09:49:50 -04:00
|
|
|
def makeSceneSearchString(show, ep_obj):
|
2014-06-21 18:46:59 -04:00
|
|
|
myDB = db.DBConnection()
|
|
|
|
numseasonsSQlResult = myDB.select(
|
|
|
|
"SELECT COUNT(DISTINCT season) as numseasons FROM tv_episodes WHERE showid = ? and season != 0",
|
|
|
|
[show.indexerid])
|
2014-03-10 01:18:05 -04:00
|
|
|
numseasons = int(numseasonsSQlResult[0][0])
|
|
|
|
|
|
|
|
# see if we should use dates instead of episodes
|
2014-05-26 02:29:22 -04:00
|
|
|
if (show.air_by_date or show.sports) and ep_obj.airdate != datetime.date.fromordinal(1):
|
2014-05-03 23:16:26 -04:00
|
|
|
epStrings = [str(ep_obj.airdate)]
|
2014-05-26 02:29:22 -04:00
|
|
|
elif show.is_anime:
|
|
|
|
epStrings = ["%i" % int(ep_obj.scene_absolute_number)]
|
2014-03-10 01:18:05 -04:00
|
|
|
else:
|
2014-04-30 09:49:50 -04:00
|
|
|
epStrings = ["S%02iE%02i" % (int(ep_obj.scene_season), int(ep_obj.scene_episode)),
|
|
|
|
"%ix%02i" % (int(ep_obj.scene_season), int(ep_obj.scene_episode))]
|
2014-03-10 01:18:05 -04:00
|
|
|
|
|
|
|
# for single-season shows just search for the show name -- if total ep count (exclude s0) is less than 11
|
|
|
|
# due to the amount of qualities and releases, it is easy to go over the 50 result limit on rss feeds otherwise
|
2014-05-26 02:29:22 -04:00
|
|
|
if numseasons == 1 and not ep_obj.show.is_anime:
|
2014-03-10 01:18:05 -04:00
|
|
|
epStrings = ['']
|
|
|
|
|
2014-05-28 17:13:29 -04:00
|
|
|
bwl = BlackAndWhiteList(ep_obj.show.indexerid)
|
2014-05-26 02:29:22 -04:00
|
|
|
showNames = set(makeSceneShowSearchStrings(show, ep_obj.scene_season))
|
2014-03-10 01:18:05 -04:00
|
|
|
|
|
|
|
toReturn = []
|
|
|
|
|
|
|
|
for curShow in showNames:
|
|
|
|
for curEpString in epStrings:
|
2014-05-28 17:13:29 -04:00
|
|
|
if len(bwl.whiteList) > 0:
|
|
|
|
for keyword in bwl.whiteList:
|
|
|
|
toReturn.append(keyword + '.' + curShow + '.' + curEpString)
|
|
|
|
else:
|
|
|
|
toReturn.append(curShow + '.' + curEpString)
|
2014-03-10 01:18:05 -04:00
|
|
|
|
|
|
|
return toReturn
|
|
|
|
|
2014-03-25 01:57:24 -04:00
|
|
|
|
2014-05-26 02:29:22 -04:00
|
|
|
def isGoodResult(name, show, log=True, season=-1):
|
2014-03-10 01:18:05 -04:00
|
|
|
"""
|
|
|
|
Use an automatically-created regex to make sure the result actually is the show it claims to be
|
|
|
|
"""
|
|
|
|
|
2014-05-26 02:29:22 -04:00
|
|
|
all_show_names = allPossibleShowNames(show, season=season)
|
2014-03-10 01:18:05 -04:00
|
|
|
showNames = map(sanitizeSceneName, all_show_names) + all_show_names
|
2014-03-25 01:57:24 -04:00
|
|
|
showNames += map(unidecode, all_show_names)
|
2014-03-10 01:18:05 -04:00
|
|
|
|
|
|
|
for curName in set(showNames):
|
2014-05-26 02:29:22 -04:00
|
|
|
if not show.is_anime:
|
|
|
|
escaped_name = re.sub('\\\\[\\s.-]', '\W+', re.escape(curName))
|
|
|
|
if show.startyear:
|
|
|
|
escaped_name += "(?:\W+" + str(show.startyear) + ")?"
|
|
|
|
curRegex = '^' + escaped_name + '\W+(?:(?:S\d[\dE._ -])|(?:\d\d?x)|(?:\d{4}\W\d\d\W\d\d)|(?:(?:part|pt)[\._ -]?(\d|[ivx]))|Season\W+\d+\W+|E\d+\W+|(?:\d{1,3}.+\d{1,}[a-zA-Z]{2}\W+[a-zA-Z]{3,}\W+\d{4}.+))'
|
|
|
|
else:
|
|
|
|
escaped_name = re.sub('\\\\[\\s.-]', '[\W_]+', re.escape(curName))
|
|
|
|
# FIXME: find a "automatically-created" regex for anime releases # test at http://regexr.com?2uon3
|
|
|
|
curRegex = '^((\[.*?\])|(\d+[\.-]))*[ _\.]*' + escaped_name + '(([ ._-]+\d+)|([ ._-]+s\d{2})).*'
|
|
|
|
|
2014-03-10 01:18:05 -04:00
|
|
|
if log:
|
|
|
|
logger.log(u"Checking if show " + name + " matches " + curRegex, logger.DEBUG)
|
|
|
|
|
|
|
|
match = re.search(curRegex, name, re.I)
|
|
|
|
if match:
|
|
|
|
logger.log(u"Matched " + curRegex + " to " + name, logger.DEBUG)
|
|
|
|
return True
|
|
|
|
|
|
|
|
if log:
|
2014-05-28 17:13:29 -04:00
|
|
|
logger.log(
|
|
|
|
u"Provider gave result " + name + " but that doesn't seem like a valid result for " + show.name + " so I'm ignoring it")
|
2014-03-10 01:18:05 -04:00
|
|
|
return False
|
|
|
|
|
2014-03-25 01:57:24 -04:00
|
|
|
|
2014-05-26 02:29:22 -04:00
|
|
|
def allPossibleShowNames(show, season=-1):
|
2014-03-10 01:18:05 -04:00
|
|
|
"""
|
|
|
|
Figures out every possible variation of the name for a particular show. Includes TVDB name, TVRage name,
|
|
|
|
country codes on the end, eg. "Show Name (AU)", and any scene exception names.
|
|
|
|
|
|
|
|
show: a TVShow object that we should get the names of
|
|
|
|
|
|
|
|
Returns: a list of all the possible show names
|
|
|
|
"""
|
|
|
|
|
2014-05-26 02:29:22 -04:00
|
|
|
showNames = get_scene_exceptions(show.indexerid, season=season)
|
|
|
|
if not showNames: # if we dont have any season specific exceptions fallback to generic exceptions
|
|
|
|
season = -1
|
|
|
|
showNames = get_scene_exceptions(show.indexerid, season=season)
|
|
|
|
|
|
|
|
if season in [-1, 1]:
|
|
|
|
showNames.append(show.name)
|
2014-03-10 01:18:05 -04:00
|
|
|
|
2014-05-26 02:29:22 -04:00
|
|
|
if not show.is_anime:
|
2014-07-03 16:44:34 -04:00
|
|
|
newShowNames = []
|
|
|
|
country_list = common.countryList
|
|
|
|
country_list.update(dict(zip(common.countryList.values(), common.countryList.keys())))
|
2014-05-26 02:29:22 -04:00
|
|
|
for curName in set(showNames):
|
|
|
|
if not curName:
|
|
|
|
continue
|
2014-07-03 16:44:34 -04:00
|
|
|
|
|
|
|
# if we have "Show Name Australia" or "Show Name (Australia)" this will add "Show Name (AU)" for
|
|
|
|
# any countries defined in common.countryList
|
|
|
|
# (and vice versa)
|
2014-05-26 02:29:22 -04:00
|
|
|
for curCountry in country_list:
|
|
|
|
if curName.endswith(' ' + curCountry):
|
|
|
|
newShowNames.append(curName.replace(' ' + curCountry, ' (' + country_list[curCountry] + ')'))
|
|
|
|
elif curName.endswith(' (' + curCountry + ')'):
|
|
|
|
newShowNames.append(curName.replace(' (' + curCountry + ')', ' (' + country_list[curCountry] + ')'))
|
|
|
|
|
2014-07-03 16:44:34 -04:00
|
|
|
# if we have "Show Name (2013)" this will strip the (2013) show year from the show name
|
|
|
|
#newShowNames.append(re.sub('\(\d{4}\)','',curName))
|
|
|
|
|
2014-05-26 02:29:22 -04:00
|
|
|
showNames += newShowNames
|
2014-03-10 01:18:05 -04:00
|
|
|
|
|
|
|
return showNames
|
|
|
|
|
|
|
|
def determineReleaseName(dir_name=None, nzb_name=None):
|
|
|
|
"""Determine a release name from an nzb and/or folder name"""
|
|
|
|
|
|
|
|
if nzb_name is not None:
|
|
|
|
logger.log(u"Using nzb_name for release name.")
|
|
|
|
return nzb_name.rpartition('.')[0]
|
|
|
|
|
|
|
|
if dir_name is None:
|
|
|
|
return None
|
|
|
|
|
|
|
|
# try to get the release name from nzb/nfo
|
|
|
|
file_types = ["*.nzb", "*.nfo"]
|
|
|
|
|
|
|
|
for search in file_types:
|
|
|
|
|
|
|
|
reg_expr = re.compile(fnmatch.translate(search), re.IGNORECASE)
|
2014-03-25 01:57:24 -04:00
|
|
|
files = [file_name for file_name in ek.ek(os.listdir, dir_name) if
|
|
|
|
ek.ek(os.path.isfile, ek.ek(os.path.join, dir_name, file_name))]
|
2014-03-10 01:18:05 -04:00
|
|
|
results = filter(reg_expr.search, files)
|
|
|
|
|
|
|
|
if len(results) == 1:
|
|
|
|
found_file = ek.ek(os.path.basename, results[0])
|
|
|
|
found_file = found_file.rpartition('.')[0]
|
|
|
|
if filterBadReleases(found_file):
|
|
|
|
logger.log(u"Release name (" + found_file + ") found from file (" + results[0] + ")")
|
|
|
|
return found_file.rpartition('.')[0]
|
|
|
|
|
|
|
|
# If that fails, we try the folder
|
|
|
|
folder = ek.ek(os.path.basename, dir_name)
|
|
|
|
if filterBadReleases(folder):
|
|
|
|
# NOTE: Multiple failed downloads will change the folder name.
|
|
|
|
# (e.g., appending #s)
|
|
|
|
# Should we handle that?
|
|
|
|
logger.log(u"Folder name (" + folder + ") appears to be a valid release name. Using it.")
|
|
|
|
return folder
|
|
|
|
|
|
|
|
return None
|