github/nzbToMedia
1
0
Fork 0
mirror of https://github.com/clinton-hall/nzbToMedia.git synced 2025-08-14 18:47:09 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Updates vendored subliminal to 2.1.0

Browse source 
Updates rarfile to 3.1
Updates stevedore to 3.5.0
Updates appdirs to 1.4.4
Updates click to 8.1.3
Updates decorator to 5.1.1
Updates dogpile.cache to 1.1.8
Updates pbr to 5.11.0
Updates pysrt to 1.1.2
Updates pytz to 2022.6
Adds importlib-metadata version 3.1.1
Adds typing-extensions version 4.1.1
Adds zipp version 3.11.0
This commit is contained in:
Labrys of Knossos 2022-11-29 00:08:39 -05:00
commit f05b09f349
694 changed files with 16621 additions and 11056 deletions
Download patch file Download diff file Expand all files Collapse all files

136
libs/common/subliminal/providers/addic7ed.py
View file

@ -7,20 +7,22 @@ from guessit import guessit
from requests import Session
from . import ParserBeautifulSoup, Provider
from .. import __short_version__
from ..cache import SHOW_EXPIRATION_TIME, region
from ..exceptions import AuthenticationError, ConfigurationError, DownloadLimitExceeded, TooManyRequests
from ..score import get_equivalent_release_groups
from ..subtitle import Subtitle, fix_line_ending, guess_matches
from ..utils import sanitize, sanitize_release_group
from ..exceptions import AuthenticationError, ConfigurationError, DownloadLimitExceeded
from ..matches import guess_matches
from ..subtitle import Subtitle, fix_line_ending
from ..utils import sanitize
from ..video import Episode
logger = logging.getLogger(__name__)
language_converters.register('addic7ed = subliminal.converters.addic7ed:Addic7edConverter')
# Series cell matching regex
show_cells_re = re.compile(b'<td class="version">.*?</td>', re.DOTALL)
#: Series header parsing regex
series_year_re = re.compile(r'^(?P<series>[ \w\'.:(),&!?-]+?)(?: \((?P<year>\d{4})\))?$')
series_year_re = re.compile(r'^(?P<series>[ \w\'.:(),*&!?-]+?)(?: \((?P<year>\d{4})\))?$')
class Addic7edSubtitle(Subtitle):
@ -29,7 +31,7 @@ class Addic7edSubtitle(Subtitle):
def __init__(self, language, hearing_impaired, page_link, series, season, episode, title, year, version,
download_link):
super(Addic7edSubtitle, self).__init__(language, hearing_impaired, page_link)
super(Addic7edSubtitle, self).__init__(language, hearing_impaired=hearing_impaired, page_link=page_link)
self.series = series
self.season = season
self.episode = episode
@ -42,37 +44,31 @@ class Addic7edSubtitle(Subtitle):
def id(self):
return self.download_link
def get_matches(self, video):
matches = set()
@property
def info(self):
return '{series}{yopen}{year}{yclose} s{season:02d}e{episode:02d}{topen}{title}{tclose}{version}'.format(
series=self.series, season=self.season, episode=self.episode, title=self.title, year=self.year or '',
version=self.version, yopen=' (' if self.year else '', yclose=')' if self.year else '',
topen=' - ' if self.title else '', tclose=' - ' if self.version else ''
)
def get_matches(self, video):
# series name
matches = guess_matches(video, {
'title': self.series,
'season': self.season,
'episode': self.episode,
'episode_title': self.title,
'year': self.year,
'release_group': self.version,
})
# series
if video.series and sanitize(self.series) == sanitize(video.series):
matches.add('series')
# season
if video.season and self.season == video.season:
matches.add('season')
# episode
if video.episode and self.episode == video.episode:
matches.add('episode')
# title
if video.title and sanitize(self.title) == sanitize(video.title):
matches.add('title')
# year
if video.original_series and self.year is None or video.year and video.year == self.year:
matches.add('year')
# release_group
if (video.release_group and self.version and
any(r in sanitize_release_group(self.version)
for r in get_equivalent_release_groups(sanitize_release_group(video.release_group)))):
matches.add('release_group')
# resolution
if video.resolution and self.version and video.resolution in self.version.lower():
matches.add('resolution')
# format
if video.format and self.version and video.format.lower() in self.version.lower():
matches.add('format')
# other properties
matches |= guess_matches(video, guessit(self.version), partial=True)
if self.version:
matches |= guess_matches(video, guessit(self.version, {'type': 'episode'}), partial=True)
return matches
@ -86,21 +82,23 @@ class Addic7edProvider(Provider):
]}
video_types = (Episode,)
server_url = 'http://www.addic7ed.com/'
subtitle_class = Addic7edSubtitle
def __init__(self, username=None, password=None):
if username is not None and password is None or username is None and password is not None:
if any((username, password)) and not all((username, password)):
raise ConfigurationError('Username and password must be specified')
self.username = username
self.password = password
self.logged_in = False
self.session = None
def initialize(self):
self.session = Session()
self.session.headers['User-Agent'] = 'Subliminal/%s' % __short_version__
self.session.headers['User-Agent'] = self.user_agent
# login
if self.username is not None and self.password is not None:
if self.username and self.password:
logger.info('Logging in')
data = {'username': self.username, 'password': self.password, 'Submit': 'Log in'}
r = self.session.post(self.server_url + 'dologin.php', data, allow_redirects=False, timeout=10)
@ -134,7 +132,16 @@ class Addic7edProvider(Provider):
logger.info('Getting show ids')
r = self.session.get(self.server_url + 'shows.php', timeout=10)
r.raise_for_status()
soup = ParserBeautifulSoup(r.content, ['lxml', 'html.parser'])
# LXML parser seems to fail when parsing Addic7ed.com HTML markup.
# Last known version to work properly is 3.6.4 (next version, 3.7.0, fails)
# Assuming the site's markup is bad, and stripping it down to only contain what's needed.
show_cells = re.findall(show_cells_re, r.content)
if show_cells:
soup = ParserBeautifulSoup(b''.join(show_cells), ['lxml', 'html.parser'])
else:
# If RegEx fails, fall back to original r.content and use 'html.parser'
soup = ParserBeautifulSoup(r.content, ['html.parser'])
# populate the show ids
show_ids = {}
@ -164,10 +171,8 @@ class Addic7edProvider(Provider):
# make the search
logger.info('Searching show ids with %r', params)
r = self.session.get(self.server_url + 'search.php', params=params, timeout=10)
r = self.session.get(self.server_url + 'srch.php', params=params, timeout=10)
r.raise_for_status()
if r.status_code == 304:
raise TooManyRequests()
soup = ParserBeautifulSoup(r.content, ['lxml', 'html.parser'])
# get the suggestion
@ -218,24 +223,23 @@ class Addic7edProvider(Provider):
# search as last resort
if not show_id:
logger.warning('Series not found in show ids')
logger.warning('Series %s not found in show ids', series)
show_id = self._search_show_id(series)
return show_id
def query(self, series, season, year=None, country=None):
# get the show id
show_id = self.get_show_id(series, year, country)
if show_id is None:
logger.error('No show id found for %r (%r)', series, {'year': year, 'country': country})
return []
def query(self, show_id, series, season, year=None, country=None):
# get the page of the season of the show
logger.info('Getting the page of show id %d, season %d', show_id, season)
r = self.session.get(self.server_url + 'show/%d' % show_id, params={'season': season}, timeout=10)
r = self.session.get(self.server_url + 'show/%d' % show_id, params={'season': season}, timeout=10)
r.raise_for_status()
if r.status_code == 304:
raise TooManyRequests()
if not r.content:
# Provider returns a status of 304 Not Modified with an empty content
# raise_for_status won't raise exception for that status code
logger.debug('No data returned from provider')
return []
soup = ParserBeautifulSoup(r.content, ['lxml', 'html.parser'])
# loop over subtitle rows
@ -262,16 +266,32 @@ class Addic7edProvider(Provider):
version = cells[4].text
download_link = cells[9].a['href'][1:]
subtitle = Addic7edSubtitle(language, hearing_impaired, page_link, series, season, episode, title, year,
version, download_link)
subtitle = self.subtitle_class(language, hearing_impaired, page_link, series, season, episode, title, year,
version, download_link)
logger.debug('Found subtitle %r', subtitle)
subtitles.append(subtitle)
return subtitles
def list_subtitles(self, video, languages):
return [s for s in self.query(video.series, video.season, video.year)
if s.language in languages and s.episode == video.episode]
# lookup show_id
titles = [video.series] + video.alternative_series
show_id = None
for title in titles:
show_id = self.get_show_id(title, video.year)
if show_id is not None:
break
# query for subtitles with the show_id
if show_id is not None:
subtitles = [s for s in self.query(show_id, title, video.season, video.year)
if s.language in languages and s.episode == video.episode]
if subtitles:
return subtitles
else:
logger.error('No show id found for %r (%r)', video.series, {'year': video.year})
return []
def download_subtitle(self, subtitle):
# download the subtitle
@ -280,6 +300,12 @@ class Addic7edProvider(Provider):
timeout=10)
r.raise_for_status()
if not r.content:
# Provider returns a status of 304 Not Modified with an empty content
# raise_for_status won't raise exception for that status code
logger.debug('Unable to download subtitle. No data returned from provider')
return
# detect download limit exceeded
if r.headers['Content-Type'] == 'text/html':
raise DownloadLimitExceeded