Add subsunacs.net and subs.sab.bz providers

pull/292/head
e01 6 years ago
parent 5ba92b2142
commit 76d5be0e77

@ -0,0 +1,156 @@
# -*- coding: utf-8 -*-
import logging
import re
import io
import os
from rarfile import RarFile, is_rarfile
from zipfile import ZipFile, is_zipfile
from babelfish import Language
from requests import Session
from guessit import guessit
from . import ParserBeautifulSoup, Provider
from ..utils import sanitize, sanitize_release_group
from ..subtitle import Subtitle, fix_line_ending, guess_matches
from ..video import Episode
from ..video import Movie
logger = logging.getLogger(__name__)
class SubsSabBzSubtitle(Subtitle):
"""SubsSabBz Subtitle."""
provider_name = 'subssabbz'
def __init__(self, langauge, filename, type):
super(SubsSabBzSubtitle, self).__init__(langauge)
self.langauge = langauge
self.filename = filename
self.type = type
@property
def id(self):
return self.filename
def get_matches(self, video):
matches = set()
video_filename = video.name
video_filename = os.path.basename(video_filename)
video_filename, _ = os.path.splitext(video_filename)
video_filename = sanitize_release_group(video_filename)
subtitle_filename = self.filename
subtitle_filename = os.path.basename(subtitle_filename)
subtitle_filename, _ = os.path.splitext(subtitle_filename)
subtitle_filename = sanitize_release_group(subtitle_filename)
if video_filename == subtitle_filename:
matches.add('hash')
matches |= guess_matches(video, guessit(self.filename, {'type': self.type}))
matches.add(id(self))
return matches
class SubsSabBzProvider(Provider):
"""SubsSabBz Provider."""
languages = {Language('por', 'BR')} | {Language(l) for l in [
'bul', 'eng'
]}
def initialize(self):
self.session = Session()
self.session.headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36'
self.session.headers["Accept"] = "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"
self.session.headers["Accept-Language"] = "en-US,en;q=0.5"
self.session.headers["Accept-Encoding"] = "gzip, deflate, br"
self.session.headers["DNT"] = "1"
self.session.headers["Connection"] = "keep-alive"
self.session.headers["Upgrade-Insecure-Requests"] = "1"
self.session.headers["Cache-Control"] = "max-age=0"
def terminate(self):
self.session.close()
def query(self, language, video):
subtitles = []
isEpisode = isinstance(video, Episode)
params = {
'act': 'search',
'movie': '',
'select-language': '2',
'upldr': '',
'yr': '',
'release': ''
}
if isEpisode:
params['movie'] = "%s %02d %02d" % (sanitize(video.series), video.season, video.episode)
else:
params['yr'] = video.year
params['movie'] = (video.title)
if language == 'en' or language == 'eng':
params['select-language'] = 1
logger.info('Searching subtitle %r', params)
response = self.session.post('http://subs.sab.bz/index.php?', params=params, allow_redirects=False, timeout=10, headers={
'Referer': 'http://subs.sab.bz/',
})
response.raise_for_status()
if response.status_code != 200:
logger.debug('No subtitles found')
return subtitles
soup = ParserBeautifulSoup(response.content, ['html.parser'])
rows = soup.findAll('tr', {'class': 'subs-row'})
# Search on first 10 rows only
for row in rows[:10]:
a_element_wrapper = row.find('td', { 'class': 'c2field' })
if a_element_wrapper:
element = row.find('a')
if element:
link = element.get('href')
logger.info('Found subtitle link %r', link)
subtitles = subtitles + self.download_archive_and_add_subtitle_files(link, language, video)
return subtitles
def list_subtitles(self, video, languages):
return [s for l in languages for s in self.query(l, video)]
def download_subtitle(self, subtitle):
pass
def process_archive_subtitle_files(self, archiveStream, language, video):
subtitles = []
type = 'episode' if isinstance(video, Episode) else 'movie'
for f in archiveStream.infolist():
if f.filename.lower().endswith(('.srt', '.sub')):
logger.info('Found subtitle file %r', f.filename)
subtitle = SubsSabBzSubtitle(language, f.filename, type)
subtitle.content = archiveStream.read(f)
subtitles.append(subtitle)
return subtitles
def download_archive_and_add_subtitle_files(self, link, language, video ):
logger.info('Downloading subtitle %r', link)
request = self.session.get(link, headers={
'Referer': 'http://subs.sab.bz/index.php?'
})
request.raise_for_status()
archive_stream = io.BytesIO(request.content)
if is_rarfile(archive_stream):
return self.process_archive_subtitle_files( RarFile(archive_stream), language, video )
elif is_zipfile(archive_stream):
return self.process_archive_subtitle_files( ZipFile(archive_stream), language, video )
else:
raise ValueError('Not a valid archive')

@ -0,0 +1,158 @@
# -*- coding: utf-8 -*-
import logging
import re
import io
import os
from rarfile import RarFile, is_rarfile
from zipfile import ZipFile, is_zipfile
from babelfish import Language
from requests import Session
from guessit import guessit
from . import ParserBeautifulSoup, Provider
from ..utils import sanitize, sanitize_release_group
from ..subtitle import Subtitle, fix_line_ending, guess_matches
from ..video import Episode
from ..video import Movie
logger = logging.getLogger(__name__)
class SubsUnacsSubtitle(Subtitle):
"""SubsUnacs Subtitle."""
provider_name = 'subsunacs'
def __init__(self, langauge, filename, type):
super(SubsUnacsSubtitle, self).__init__(langauge)
self.langauge = langauge
self.filename = filename
self.type = type
@property
def id(self):
return self.filename
def get_matches(self, video):
matches = set()
video_filename = video.name
video_filename = os.path.basename(video_filename)
video_filename, _ = os.path.splitext(video_filename)
video_filename = sanitize_release_group(video_filename)
subtitle_filename = self.filename
subtitle_filename = os.path.basename(subtitle_filename)
subtitle_filename, _ = os.path.splitext(subtitle_filename)
subtitle_filename = sanitize_release_group(subtitle_filename)
if video_filename == subtitle_filename:
matches.add('hash')
matches |= guess_matches(video, guessit(self.filename, {'type': self.type}))
matches.add(id(self))
return matches
class SubsUnacsProvider(Provider):
"""SubsUnacs Provider."""
languages = {Language('por', 'BR')} | {Language(l) for l in [
'bul', 'eng'
]}
def initialize(self):
self.session = Session()
self.session.headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36'
self.session.headers["Accept"] = "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"
self.session.headers["Accept-Language"] = "en-US,en;q=0.5"
self.session.headers["Accept-Encoding"] = "gzip, deflate, br"
self.session.headers["DNT"] = "1"
self.session.headers["Connection"] = "keep-alive"
self.session.headers["Upgrade-Insecure-Requests"] = "1"
self.session.headers["Cache-Control"] = "max-age=0"
def terminate(self):
self.session.close()
def query(self, language, video):
subtitles = []
isEpisode = isinstance(video, Episode)
params = {
'm': '',
'l': 0,
'c': '',
'y': '',
'action': " Търси ",
'a': '',
'd': '',
'u': '',
'g': '',
't': '',
'imdbcheck': 1}
if isEpisode:
params['m'] = "%s %02d %02d" % (sanitize(video.series), video.season, video.episode)
else:
params['y'] = video.year
params['m'] = (video.title)
if language == 'en' or language == 'eng':
params['l'] = 1
logger.info('Searching subtitle %r', params)
response = self.session.post('https://subsunacs.net/search.php', params=params, allow_redirects=False, timeout=10, headers={
'Referer': 'https://subsunacs.net/index.php',
})
response.raise_for_status()
if response.status_code != 200:
logger.debug('No subtitles found')
return subtitles
soup = ParserBeautifulSoup(response.content, ['html.parser'])
rows = soup.findAll('td', {'class': 'tdMovie'})
# Search on first 10 rows only
for row in rows[:10]:
element = row.find('a', {'class': 'tooltip'})
if element:
link = element.get('href')
logger.info('Found subtitle link %r', link)
subtitles = subtitles + self.download_archive_and_add_subtitle_files('https://subsunacs.net' + link, language, video)
return subtitles
def list_subtitles(self, video, languages):
return [s for l in languages for s in self.query(l, video)]
def download_subtitle(self, subtitle):
pass
def process_archive_subtitle_files(self, archiveStream, language, video):
subtitles = []
type = 'episode' if isinstance(video, Episode) else 'movie'
for f in archiveStream.infolist():
if f.filename.lower().endswith(('.srt', '.sub')):
logger.info('Found subtitle file %r', f.filename)
subtitle = SubsUnacsSubtitle(language, f.filename, type)
subtitle.content = archiveStream.read(f)
subtitles.append(subtitle)
return subtitles
def download_archive_and_add_subtitle_files(self, link, language, video ):
logger.info('Downloading subtitle %r', link)
request = self.session.get(link, headers={
'Referer': 'https://subsunacs.net/search.php'
})
request.raise_for_status()
archive_stream = io.BytesIO(request.content)
if is_rarfile(archive_stream):
return self.process_archive_subtitle_files( RarFile(archive_stream), language, video )
elif is_zipfile(archive_stream):
return self.process_archive_subtitle_files( ZipFile(archive_stream), language, video )
else:
raise ValueError('Not a valid archive')
Loading…
Cancel
Save