# Conflicts: # bazarr/get_subtitle.pypull/489/head
Halali
6 years ago
commit
eef8e33554
@ -0,0 +1,159 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import logging
|
||||
import re
|
||||
import io
|
||||
import os
|
||||
from random import randint
|
||||
from bs4 import BeautifulSoup
|
||||
from zipfile import ZipFile, is_zipfile
|
||||
from rarfile import RarFile, is_rarfile
|
||||
from requests import Session
|
||||
from guessit import guessit
|
||||
from subliminal_patch.providers import Provider
|
||||
from subliminal_patch.subtitle import Subtitle
|
||||
from subliminal_patch.utils import sanitize
|
||||
from subliminal.exceptions import ProviderError
|
||||
from subliminal.utils import sanitize_release_group
|
||||
from subliminal.subtitle import guess_matches
|
||||
from subliminal.video import Episode, Movie
|
||||
from subliminal.subtitle import fix_line_ending
|
||||
from subzero.language import Language
|
||||
from .utils import FIRST_THOUSAND_OR_SO_USER_AGENTS as AGENT_LIST
|
||||
|
||||
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'] = AGENT_LIST[randint(0, len(AGENT_LIST) - 1)]
|
||||
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 = BeautifulSoup(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 file_name in archiveStream.namelist():
|
||||
if file_name.lower().endswith(('.srt', '.sub')):
|
||||
logger.info('Found subtitle file %r', file_name)
|
||||
subtitle = SubsSabBzSubtitle(language, file_name, type)
|
||||
subtitle.content = archiveStream.read(file_name)
|
||||
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 +1,161 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import logging
|
||||
import re
|
||||
import io
|
||||
import os
|
||||
from random import randint
|
||||
from bs4 import BeautifulSoup
|
||||
from zipfile import ZipFile, is_zipfile
|
||||
from rarfile import RarFile, is_rarfile
|
||||
from requests import Session
|
||||
from guessit import guessit
|
||||
from subliminal_patch.providers import Provider
|
||||
from subliminal_patch.subtitle import Subtitle
|
||||
from subliminal_patch.utils import sanitize
|
||||
from subliminal.exceptions import ProviderError
|
||||
from subliminal.utils import sanitize_release_group
|
||||
from subliminal.subtitle import guess_matches
|
||||
from subliminal.video import Episode, Movie
|
||||
from subliminal.subtitle import fix_line_ending
|
||||
from subzero.language import Language
|
||||
from .utils import FIRST_THOUSAND_OR_SO_USER_AGENTS as AGENT_LIST
|
||||
|
||||
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'] = AGENT_LIST[randint(0, len(AGENT_LIST) - 1)]
|
||||
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 = BeautifulSoup(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 file_name in archiveStream.namelist():
|
||||
if file_name.lower().endswith(('.srt', '.sub')):
|
||||
logger.info('Found subtitle file %r', file_name)
|
||||
subtitle = SubsUnacsSubtitle(language, file_name, type)
|
||||
subtitle.content = archiveStream.read(file_name)
|
||||
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')
|
||||
@ -0,0 +1,77 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
__author__ = "Daniel Roy Greenfeld"
|
||||
__email__ = "pydanny@gmail.com"
|
||||
__version__ = "0.5.2"
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
try: # Forced testing
|
||||
from shutil import which
|
||||
except ImportError: # Forced testing
|
||||
# Versions prior to Python 3.3 don't have shutil.which
|
||||
|
||||
def which(cmd, mode=os.F_OK | os.X_OK, path=None):
|
||||
"""Given a command, mode, and a PATH string, return the path which
|
||||
conforms to the given mode on the PATH, or None if there is no such
|
||||
file.
|
||||
`mode` defaults to os.F_OK | os.X_OK. `path` defaults to the result
|
||||
of os.environ.get("PATH"), or can be overridden with a custom search
|
||||
path.
|
||||
Note: This function was backported from the Python 3 source code.
|
||||
"""
|
||||
# Check that a given file can be accessed with the correct mode.
|
||||
# Additionally check that `file` is not a directory, as on Windows
|
||||
# directories pass the os.access check.
|
||||
|
||||
def _access_check(fn, mode):
|
||||
return os.path.exists(fn) and os.access(fn, mode) and not os.path.isdir(fn)
|
||||
|
||||
# If we're given a path with a directory part, look it up directly
|
||||
# rather than referring to PATH directories. This includes checking
|
||||
# relative to the current directory, e.g. ./script
|
||||
if os.path.dirname(cmd):
|
||||
if _access_check(cmd, mode):
|
||||
return cmd
|
||||
|
||||
return None
|
||||
|
||||
if path is None:
|
||||
path = os.environ.get("PATH", os.defpath)
|
||||
if not path:
|
||||
return None
|
||||
|
||||
path = path.split(os.pathsep)
|
||||
|
||||
if sys.platform == "win32":
|
||||
# The current directory takes precedence on Windows.
|
||||
if os.curdir not in path:
|
||||
path.insert(0, os.curdir)
|
||||
|
||||
# PATHEXT is necessary to check on Windows.
|
||||
pathext = os.environ.get("PATHEXT", "").split(os.pathsep)
|
||||
# See if the given file matches any of the expected path
|
||||
# extensions. This will allow us to short circuit when given
|
||||
# "python.exe". If it does match, only test that one, otherwise we
|
||||
# have to try others.
|
||||
if any(cmd.lower().endswith(ext.lower()) for ext in pathext):
|
||||
files = [cmd]
|
||||
else:
|
||||
files = [cmd + ext for ext in pathext]
|
||||
else:
|
||||
# On other platforms you don't have things like PATHEXT to tell you
|
||||
# what file suffixes are executable, so just pass on cmd as-is.
|
||||
files = [cmd]
|
||||
|
||||
seen = set()
|
||||
for dir in path:
|
||||
normdir = os.path.normcase(dir)
|
||||
if normdir not in seen:
|
||||
seen.add(normdir)
|
||||
for thefile in files:
|
||||
name = os.path.join(dir, thefile)
|
||||
if _access_check(name, mode):
|
||||
return name
|
||||
|
||||
return None
|
||||
Loading…
Reference in new issue