1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
|
# -*- 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, video, link):
super(SubsSabBzSubtitle, self).__init__(langauge)
self.langauge = langauge
self.filename = filename
self.page_link = link
self.type = type
self.video = video
@property
def id(self):
return self.filename
def make_picklable(self):
self.content = None
return self
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 = a_element_wrapper.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):
if subtitle.content:
pass
else:
seeking_subtitle_file = subtitle.filename
arch = self.download_archive_and_add_subtitle_files(subtitle.page_link, subtitle.language, subtitle.video)
for s in arch:
if s.filename == seeking_subtitle_file:
subtitle.content = s.content
def process_archive_subtitle_files(self, archiveStream, language, video, link):
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, video, link)
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, link )
elif is_zipfile(archive_stream):
return self.process_archive_subtitle_files( ZipFile(archive_stream), language, video, link )
else:
raise ValueError('Not a valid archive')
|
