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
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
|
# -*- coding: utf-8 -*-
from __future__ import absolute_import
import io
import logging
import os
import random
import rarfile
import re
import zipfile
from subzero.language import Language
from guessit import guessit
from requests import Session
from subliminal.providers import ParserBeautifulSoup, Provider
from subliminal import __short_version__
from subliminal.cache import SHOW_EXPIRATION_TIME, region
from subliminal.score import get_equivalent_release_groups
from subliminal.subtitle import SUBTITLE_EXTENSIONS, Subtitle, fix_line_ending
from subliminal.utils import sanitize, sanitize_release_group
from subliminal.video import Movie
from subliminal_patch.subtitle import guess_matches
logger = logging.getLogger(__name__)
year_re = re.compile(r'^\((\d{4})\)$')
class Subs4FreeSubtitle(Subtitle):
"""Subs4Free Subtitle."""
provider_name = 'subs4free'
def __init__(self, language, page_link, title, year, version, download_link, uploader):
super(Subs4FreeSubtitle, self).__init__(language, page_link=page_link)
self.title = title
self.year = year
self.version = version
self.release_info = version
self.download_link = download_link
self.uploader = uploader
self.hearing_impaired = None
self.encoding = 'utf8'
@property
def id(self):
return self.download_link
def get_matches(self, video):
matches = set()
# movie
if isinstance(video, Movie):
# title
if video.title and (sanitize(self.title) in (
sanitize(name) for name in [video.title] + video.alternative_titles)):
matches.add('title')
# year
if video.year and self.year == video.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')
# other properties
matches |= guess_matches(video, guessit(self.version, {'type': 'movie'}), partial=True)
return matches
class Subs4FreeProvider(Provider):
"""Subs4Free Provider."""
languages = {Language(l) for l in ['ell', 'eng']}
video_types = (Movie,)
server_url = 'https://www.subs4free.info'
download_url = '/getSub.php'
search_url = '/search_report.php?search={}&searchType=1'
anti_block_1 = 'https://images.subs4free.info/favicon.ico'
anti_block_2 = 'https://www.subs4series.com/includes/anti-block-layover.php?launch=1'
anti_block_3 = 'https://www.subs4series.com/includes/anti-block.php'
subtitle_class = Subs4FreeSubtitle
def __init__(self):
self.session = None
def initialize(self):
self.session = Session()
from .utils import FIRST_THOUSAND_OR_SO_USER_AGENTS as AGENT_LIST
self.session.headers['User-Agent'] = AGENT_LIST[random.randint(0, len(AGENT_LIST) - 1)]
def terminate(self):
self.session.close()
def get_show_links(self, title, year=None):
"""Get the matching show links for `title` and `year`.
First search in the result of :meth:`_get_show_suggestions`.
:param title: show title.
:param year: year of the show, if any.
:type year: int
:return: the show links, if found.
:rtype: list of str
"""
title = sanitize(title)
suggestions = self._get_suggestions(title)
show_links = []
for suggestion in suggestions:
show_title = sanitize(suggestion['title'])
if show_title == title or (year and show_title == '{title} {year:d}'.format(title=title, year=year)):
logger.debug('Getting show id')
show_links.append(suggestion['link'].split('?p=')[-1])
return show_links
@region.cache_on_arguments(expiration_time=SHOW_EXPIRATION_TIME, should_cache_fn=lambda value: value)
def _get_suggestions(self, title):
"""Search the show or movie id from the `title` and `year`.
:param str title: title of the show.
:return: the show suggestions found.
:rtype: list of dict
"""
# make the search
logger.info('Searching show ids with %r', title)
r = self.session.get(self.server_url + self.search_url.format(title),
headers={'Referer': self.server_url}, timeout=10)
r.raise_for_status()
if not r.content:
logger.debug('No data returned from provider')
return []
soup = ParserBeautifulSoup(r.content, ['html.parser'])
suggestions = [{'link': l.attrs['value'], 'title': l.text}
for l in soup.select('select[name="Mov_sel"] > option[value]')]
logger.debug('Found suggestions: %r', suggestions)
return suggestions
def query(self, movie_id, title, year):
# get the season list of the show
logger.info('Getting the subtitle list of show id %s', movie_id)
if movie_id:
page_link = self.server_url + '/' + movie_id
else:
page_link = self.server_url + self.search_url.format(' '.join([title, str(year)]))
r = self.session.get(page_link, timeout=10)
r.raise_for_status()
if not r.content:
logger.debug('No data returned from provider')
return []
soup = ParserBeautifulSoup(r.content, ['html.parser'])
year = None
year_element = soup.select_one('td#dates_header > table div')
matches = False
if year_element:
matches = year_re.match(str(year_element.contents[2]).strip())
if matches:
year = int(matches.group(1))
title_tag = soup.select_one('td#dates_header > table u')
show_title = str(title_tag.contents[0]).strip() if title_tag else None
subtitles = []
# loop over episode rows
for subs_tag in soup.select('.movie-details'):
# read common info
version = subs_tag.find('span').text
download_link = self.server_url + subs_tag.find('a')['href']
uploader = subs_tag.select_one('.movie-info').find('p').find('a').text
language_code = subs_tag.select_one('.sprite')['class'][1].split('gif')[0]
language = Language.fromietf(language_code)
subtitle = self.subtitle_class(language, page_link, show_title, year, version, download_link, uploader)
logger.debug('Found subtitle {!r}'.format(subtitle))
subtitles.append(subtitle)
return subtitles
def list_subtitles(self, video, languages):
# lookup show_id
titles = [video.title] + video.alternative_titles if isinstance(video, Movie) else []
show_links = None
for title in titles:
show_links = self.get_show_links(title, video.year)
if show_links:
break
subtitles = []
# query for subtitles with the show_id
if show_links:
for show_link in show_links:
subtitles += [s for s in self.query(show_link, video.title, video.year) if s.language in languages]
else:
subtitles += [s for s in self.query(None, sanitize(video.title), video.year) if s.language in languages]
return subtitles
def download_subtitle(self, subtitle):
if isinstance(subtitle, Subs4FreeSubtitle):
# download the subtitle
logger.info('Downloading subtitle %r', subtitle)
r = self.session.get(subtitle.download_link, headers={'Referer': subtitle.page_link}, timeout=10)
r.raise_for_status()
if not r.content:
logger.debug('Unable to download subtitle. No data returned from provider')
return
soup = ParserBeautifulSoup(r.content, ['lxml', 'html.parser'])
download_element = soup.select_one('input[name="id"]')
image_element = soup.select_one('input[type="image"]')
subtitle_id = download_element['value'] if download_element else None
width = int(str(image_element['width']).strip('px')) if image_element else 0
height = int(str(image_element['height']).strip('px')) if image_element else 0
if not subtitle_id:
logger.debug('Unable to download subtitle. No download link found')
return
self.apply_anti_block(subtitle)
download_url = self.server_url + self.download_url
r = self.session.post(download_url, data={'id': subtitle_id, 'x': random.randint(0, width),
'y': random.randint(0, height)},
headers={'Referer': subtitle.download_link}, timeout=10)
r.raise_for_status()
if not r.content:
logger.debug('Unable to download subtitle. No data returned from provider')
return
archive = _get_archive(r.content)
subtitle_content = _get_subtitle_from_archive(archive) if archive else r.content
if subtitle_content:
subtitle.content = fix_line_ending(subtitle_content)
else:
logger.debug('Could not extract subtitle from %r', archive)
def apply_anti_block(self, subtitle):
self.session.get(self.anti_block_1, headers={'Referer': subtitle.download_link}, timeout=10)
self.session.get(self.anti_block_2, headers={'Referer': subtitle.download_link}, timeout=10)
self.session.get(self.anti_block_3, headers={'Referer': subtitle.download_link}, timeout=10)
def _get_archive(content):
# open the archive
archive_stream = io.BytesIO(content)
archive = None
if rarfile.is_rarfile(archive_stream):
logger.debug('Identified rar archive')
archive = rarfile.RarFile(archive_stream)
elif zipfile.is_zipfile(archive_stream):
logger.debug('Identified zip archive')
archive = zipfile.ZipFile(archive_stream)
return archive
def _get_subtitle_from_archive(archive):
for name in archive.namelist():
# discard hidden files
if os.path.split(name)[-1].startswith('.'):
continue
# discard non-subtitle files
if not name.lower().endswith(SUBTITLE_EXTENSIONS):
continue
return archive.read(name)
return None
|
