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
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
|
# -*- coding: utf-8 -*-
from difflib import SequenceMatcher
import functools
import logging
import re
import time
import urllib.parse
from guessit import guessit
from requests import Session
from bs4 import BeautifulSoup as bso
from guessit import guessit
from requests import Session
from subliminal_patch.core import Episode
from subliminal_patch.core import Movie
from subliminal_patch.exceptions import APIThrottled
from subliminal_patch.providers import Provider
from subliminal_patch.providers.utils import get_archive_from_bytes
from subliminal_patch.providers.utils import get_subtitle_from_archive
from subliminal_patch.providers.utils import update_matches
from subliminal_patch.subtitle import Subtitle
from subzero.language import Language
logger = logging.getLogger(__name__)
class Subf2mSubtitle(Subtitle):
provider_name = "subf2m"
hash_verifiable = False
def __init__(self, language, page_link, release_info, episode_number=None):
super().__init__(language, page_link=page_link)
self.release_info = release_info
self.episode_number = episode_number
self.episode_title = None
self._matches = set(
("title", "year")
if episode_number is None
else ("title", "series", "year", "season", "episode")
)
def get_matches(self, video):
update_matches(self._matches, video, self.release_info)
return self._matches
@property
def id(self):
return self.page_link
_BASE_URL = "https://subf2m.co"
# TODO: add more seasons and languages
_SEASONS = (
"First",
"Second",
"Third",
"Fourth",
"Fifth",
"Sixth",
"Seventh",
"Eighth",
"Ninth",
"Tenth",
"Eleventh",
"Twelfth",
"Thirdteenth",
"Fourthteenth",
"Fifteenth",
"Sixteenth",
"Seventeenth",
"Eightheenth",
"Nineteenth",
"Tweentieth",
)
_LANGUAGE_MAP = {
"english": "eng",
"farsi_persian": "per",
"arabic": "ara",
"spanish": "spa",
"portuguese": "por",
"italian": "ita",
"dutch": "dut",
"hebrew": "heb",
"indonesian": "ind",
"danish": "dan",
"norwegian": "nor",
"bengali": "ben",
"bulgarian": "bul",
"croatian": "hrv",
"swedish": "swe",
"vietnamese": "vie",
"czech": "cze",
"finnish": "fin",
"french": "fre",
"german": "ger",
"greek": "gre",
"hungarian": "hun",
"icelandic": "ice",
"japanese": "jpn",
"macedonian": "mac",
"malay": "may",
"polish": "pol",
"romanian": "rum",
"russian": "rus",
"serbian": "srp",
"thai": "tha",
"turkish": "tur",
}
_DEFAULT_HEADERS = {
"authority": "subf2m.co",
"accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
"accept-language": "en-US,en;q=0.9",
"referer": "https://subf2m.co",
"sec-ch-ua": '"Chromium";v="111", "Not(A:Brand";v="8"',
"sec-ch-ua-mobile": "?0",
"sec-ch-ua-platform": '"Unknown"',
"sec-fetch-dest": "document",
"sec-fetch-mode": "navigate",
"sec-fetch-site": "same-origin",
"sec-fetch-user": "?1",
"upgrade-insecure-requests": "1",
}
class Subf2mProvider(Provider):
provider_name = "subf2m"
_movie_title_regex = re.compile(r"^(.+?)( \((\d{4})\))?$")
_tv_show_title_regex = re.compile(
r"^(.+?) [-\(]\s?(.*?) (season|series)\)?( \((\d{4})\))?$"
)
_supported_languages = {}
_supported_languages["brazillian-portuguese"] = Language("por", "BR")
for key, val in _LANGUAGE_MAP.items():
_supported_languages[key] = Language.fromalpha3b(val)
_supported_languages_reversed = {
val: key for key, val in _supported_languages.items()
}
languages = set(_supported_languages.values())
video_types = (Episode, Movie)
subtitle_class = Subf2mSubtitle
def __init__(self, verify_ssl=True, user_agent=None, session_factory=None):
super().__init__()
if not user_agent:
raise ValueError("User-agent config missing")
self._user_agent = user_agent
self._verify_ssl = verify_ssl
self._session_factory = session_factory
def initialize(self):
if self._session_factory is not None:
self._session = self._session_factory()
else:
logger.debug("No session factory set. Using default requests.Session.")
self._session = Session()
self._session.verify = self._verify_ssl
self._session.headers.update(_DEFAULT_HEADERS)
self._session.headers.update({"user-agent": self._user_agent})
def terminate(self):
self._session.close()
def _safe_get_text(self, url, retry=3, default_return=""):
req = None
for n in range(retry):
req = self._session.get(url, stream=True)
if req.status_code == 403:
logger.debug("Access to this resource is forbidden: %s", url)
break
# Sometimes subf2m will return a 503 code. This error usually disappears
# retrying the query
if req.status_code == 503:
logger.debug("503 returned. Trying again [%d] in 3 seconds", n + 1)
time.sleep(3)
continue
else:
req.raise_for_status()
break
if req is not None:
return "\n".join(
line for line in req.iter_lines(decode_unicode=True) if line
)
return default_return
def _gen_results(self, query):
query = urllib.parse.quote(query)
url = f"{_BASE_URL}/subtitles/searchbytitle?query={query}&l="
text = self._safe_get_text(url)
soup = bso(text, "html.parser")
for title in soup.select("li div[class='title'] a"):
yield title
def _search_movie(self, title, year):
title = title.lower()
year = str(year)
found_movie = None
results = []
for result in self._gen_results(title):
text = result.text.lower()
match = self._movie_title_regex.match(text)
if not match:
continue
match_title = match.group(1)
match_year = match.group(3)
if year == match_year:
results.append(
{
"href": result.get("href"),
"similarity": SequenceMatcher(None, title, match_title).ratio(),
}
)
if results:
results.sort(key=lambda x: x["similarity"], reverse=True)
found_movie = results[0]["href"]
logger.debug("Movie found: %s", results[0])
return found_movie
def _search_tv_show_season(self, title, season, year=None):
try:
season_str = _SEASONS[season - 1].lower()
except IndexError:
logger.debug("Season number not supported: %s", season)
return None
found_tv_show_season = None
results = []
for result in self._gen_results(title):
text = result.text.lower()
match = self._tv_show_title_regex.match(text)
if not match:
logger.debug("Series title not matched: %s", text)
continue
else:
logger.debug("Series title matched: %s", text)
match_title = match.group(1)
match_season = match.group(2)
# Match "complete series" titles as they usually contain season packs
if season_str == match_season or "complete" in match_season:
plus = 0.1 if year and str(year) in text else 0
results.append(
{
"href": result.get("href"),
"similarity": SequenceMatcher(None, title, match_title).ratio()
+ plus,
}
)
if results:
results.sort(key=lambda x: x["similarity"], reverse=True)
found_tv_show_season = results[0]["href"]
logger.debug("TV Show season found: %s", results[0])
return found_tv_show_season
def _find_movie_subtitles(self, path, language):
soup = self._get_subtitle_page_soup(path, language)
subtitles = []
for item in soup.select("li.item"):
subtitle = _get_subtitle_from_item(item, language)
if subtitle is None:
continue
logger.debug("Found subtitle: %s", subtitle)
subtitles.append(subtitle)
return subtitles
def _find_episode_subtitles(
self, path, season, episode, language, episode_title=None
):
soup = self._get_subtitle_page_soup(path, language)
subtitles = []
for item in soup.select("li.item"):
valid_item = None
clean_text = " ".join(item.text.split())
if not clean_text:
continue
# First try with the special episode matches for subf2m
guess = _get_episode_from_release(clean_text)
if guess is None:
guess = _memoized_episode_guess(clean_text)
if "season" not in guess:
if "complete series" in clean_text.lower():
logger.debug("Complete series pack found: %s", clean_text)
guess["season"] = [season]
else:
logger.debug("Nothing guessed from release: %s", clean_text)
continue
if season in guess["season"] and episode in guess.get("episode", []):
logger.debug("Episode match found: %s - %s", guess, clean_text)
valid_item = item
elif season in guess["season"] and not "episode" in guess:
logger.debug("Season pack found: %s", clean_text)
valid_item = item
if valid_item is None:
continue
subtitle = _get_subtitle_from_item(item, language, episode)
if subtitle is None:
continue
subtitle.episode_title = episode_title
logger.debug("Found subtitle: %s", subtitle)
subtitles.append(subtitle)
return subtitles
def _get_subtitle_page_soup(self, path, language):
language_path = self._supported_languages_reversed[language]
text = self._safe_get_text(f"{_BASE_URL}{path}/{language_path}")
return bso(text, "html.parser")
def list_subtitles(self, video, languages):
is_episode = isinstance(video, Episode)
if is_episode:
result = self._search_tv_show_season(video.series, video.season, video.year)
else:
result = self._search_movie(video.title, video.year)
if result is None:
logger.debug("No results")
return []
subtitles = []
for language in languages:
if is_episode:
subtitles.extend(
self._find_episode_subtitles(
result, video.season, video.episode, language, video.title
)
)
else:
subtitles.extend(self._find_movie_subtitles(result, language))
return subtitles
def download_subtitle(self, subtitle):
# TODO: add MustGetBlacklisted support
text = self._safe_get_text(subtitle.page_link)
soup = bso(text, "html.parser")
try:
download_url = _BASE_URL + str(
soup.select_one("a[id='downloadButton']")["href"] # type: ignore
)
except (AttributeError, KeyError, TypeError):
raise APIThrottled(f"Couldn't get download url from {subtitle.page_link}")
downloaded = self._session.get(download_url, allow_redirects=True)
archive = get_archive_from_bytes(downloaded.content)
if archive is None:
raise APIThrottled(f"Invalid archive: {subtitle.page_link}")
subtitle.content = get_subtitle_from_archive(
archive,
episode=subtitle.episode_number,
episode_title=subtitle.episode_title,
)
@functools.lru_cache(2048)
def _memoized_episode_guess(content):
# Use include to save time from unnecessary checks
return guessit(
content,
{
"type": "episode",
# Add codec keys to avoid matching x264, 5.1, etc as episode info
"includes": ["season", "episode", "video_codec", "audio_codec"],
"enforce_list": True,
},
)
_EPISODE_SPECIAL_RE = re.compile(
r"(season|s)\s*?(?P<x>\d{,2})\s?[-−]\s?(?P<y>\d{,2})", flags=re.IGNORECASE
)
def _get_episode_from_release(release: str):
match = _EPISODE_SPECIAL_RE.search(release)
if match is None:
return None
try:
season, episode = [int(item) for item in match.group("x", "y")]
except (IndexError, ValueError):
return None
return {"season": [season], "episode": [episode]}
def _get_subtitle_from_item(item, language, episode_number=None):
release_info = [
rel.text.strip() for rel in item.find("ul", {"class": "scrolllist"})
]
try:
text = item.find("div", {"class": "comment-col"}).find("p").text
release_info.append(text.replace("\n", " ").strip())
except AttributeError:
pass
release_info = "\n".join([item for item in release_info if item])
try:
path = item.find("a", {"class": "download icon-download"})["href"] # type: ignore
except (AttributeError, KeyError):
logger.debug("Couldn't get path: %s", item)
return None
return Subf2mSubtitle(language, _BASE_URL + path, release_info, episode_number)
|