summaryrefslogtreecommitdiffhomepage
path: root/libs/subliminal_patch/providers/subdivx.py
blob: b20523cbfe3bbac2ee6f8b1f96ef9bb855d09e75 (plain)
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
# -*- coding: utf-8 -*-
from __future__ import absolute_import

import logging
import re
import time

from requests import Session
from six.moves import range
from subliminal import __short_version__
from subliminal.providers import ParserBeautifulSoup
from subliminal.video import Episode
from subliminal.video 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

_SERVER_URL = "https://www.subdivx.com"

_CLEAN_TITLE_RES = [
    (r"subt[ií]tulos de", ""),
    (r"´|`", "'"),
    (r" {2,}", " "),
]

_SPANISH_RE = re.compile(r"españa|ib[eé]rico|castellano|gallego|castilla")
_YEAR_RE = re.compile(r"(\(\d{4}\))")


_SERIES_RE = re.compile(
    r"\(?\d{4}\)?|(s\d{1,2}(e\d{1,2})?|(season|temporada)\s\d{1,2}).*?$",
    flags=re.IGNORECASE,
)
_EPISODE_NUM_RE = re.compile(r"[eE](?P<x>\d{1,2})")
_SEASON_NUM_RE = re.compile(
    r"(s|(season|temporada)\s)(?P<x>\d{1,2})", flags=re.IGNORECASE
)
_EPISODE_YEAR_RE = re.compile(r"\((?P<x>(19\d{2}|20[0-2]\d))\)")
_UNSUPPORTED_RE = re.compile(
    r"(\)?\d{4}\)?|[sS]\d{1,2})\s.{,3}(extras|forzado(s)?|forced)", flags=re.IGNORECASE
)

logger = logging.getLogger(__name__)


class SubdivxSubtitle(Subtitle):
    provider_name = "subdivx"
    hash_verifiable = False

    def __init__(
        self, language, video, page_link, title, description, uploader, download_url
    ):
        super(SubdivxSubtitle, self).__init__(
            language, hearing_impaired=False, page_link=page_link
        )
        self.video = video

        self.download_url = download_url
        self.uploader = uploader

        self._title = str(title).strip()
        self._description = str(description).strip()

        self.release_info = self._title

        if self._description:
            self.release_info += " | " + self._description

    @property
    def id(self):
        return self.page_link

    def get_matches(self, video):
        matches = set()

        # episode
        if isinstance(video, Episode):
            # already matched within provider
            matches.update(["title", "series", "season", "episode", "year"])

        # movie
        elif isinstance(video, Movie):
            # already matched within provider
            matches.update(["title", "year"])

        update_matches(matches, video, self._description)

        # Don't lowercase; otherwise it will match a lot of false positives
        if video.release_group and video.release_group in self._description:
            matches.add("release_group")

        return matches


_IDUSER_COOKIE = "VkZaRk9WQlJQVDA12809"


class SubdivxSubtitlesProvider(Provider):
    provider_name = "subdivx"
    hash_verifiable = False
    languages = {Language("spa", "MX")} | {Language.fromalpha2("es")}
    video_types = (Episode, Movie)
    subtitle_class = SubdivxSubtitle

    multi_result_throttle = 2

    def __init__(self):
        self.session = None

    def initialize(self):
        self.session = Session()
        self.session.headers["User-Agent"] = f"Subliminal/{__short_version__}"
        self.session.cookies.update({"iduser_cookie": _IDUSER_COOKIE})

    def terminate(self):
        self.session.close()

    def query(self, video, languages):
        subtitles = []

        if isinstance(video, Episode):
            # TODO: cache pack queries (TV SHOW S01).
            # Too many redundant server calls.

            for query in (
                f"{video.series} S{video.season:02}E{video.episode:02}",
                f"{video.series} S{video.season:02}",
            ):
                subtitles += self._handle_multi_page_search(query, video)

            # Try only with series title
            if len(subtitles) <= 5:
                subtitles += self._handle_multi_page_search(video.series, video, 1)

        else:
            for query in (video.title, f"{video.title} ({video.year})"):
                subtitles += self._handle_multi_page_search(query, video)
                # Second query is a fallback
                if subtitles:
                    break

        return subtitles

    def _handle_multi_page_search(self, query, video, max_loops=2):
        params = {
            "buscar2": query,
            "accion": "5",
            "masdesc": "",
            "subtitulos": "1",
            "realiza_b": "1",
            "pg": 1,
        }
        logger.debug("Query: %s", query)

        loops = 1
        max_loops_not_met = True

        while max_loops_not_met:
            max_loops_not_met = loops < max_loops

            page_subtitles, last_page = self._get_page_subtitles(params, video)

            logger.debug("Yielding %d subtitles [loop #%d]", len(page_subtitles), loops)
            yield from page_subtitles

            if last_page:
                logger.debug("Last page for '%s' query. Breaking loop", query)
                break

            loops += 1

            params["pg"] += 1  # search next page
            time.sleep(self.multi_result_throttle)

        if not max_loops_not_met:
            logger.debug("Max loops limit exceeded (%d)", max_loops)

    def _get_page_subtitles(self, params, video):
        search_link = f"{_SERVER_URL}/index.php"
        response = self.session.get(
            search_link, params=params, allow_redirects=True, timeout=20
        )

        try:
            page_subtitles, last_page = self._parse_subtitles_page(video, response)
        except Exception as error:
            logger.error(f"Error parsing subtitles list: {error}")
            return []

        return page_subtitles, last_page

    def list_subtitles(self, video, languages):
        return self.query(video, languages)

    def download_subtitle(self, subtitle):
        # download the subtitle
        logger.debug("Downloading subtitle %r", subtitle)

        response = self.session.get(
            subtitle.download_url,
            headers={"Referer": _SERVER_URL},
            timeout=30,
        )
        response.raise_for_status()

        # TODO: add MustGetBlacklisted support

        archive = get_archive_from_bytes(response.content)
        if archive is None:
            raise APIThrottled("Unknwon compressed format")

        episode = None
        if isinstance(subtitle.video, Episode):
            episode = subtitle.video.episode

        subtitle.content = get_subtitle_from_archive(archive, episode=episode)

    def _parse_subtitles_page(self, video, response):
        subtitles = []

        page_soup = ParserBeautifulSoup(
            response.content.decode("utf-8", "ignore"), ["lxml", "html.parser"]
        )
        title_soups = page_soup.find_all("div", {"id": "menu_detalle_buscador"})
        body_soups = page_soup.find_all("div", {"id": "buscador_detalle"})

        title_checker = _check_episode if isinstance(video, Episode) else _check_movie

        for subtitle in range(0, len(title_soups)):
            title_soup, body_soup = title_soups[subtitle], body_soups[subtitle]
            # title
            title = _clean_title(title_soup.find("a").text)

            if _UNSUPPORTED_RE.search(title):
                logger.debug("Skipping unsupported subtitles: %s", title)
                continue

            if not title_checker(video, title):
                continue

            # Data
            datos = body_soup.find("div", {"id": "buscador_detalle_sub_datos"}).text
            # Ignore multi-disc and non-srt subtitles
            if not any(item in datos for item in ("Cds:</b> 1", "SubRip")):
                continue

            # description
            sub_details = body_soup.find("div", {"id": "buscador_detalle_sub"}).text
            description = sub_details.replace(",", " ")

            # language
            spain = (
                "/pais/7.gif" in datos
                or _SPANISH_RE.search(description.lower()) is not None
            )
            language = Language.fromalpha2("es") if spain else Language("spa", "MX")

            # uploader
            uploader = body_soup.find("a", {"class": "link1"}).text
            download_url = _get_download_url(body_soup)
            page_link = title_soup.find("a")["href"]

            subtitle = self.subtitle_class(
                language, video, page_link, title, description, uploader, download_url
            )

            logger.debug("Found subtitle %r", subtitle)
            subtitles.append(subtitle)

        return subtitles, len(title_soups) < 100


def _clean_title(title):
    """
    Normalize apostrophes and spaces to avoid matching problems
    (e.g. Subtitulos de  Carlito´s  Way -> Carlito's Way)
    """
    for og, new in _CLEAN_TITLE_RES:
        title = re.sub(og, new, title, flags=re.IGNORECASE)

    return title


def _get_download_url(data):
    try:
        return [
            a_.get("href")
            for a_ in data.find_all("a")
            if "bajar.php" in a_.get("href", "n/a")
        ][0]
    except IndexError:
        return None


def _check_episode(video, title):
    ep_num = _EPISODE_NUM_RE.search(title)
    season_num = _SEASON_NUM_RE.search(title)
    year = _EPISODE_YEAR_RE.search(title)

    # Only check if both video and Subdivx's title have year metadata
    if year is not None and video.year:
        year = int(year.group("x"))
        # Tolerancy of 1 year difference
        if abs(year - (video.year or 0)) > 1:
            logger.debug("Series year doesn't match: %s", title)
            return False

    if season_num is None:
        logger.debug("Not a season/episode: %s", title)
        return False

    season_num = int(season_num.group("x"))

    if ep_num is not None:
        ep_num = int(ep_num.group("x"))

    ep_matches = (
        (video.episode == ep_num) or (ep_num is None)
    ) and season_num == video.season

    series_title = _SERIES_RE.sub("", title).strip()

    distance = abs(len(series_title) - len(video.series))

    series_matched = distance < 4 and ep_matches

    logger.debug(
        "Series matched? %s [%s -> %s] [title distance: %d]",
        series_matched,
        video,
        title,
        distance,
    )

    return series_matched


def _check_movie(video, title):
    if str(video.year) not in title:
        return False

    aka_split = re.split("aka", title, flags=re.IGNORECASE)

    alt_title = None
    if len(aka_split) == 2:
        alt_title = aka_split[-1].strip()

    try:
        actual_movie_title = _YEAR_RE.split(title)[0].strip()
    except IndexError:
        return False

    all_titles = [
        v_title.lower() for v_title in [video.title, *video.alternative_titles]
    ]

    return (
        actual_movie_title.lower() in all_titles
        or (alt_title or "").lower() in all_titles
    )