summaryrefslogtreecommitdiffhomepage
path: root/libs/subliminal_patch/providers/titrari.py
blob: 2a400892390e083da5b40396fed69fed90da351e (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
# coding=utf-8

from __future__ import absolute_import
import os
import io
import logging
import re
import rarfile
from random import randint

from zipfile import ZipFile, is_zipfile
from rarfile import RarFile, is_rarfile
from guessit import guessit
from subliminal_patch.providers import Provider
from subliminal_patch.providers.mixins import ProviderSubtitleArchiveMixin
from subliminal_patch.subtitle import Subtitle, guess_matches
from subliminal_patch.utils import sanitize, fix_inconsistent_naming as _fix_inconsistent_naming
from .utils import FIRST_THOUSAND_OR_SO_USER_AGENTS as AGENT_LIST
from subliminal.exceptions import ProviderError
from subliminal.providers import ParserBeautifulSoup
from subliminal.video import Episode, Movie
from subliminal.subtitle import SUBTITLE_EXTENSIONS
from subzero.language import Language

# parsing regex definitions
title_re = re.compile(r'(?P<title>(?:.+(?= [Aa][Kk][Aa] ))|.+)(?:(?:.+)(?P<altitle>(?<= [Aa][Kk][Aa] ).+))?')


def fix_inconsistent_naming(title):
    """Fix titles with inconsistent naming using dictionary and sanitize them.

    :param str title: original title.
    :return: new title.
    :rtype: str

    """
    return _fix_inconsistent_naming(title, {"DC's Legends of Tomorrow": "Legends of Tomorrow",
                                            "Marvel's Jessica Jones": "Jessica Jones"})


logger = logging.getLogger(__name__)

# Configure :mod:`rarfile` to use the same path separator as :mod:`zipfile`
rarfile.PATH_SEP = '/'


class TitrariSubtitle(Subtitle):

    provider_name = 'titrari'

    def __init__(self, language, download_link, sid, releases, title, imdb_id, year=None, download_count=None,
                 comments=None, is_episode=False, desired_episode=None):
        super(TitrariSubtitle, self).__init__(language)
        self.sid = sid
        self.title = title
        self.imdb_id = imdb_id
        self.download_link = download_link
        self.year = year
        self.download_count = download_count
        self.releases = self.release_info = releases
        self.comments = comments
        self.matches = None
        self.is_episode = is_episode
        self.desired_episode = desired_episode

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

    def __str__(self):
        return self.title + "(" + str(self.year) + ")" + " -> " + self.download_link

    def __repr__(self):
        return self.title + "(" + str(self.year) + ")"

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

        if video.year and self.year == video.year:
            matches.add('year')

        if video.release_group and video.release_group in self.comments:
            matches.add('release_group')

        if isinstance(video, Movie):
            # title
            if video.title and sanitize(self.title) == fix_inconsistent_naming(video.title):
                matches.add('title')

            # imdb
            if video.imdb_id and self.imdb_id == video.imdb_id:
                matches.add('imdb_id')

            # guess match others
            matches |= guess_matches(video, guessit(self.comments, {"type": "movie"}))

        else:
            # title
            seasonless_title = re.sub(r'\s-\sSezonul\s\d+$', '', self.title.rstrip())
            if video.series and fix_inconsistent_naming(video.series) == sanitize(seasonless_title):
                matches.add('series')

            # imdb
            if video.series_imdb_id and self.imdb_id == video.series_imdb_id:
                matches.add('imdb_id')

            # season
            if f"Sezonul {video.season}" in self.title:
                matches.add('season')

            # episode
            if {"imdb_id", "season"}.issubset(matches):
                matches.add('episode')

            # guess match others
            matches |= guess_matches(video, guessit(self.comments, {"type": "episode"}))

        self.matches = matches

        return matches


class TitrariProvider(Provider, ProviderSubtitleArchiveMixin):
    subtitle_class = TitrariSubtitle
    languages = {Language(lang) for lang in ['ron', 'eng']}
    languages.update(set(Language.rebuild(lang, forced=True) for lang in languages))
    api_url = 'https://www.titrari.ro/'
    query_advanced_search = 'cautarepreaavansata'

    def __init__(self):
        self.session = None

    def initialize(self):
        self.session = Session()
        # Hardcoding the UA to bypass the 30s throttle that titrari.ro uses for IP/UA pair
        self.session.headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, ' \
                                             'like Gecko) Chrome/93.0.4535.2 Safari/537.36'
        # self.session.headers['User-Agent'] = AGENT_LIST[randint(0, len(AGENT_LIST) - 1)]

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

    def query(self, languages=None, title=None, imdb_id=None, video=None):
        subtitles = []

        params = self.getQueryParams(imdb_id, title)

        search_response = self.session.get(self.api_url, params=params, timeout=15)
        search_response.raise_for_status()

        if not search_response.content:
            logger.debug('[#### Provider: titrari.ro] No data returned from provider')
            return []

        soup = ParserBeautifulSoup(search_response.content.decode('utf-8', 'ignore'), ['lxml', 'html.parser'])

        # loop over subtitle cells
        rows = soup.select('td[rowspan=\'5\']')
        for index, row in enumerate(rows):
            result_anchor_el = row.select_one('a')

            # Download link
            href = result_anchor_el.get('href')
            download_link = self.api_url + href

            fullTitle = row.parent.find("h1").find("a").text

            # Get title
            try:
                title = fullTitle.split("(")[0]
            except:
                logger.error("[#### Provider: titrari.ro] Error parsing title.")

            # Get downloads count
            downloads = 0
            try:
                downloads = int(row.parent.parent.select("span")[index].text[12:])
            except:
                logger.error("[#### Provider: titrari.ro] Error parsing downloads.")

            # Get year
            try:
                year = int(fullTitle.split("(")[1].split(")")[0])
            except:
                year = None
                logger.error("[#### Provider: titrari.ro] Error parsing year.")

            # Get imdbId
            sub_imdb_id = self.getImdbIdFromSubtitle(row)

            comments = ''
            try:
                comments = row.parent.parent.find_all("td", class_=re.compile("comment"))[index*2+1].text
            except:
                logger.error("Error parsing comments.")

            episode_number = video.episode if isinstance(video, Episode) else None
            subtitle = self.subtitle_class(next(iter(languages)), download_link, index, None, title, sub_imdb_id,
                                           year, downloads, comments, isinstance(video, Episode), episode_number)
            logger.debug('[#### Provider: titrari.ro] Found subtitle %r', str(subtitle))
            subtitles.append(subtitle)

        ordered_subs = self.order(subtitles)

        return ordered_subs

    @staticmethod
    def order(subtitles):
        logger.debug("[#### Provider: titrari.ro] Sorting by download count...")
        sorted_subs = sorted(subtitles, key=lambda s: s.download_count, reverse=True)
        return sorted_subs

    @staticmethod
    def getImdbIdFromSubtitle(row):
        imdbId = None
        try:
            imdbId = row.parent.parent.find_all(src=re.compile("imdb"))[0].parent.get('href').split("tt")[-1]
        except:
            logger.error("[#### Provider: titrari.ro] Error parsing imdbId.")
        if imdbId is not None:
            return "tt" + imdbId
        else:
            return None

    # titrari.ro seems to require all parameters now
    #  z2 = comment (empty)
    #  z3 = fps (-1: any, 0: N/A, 1: 23.97 FPS etc.)
    #  z4 = CD count (-1: any)
    #  z5 = imdb_id (empty or integer)
    #  z6 = sort order (0: unsorted, 1: by date, 2: by name)
    #  z7 = title (empty or string)
    #  z8 = language (-1: all, 1: ron, 2: eng)
    #  z9 = genre (All: all, Action: action etc.)
    # z11 = type (0: any, 1: movie, 2: series)
    def getQueryParams(self, imdb_id, title):
        queryParams = {
            'page': self.query_advanced_search,
            'z7': '',
            'z2': '',
            'z5': '',
            'z3': '-1',
            'z4': '-1',
            'z8': '-1',
            'z9': 'All',
            'z11': '0',
            'z6': '0'
        }
        if imdb_id is not None:
            queryParams["z5"] = imdb_id
        elif title is not None:
            queryParams["z7"] = title

        return queryParams

    def list_subtitles(self, video, languages):
        title = fix_inconsistent_naming(video.title)
        imdb_id = None
        try:
            if isinstance(video, Episode):
                imdb_id = video.series_imdb_id[2:]
            else:
                imdb_id = video.imdb_id[2:]
        except:
            logger.error("[#### Provider: titrari.ro] Error parsing video.imdb_id.")

        subtitles = [s for s in
                     self.query(languages, title, imdb_id, video)]
        return subtitles

    def download_subtitle(self, subtitle):
        r = self.session.get(subtitle.download_link, headers={'Referer': self.api_url}, timeout=10)
        r.raise_for_status()

        # open the archive
        archive_stream = io.BytesIO(r.content)
        if is_rarfile(archive_stream):
            logger.debug('[#### Provider: titrari.ro] Archive identified as rar')
            archive = RarFile(archive_stream)
        elif is_zipfile(archive_stream):
            logger.debug('[#### Provider: titrari.ro] Archive identified as zip')
            archive = ZipFile(archive_stream)
        else:
            subtitle.content = r.content
            if subtitle.is_valid():
                return
            subtitle.content = None

            raise ProviderError('[#### Provider: titrari.ro] Unidentified archive type')

        subtitle.releases = _get_releases_from_archive(archive)
        if subtitle.is_episode:
            subtitle.content = self._get_subtitle_from_archive(subtitle, archive)
        else:
            subtitle.content = self.get_subtitle_from_archive(subtitle, archive)

    @staticmethod
    def _get_subtitle_from_archive(subtitle, 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

            _guess = guessit(name)
            if subtitle.desired_episode == _guess['episode']:
                return archive.read(name)

        return None


def _get_releases_from_archive(archive):
    releases = []
    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

        releases.append(os.path.splitext(os.path.split(name)[1])[0])

    return releases