aboutsummaryrefslogtreecommitdiffhomepage
path: root/libs/subliminal_patch/providers/assrt.py
blob: 4831da792911eb047d1dd4c8a61c60d5e8d1485f (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
# -*- coding: utf-8 -*-
from __future__ import absolute_import
import json
import logging
import os
import re

from babelfish import language_converters
from guessit import guessit
from requests import Session

from subliminal import Movie, Episode, ProviderError, __short_version__
from subliminal.exceptions import AuthenticationError, ConfigurationError, DownloadLimitExceeded, ProviderError
from subliminal_patch.subtitle import Subtitle, guess_matches
from subliminal.subtitle import fix_line_ending
from subliminal_patch.providers import Provider
from subzero.language import Language

logger = logging.getLogger(__name__)

language_converters.register('assrt = subliminal_patch.converters.assrt:AssrtConverter')

server_url = 'https://api.assrt.net/v1'
supported_languages = list(language_converters['assrt'].to_assrt.keys())


class AssrtSubtitle(Subtitle):
    """Assrt Sbutitle."""
    provider_name = 'assrt'
    guessit_options = {
        'allowed_languages': [ l[0] for l in supported_languages ],
        'allowed_countries': [ l[1] for l in supported_languages if len(l) > 1 ],
        'enforce_list': True
    }

    def __init__(self, language, subtitle_id, video_name, session, token):
        super(AssrtSubtitle, self).__init__(language)
        self.session = session
        self.token = token
        self.subtitle_id = subtitle_id
        self.video_name = video_name
        self.url = None
        self._detail = None

    def _get_detail(self):
        if self._detail:
            return self._detail
        params = {'token': self.token, 'id': self.id}
        r = self.session.get(server_url + '/sub/detail', params=params, timeout=10)
        r.raise_for_status()

        result = r.json()
        sub = result['sub']['subs'][0]
        files = sub['filelist']

        # first pass: guessit
        for f in files:
            logger.info('File %r', f)
            guess = guessit(f['f'], self.guessit_options)
            logger.info('GuessIt %r', guess)
            langs = set()
            if 'language' in guess:
                langs.update(guess['language'])
            if 'subtitle_language' in guess:
                langs.update(guess['subtitle_language'])
            if self.language in langs:
                self._defail = f
                return f

        # second pass: keyword matching
        codes = language_converters['assrt'].codes
        for f in files:
            langs = set([ Language.fromassrt(k) for k in codes if k in f['f'] ])
            logger.info('%s: %r', f['f'], langs)
            if self.language in langs:
                self._defail = f
                return f

        # fallback: pick up first file if nothing matches
        return files[0]

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

    @property
    def download_link(self):
        detail = self._get_detail()
        return detail['url']

    def get_matches(self, video):
        matches = guess_matches(video, guessit(self.video_name))
        return matches


class AssrtProvider(Provider):
    """Assrt Provider."""
    languages = {Language(*l) for l in supported_languages}

    def __init__(self, token=None):
        if not token:
            raise ConfigurationError('Token must be specified')
        self.token = token

    def initialize(self):
        self.session = Session()
        self.session.headers = {'User-Agent': os.environ.get("SZ_USER_AGENT", "Sub-Zero/2")}

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

    def query(self, languages, video):
        # query the server
        keywords = []
        if isinstance(video, Movie):
            if video.title:
                keywords.append(video.title)
            if video.year:
                keywords.append(str(video.year))
        elif isinstance(video, Episode):
            if video.series:
                keywords.append(video.series)
            if video.season and video.episode:
                keywords.append('S%02dE%02d' % (video.season, video.episode))
            elif video.episode:
                keywords.append('E%02d' % video.episode)
        query = ' '.join(keywords)

        params = {'token': self.token, 'q': query, 'is_file': 1}
        logger.debug('Searching subtitles %r', params)
        res = self.session.get(server_url + '/sub/search', params=params, timeout=10)
        res.raise_for_status()
        result = res.json()

        if result['status'] != 0:
            logger.error('status error: %r', r)
            return []

        if not result['sub']['subs']:
            logger.debug('No subtitle found')

        # parse the subtitles
        pattern = re.compile(r'lang(?P<code>\w+)')
        subtitles = []
        for sub in result['sub']['subs']:
            if 'lang' not in sub:
                continue
            for key in sub['lang']['langlist'].keys():
                match = pattern.match(key)
                try:
                    language = Language.fromassrt(match.group('code'))
                    if language in languages:
                        subtitles.append(AssrtSubtitle(language, sub['id'], sub['videoname'], self.session, self.token))
                except:
                    pass

        return subtitles

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

    def download_subtitle(self, subtitle):
        logger.info('Downloading subtitle %r', subtitle)
        r = self.session.get(subtitle.download_link, timeout=10)
        r.raise_for_status()

        subtitle.content = fix_line_ending(r.content)