aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/nova.py
blob: 80186ec50cef0e580e1e07104006f8e3f89fa799 (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
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import (
    clean_html,
    int_or_none,
    js_to_json,
    qualities,
    unified_strdate,
    url_or_none,
)


class NovaEmbedIE(InfoExtractor):
    _VALID_URL = r'https?://media\.cms\.nova\.cz/embed/(?P<id>[^/?#&]+)'
    _TEST = {
        'url': 'https://media.cms.nova.cz/embed/8o0n0r?autoplay=1',
        'md5': 'b3834f6de5401baabf31ed57456463f7',
        'info_dict': {
            'id': '8o0n0r',
            'ext': 'mp4',
            'title': '2180. díl',
            'thumbnail': r're:^https?://.*\.jpg',
            'duration': 2578,
        },
    }

    def _real_extract(self, url):
        video_id = self._match_id(url)

        webpage = self._download_webpage(url, video_id)

        bitrates = self._parse_json(
            self._search_regex(
                r'(?s)bitrates\s*=\s*({.+?})\s*;', webpage, 'formats'),
            video_id, transform_source=js_to_json)

        QUALITIES = ('lq', 'mq', 'hq', 'hd')
        quality_key = qualities(QUALITIES)

        formats = []
        for format_id, format_list in bitrates.items():
            if not isinstance(format_list, list):
                continue
            for format_url in format_list:
                format_url = url_or_none(format_url)
                if not format_url:
                    continue
                f = {
                    'url': format_url,
                }
                f_id = format_id
                for quality in QUALITIES:
                    if '%s.mp4' % quality in format_url:
                        f_id += '-%s' % quality
                        f.update({
                            'quality': quality_key(quality),
                            'format_note': quality.upper(),
                        })
                        break
                f['format_id'] = f_id
                formats.append(f)
        self._sort_formats(formats)

        title = self._og_search_title(
            webpage, default=None) or self._search_regex(
            (r'<value>(?P<title>[^<]+)',
             r'videoTitle\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
            'title', group='value')
        thumbnail = self._og_search_thumbnail(
            webpage, default=None) or self._search_regex(
            r'poster\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
            'thumbnail', fatal=False, group='value')
        duration = int_or_none(self._search_regex(
            r'videoDuration\s*:\s*(\d+)', webpage, 'duration', fatal=False))

        return {
            'id': video_id,
            'title': title,
            'thumbnail': thumbnail,
            'duration': duration,
            'formats': formats,
        }


class NovaIE(InfoExtractor):
    IE_DESC = 'TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz'
    _VALID_URL = r'https?://(?:[^.]+\.)?(?P<site>tv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P<id>[^/]+?)(?:\.html|/|$)'
    _TESTS = [{
        'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html#player_13260',
        'md5': '1dd7b9d5ea27bc361f110cd855a19bd3',
        'info_dict': {
            'id': '1757139',
            'display_id': 'tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci',
            'ext': 'mp4',
            'title': 'Podzemní nemocnice v pražské Krči',
            'description': 'md5:f0a42dd239c26f61c28f19e62d20ef53',
            'thumbnail': r're:^https?://.*\.(?:jpg)',
        }
    }, {
        'url': 'http://fanda.nova.cz/clanek/fun-and-games/krvavy-epos-zaklinac-3-divoky-hon-vychazi-vyhrajte-ho-pro-sebe.html',
        'info_dict': {
            'id': '1753621',
            'ext': 'mp4',
            'title': 'Zaklínač 3: Divoký hon',
            'description': 're:.*Pokud se stejně jako my nemůžete.*',
            'thumbnail': r're:https?://.*\.jpg(\?.*)?',
            'upload_date': '20150521',
        },
        'params': {
            # rtmp download
            'skip_download': True,
        }
    }, {
        # media.cms.nova.cz embed
        'url': 'https://novaplus.nova.cz/porad/ulice/epizoda/18760-2180-dil',
        'info_dict': {
            'id': '8o0n0r',
            'ext': 'mp4',
            'title': '2180. díl',
            'thumbnail': r're:^https?://.*\.jpg',
            'duration': 2578,
        },
        'params': {
            'skip_download': True,
        },
        'add_ie': [NovaEmbedIE.ie_key()],
    }, {
        'url': 'http://sport.tn.nova.cz/clanek/sport/hokej/nhl/zivot-jde-dal-hodnotil-po-vyrazeni-z-playoff-jiri-sekac.html',
        'only_matching': True,
    }, {
        'url': 'http://fanda.nova.cz/clanek/fun-and-games/krvavy-epos-zaklinac-3-divoky-hon-vychazi-vyhrajte-ho-pro-sebe.html',
        'only_matching': True,
    }, {
        'url': 'http://doma.nova.cz/clanek/zdravi/prijdte-se-zapsat-do-registru-kostni-drene-jiz-ve-stredu-3-cervna.html',
        'only_matching': True,
    }, {
        'url': 'http://prask.nova.cz/clanek/novinky/co-si-na-sobe-nase-hvezdy-nechaly-pojistit.html',
        'only_matching': True,
    }, {
        'url': 'http://tv.nova.cz/clanek/novinky/zivot-je-zivot-bondovsky-trailer.html',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        display_id = mobj.group('id')
        site = mobj.group('site')

        webpage = self._download_webpage(url, display_id)

        # novaplus
        embed_id = self._search_regex(
            r'<iframe[^>]+\bsrc=["\'](?:https?:)?//media\.cms\.nova\.cz/embed/([^/?#&]+)',
            webpage, 'embed url', default=None)
        if embed_id:
            return self.url_result(
                'https://media.cms.nova.cz/embed/%s' % embed_id,
                ie=NovaEmbedIE.ie_key(), video_id=embed_id)

        video_id = self._search_regex(
            [r"(?:media|video_id)\s*:\s*'(\d+)'",
             r'media=(\d+)',
             r'id="article_video_(\d+)"',
             r'id="player_(\d+)"'],
            webpage, 'video id')

        config_url = self._search_regex(
            r'src="(https?://(?:tn|api)\.nova\.cz/bin/player/videojs/config\.php\?[^"]+)"',
            webpage, 'config url', default=None)
        config_params = {}

        if not config_url:
            player = self._parse_json(
                self._search_regex(
                    r'(?s)Player\s*\(.+?\s*,\s*({.+?\bmedia\b["\']?\s*:\s*["\']?\d+.+?})\s*\)', webpage,
                    'player', default='{}'),
                video_id, transform_source=js_to_json, fatal=False)
            if player:
                config_url = url_or_none(player.get('configUrl'))
                params = player.get('configParams')
                if isinstance(params, dict):
                    config_params = params

        if not config_url:
            DEFAULT_SITE_ID = '23000'
            SITES = {
                'tvnoviny': DEFAULT_SITE_ID,
                'novaplus': DEFAULT_SITE_ID,
                'vymena': DEFAULT_SITE_ID,
                'krasna': DEFAULT_SITE_ID,
                'fanda': '30',
                'tn': '30',
                'doma': '30',
            }

            site_id = self._search_regex(
                r'site=(\d+)', webpage, 'site id', default=None) or SITES.get(
                site, DEFAULT_SITE_ID)

            config_url = 'https://api.nova.cz/bin/player/videojs/config.php'
            config_params = {
                'site': site_id,
                'media': video_id,
                'quality': 3,
                'version': 1,
            }

        config = self._download_json(
            config_url, display_id,
            'Downloading config JSON', query=config_params,
            transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1])

        mediafile = config['mediafile']
        video_url = mediafile['src']

        m = re.search(r'^(?P<url>rtmpe?://[^/]+/(?P<app>[^/]+?))/&*(?P<playpath>.+)$', video_url)
        if m:
            formats = [{
                'url': m.group('url'),
                'app': m.group('app'),
                'play_path': m.group('playpath'),
                'player_path': 'http://tvnoviny.nova.cz/static/shared/app/videojs/video-js.swf',
                'ext': 'flv',
            }]
        else:
            formats = [{
                'url': video_url,
            }]
        self._sort_formats(formats)

        title = mediafile.get('meta', {}).get('title') or self._og_search_title(webpage)
        description = clean_html(self._og_search_description(webpage, default=None))
        thumbnail = config.get('poster')

        if site == 'novaplus':
            upload_date = unified_strdate(self._search_regex(
                r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None))
        elif site == 'fanda':
            upload_date = unified_strdate(self._search_regex(
                r'<span class="date_time">(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None))
        else:
            upload_date = None

        return {
            'id': video_id,
            'display_id': display_id,
            'title': title,
            'description': description,
            'upload_date': upload_date,
            'thumbnail': thumbnail,
            'formats': formats,
        }