aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/iprima.py
blob: 11a6629d249e3bd849475b16a00b0efa4bda283d (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
# coding: utf-8
from __future__ import unicode_literals

import re
import time

from .common import InfoExtractor
from ..utils import (
    determine_ext,
    js_to_json,
)


class IPrimaIE(InfoExtractor):
    _VALID_URL = r'https?://(?:play|prima|www)\.iprima\.cz/(?:[^/]+/)*(?P<id>[^/?#&]+)'
    _GEO_BYPASS = False

    _TESTS = [{
        'url': 'http://play.iprima.cz/gondici-s-r-o-33',
        'info_dict': {
            'id': 'p136534',
            'ext': 'mp4',
            'title': 'Gondíci s. r. o. (34)',
            'description': 'md5:16577c629d006aa91f59ca8d8e7f99bd',
        },
        'params': {
            'skip_download': True,  # m3u8 download
        },
    }, {
        'url': 'http://play.iprima.cz/particka/particka-92',
        'only_matching': True,
    }, {
        # geo restricted
        'url': 'http://play.iprima.cz/closer-nove-pripady/closer-nove-pripady-iv-1',
        'only_matching': True,
    }, {
        # iframe api.play-backend.iprima.cz
        'url': 'https://prima.iprima.cz/my-little-pony/mapa-znameni-2-2',
        'only_matching': True,
    }, {
        # iframe prima.iprima.cz
        'url': 'https://prima.iprima.cz/porady/jak-se-stavi-sen/rodina-rathousova-praha',
        'only_matching': True,
    }, {
        'url': 'http://www.iprima.cz/filmy/desne-rande',
        'only_matching': True,
    }]

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

        self._set_cookie('play.iprima.cz', 'ott_adult_confirmed', '1')

        webpage = self._download_webpage(url, video_id)

        video_id = self._search_regex(
            (r'<iframe[^>]+\bsrc=["\'](?:https?:)?//(?:api\.play-backend\.iprima\.cz/prehravac/embedded|prima\.iprima\.cz/[^/]+/[^/]+)\?.*?\bid=(p\d+)',
             r'data-product="([^"]+)">'),
            webpage, 'real id')

        playerpage = self._download_webpage(
            'http://play.iprima.cz/prehravac/init',
            video_id, note='Downloading player', query={
                '_infuse': 1,
                '_ts': round(time.time()),
                'productId': video_id,
            }, headers={'Referer': url})

        formats = []

        def extract_formats(format_url, format_key=None, lang=None):
            ext = determine_ext(format_url)
            new_formats = []
            if format_key == 'hls' or ext == 'm3u8':
                new_formats = self._extract_m3u8_formats(
                    format_url, video_id, 'mp4', entry_protocol='m3u8_native',
                    m3u8_id='hls', fatal=False)
            elif format_key == 'dash' or ext == 'mpd':
                return
                new_formats = self._extract_mpd_formats(
                    format_url, video_id, mpd_id='dash', fatal=False)
            if lang:
                for f in new_formats:
                    if not f.get('language'):
                        f['language'] = lang
            formats.extend(new_formats)

        options = self._parse_json(
            self._search_regex(
                r'(?s)(?:TDIPlayerOptions|playerOptions)\s*=\s*({.+?});\s*\]\]',
                playerpage, 'player options', default='{}'),
            video_id, transform_source=js_to_json, fatal=False)
        if options:
            for key, tracks in options.get('tracks', {}).items():
                if not isinstance(tracks, list):
                    continue
                for track in tracks:
                    src = track.get('src')
                    if src:
                        extract_formats(src, key.lower(), track.get('lang'))

        if not formats:
            for _, src in re.findall(r'src["\']\s*:\s*(["\'])(.+?)\1', playerpage):
                extract_formats(src)

        if not formats and '>GEO_IP_NOT_ALLOWED<' in playerpage:
            self.raise_geo_restricted(countries=['CZ'])

        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': self._og_search_title(webpage),
            'thumbnail': self._og_search_thumbnail(webpage),
            'formats': formats,
            'description': self._og_search_description(webpage),
        }