aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/cda.py
blob: e00bdaf66a6d9eb6ac051cc169cabbf02844770b (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
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import (
    ExtractorError,
    float_or_none,
    int_or_none,
    parse_duration,
)


class CDAIE(InfoExtractor):
    _VALID_URL = r'https?://(?:(?:www\.)?cda\.pl/video|ebd\.cda\.pl/[0-9]+x[0-9]+)/(?P<id>[0-9a-z]+)'
    _BASE_URL = 'http://www.cda.pl/'
    _TESTS = [{
        'url': 'http://www.cda.pl/video/5749950c',
        'md5': '6f844bf51b15f31fae165365707ae970',
        'info_dict': {
            'id': '5749950c',
            'ext': 'mp4',
            'height': 720,
            'title': 'Oto dlaczego przed zakrętem należy zwolnić.',
            'description': 'md5:269ccd135d550da90d1662651fcb9772',
            'thumbnail': 're:^https?://.*\.jpg$',
            'average_rating': float,
            'duration': 39
        }
    }, {
        'url': 'http://www.cda.pl/video/57413289',
        'md5': 'a88828770a8310fc00be6c95faf7f4d5',
        'info_dict': {
            'id': '57413289',
            'ext': 'mp4',
            'title': 'Lądowanie na lotnisku na Maderze',
            'description': 'md5:60d76b71186dcce4e0ba6d4bbdb13e1a',
            'thumbnail': 're:^https?://.*\.jpg$',
            'uploader': 'crash404',
            'view_count': int,
            'average_rating': float,
            'duration': 137
        }
    }, {
        'url': 'http://ebd.cda.pl/0x0/5749950c',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        video_id = self._match_id(url)
        self._set_cookie('cda.pl', 'cda.player', 'html5')
        webpage = self._download_webpage(
            self._BASE_URL + '/video/' + video_id, video_id)

        if 'Ten film jest dostępny dla użytkowników premium' in webpage:
            raise ExtractorError('This video is only available for premium users.', expected=True)

        formats = []

        uploader = self._search_regex(r'''(?x)
            <(span|meta)[^>]+itemprop=(["\'])author\2[^>]*>
            (?:<\1[^>]*>[^<]*</\1>|(?!</\1>)(?:.|\n))*?
            <(span|meta)[^>]+itemprop=(["\'])name\4[^>]*>(?P<uploader>[^<]+)</\3>
        ''', webpage, 'uploader', default=None, group='uploader')
        view_count = self._search_regex(
            r'Odsłony:(?:\s|&nbsp;)*([0-9]+)', webpage,
            'view_count', default=None)
        average_rating = self._search_regex(
            r'<(?:span|meta)[^>]+itemprop=(["\'])ratingValue\1[^>]*>(?P<rating_value>[0-9.]+)',
            webpage, 'rating', fatal=False, group='rating_value')

        info_dict = {
            'id': video_id,
            'title': self._og_search_title(webpage),
            'description': self._og_search_description(webpage),
            'uploader': uploader,
            'view_count': int_or_none(view_count),
            'average_rating': float_or_none(average_rating),
            'thumbnail': self._og_search_thumbnail(webpage),
            'formats': formats,
            'duration': None,
        }

        def extract_format(page, version):
            json_str = self._search_regex(
                r'player_data=(\\?["\'])(?P<player_data>.+?)\1', page,
                '%s player_json' % version, fatal=False, group='player_data')
            if not json_str:
                return
            player_data = self._parse_json(
                json_str, '%s player_data' % version, fatal=False)
            if not player_data:
                return
            video = player_data.get('video')
            if not video or 'file' not in video:
                self.report_warning('Unable to extract %s version information' % version)
                return
            f = {
                'url': video['file'],
            }
            m = re.search(
                r'<a[^>]+data-quality="(?P<format_id>[^"]+)"[^>]+href="[^"]+"[^>]+class="[^"]*quality-btn-active[^"]*">(?P<height>[0-9]+)p',
                page)
            if m:
                f.update({
                    'format_id': m.group('format_id'),
                    'height': int(m.group('height')),
                })
            info_dict['formats'].append(f)
            if not info_dict['duration']:
                info_dict['duration'] = parse_duration(video.get('duration'))

        extract_format(webpage, 'default')

        for href, resolution in re.findall(
                r'<a[^>]+data-quality="[^"]+"[^>]+href="([^"]+)"[^>]+class="quality-btn"[^>]*>([0-9]+p)',
                webpage):
            webpage = self._download_webpage(
                self._BASE_URL + href, video_id,
                'Downloading %s version information' % resolution, fatal=False)
            if not webpage:
                # Manually report warning because empty page is returned when
                # invalid version is requested.
                self.report_warning('Unable to download %s version information' % resolution)
                continue
            extract_format(webpage, resolution)

        self._sort_formats(formats)

        return info_dict