about summary refs log tree commit diff
path: root/youtube_dl/extractor/crackle.py
blob: 13f425b2bf1672c66a723f22a0e6e3d73c0456c3 (plain) (blame)
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
# coding: utf-8
from __future__ import unicode_literals, division

from .common import InfoExtractor
from ..utils import int_or_none


class CrackleIE(InfoExtractor):
    _GEO_COUNTRIES = ['US']
    _VALID_URL = r'(?:crackle:|https?://(?:(?:www|m)\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
    _TEST = {
        'url': 'http://www.crackle.com/comedians-in-cars-getting-coffee/2498934',
        'info_dict': {
            'id': '2498934',
            'ext': 'mp4',
            'title': 'Everybody Respects A Bloody Nose',
            'description': 'Jerry is kaffeeklatsching in L.A. with funnyman J.B. Smoove (Saturday Night Live, Real Husbands of Hollywood). They’re headed for brew at 10 Speed Coffee in a 1964 Studebaker Avanti.',
            'thumbnail': r're:^https?://.*\.jpg',
            'duration': 906,
            'series': 'Comedians In Cars Getting Coffee',
            'season_number': 8,
            'episode_number': 4,
            'subtitles': {
                'en-US': [
                    {'ext': 'vtt'},
                    {'ext': 'tt'},
                ]
            },
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        }
    }

    _THUMBNAIL_RES = [
        (120, 90),
        (208, 156),
        (220, 124),
        (220, 220),
        (240, 180),
        (250, 141),
        (315, 236),
        (320, 180),
        (360, 203),
        (400, 300),
        (421, 316),
        (460, 330),
        (460, 460),
        (462, 260),
        (480, 270),
        (587, 330),
        (640, 480),
        (700, 330),
        (700, 394),
        (854, 480),
        (1024, 1024),
        (1920, 1080),
    ]

    # extracted from http://legacyweb-us.crackle.com/flash/ReferrerRedirect.ashx
    _MEDIA_FILE_SLOTS = {
        'c544.flv': {
            'width': 544,
            'height': 306,
        },
        '360p.mp4': {
            'width': 640,
            'height': 360,
        },
        '480p.mp4': {
            'width': 852,
            'height': 478,
        },
        '480p_1mbps.mp4': {
            'width': 852,
            'height': 478,
        },
    }

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

        config_doc = self._download_xml(
            'http://legacyweb-us.crackle.com/flash/QueryReferrer.ashx?site=16',
            video_id, 'Downloading config')

        item = self._download_xml(
            'http://legacyweb-us.crackle.com/app/revamp/vidwallcache.aspx?flags=-1&fm=%s' % video_id,
            video_id, headers=self.geo_verification_headers()).find('i')
        title = item.attrib['t']

        subtitles = {}
        formats = self._extract_m3u8_formats(
            'http://content.uplynk.com/ext/%s/%s.m3u8' % (config_doc.attrib['strUplynkOwnerId'], video_id),
            video_id, 'mp4', m3u8_id='hls', fatal=None)
        thumbnails = []
        path = item.attrib.get('p')
        if path:
            for width, height in self._THUMBNAIL_RES:
                res = '%dx%d' % (width, height)
                thumbnails.append({
                    'id': res,
                    'url': 'http://images-us-am.crackle.com/%stnl_%s.jpg' % (path, res),
                    'width': width,
                    'height': height,
                    'resolution': res,
                })
            http_base_url = 'http://ahttp.crackle.com/' + path
            for mfs_path, mfs_info in self._MEDIA_FILE_SLOTS.items():
                formats.append({
                    'url': http_base_url + mfs_path,
                    'format_id': 'http-' + mfs_path.split('.')[0],
                    'width': mfs_info['width'],
                    'height': mfs_info['height'],
                })
            for cc in item.findall('cc'):
                locale = cc.attrib.get('l')
                v = cc.attrib.get('v')
                if locale and v:
                    if locale not in subtitles:
                        subtitles[locale] = []
                    for url_ext, ext in (('vtt', 'vtt'), ('xml', 'tt')):
                        subtitles.setdefault(locale, []).append({
                            'url': '%s/%s%s_%s.%s' % (config_doc.attrib['strSubtitleServer'], path, locale, v, url_ext),
                            'ext': ext,
                        })
        self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))

        return {
            'id': video_id,
            'title': title,
            'description': item.attrib.get('d'),
            'duration': int(item.attrib.get('r'), 16) / 1000 if item.attrib.get('r') else None,
            'series': item.attrib.get('sn'),
            'season_number': int_or_none(item.attrib.get('se')),
            'episode_number': int_or_none(item.attrib.get('ep')),
            'thumbnails': thumbnails,
            'subtitles': subtitles,
            'formats': formats,
        }