aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/theplatform.py
blob: 48c6ff03f482a9489952f9bee9875ac0ee6a00b4 (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
from __future__ import unicode_literals

import re
import json
import time
import hmac
import binascii
import hashlib


from .common import InfoExtractor
from ..compat import (
    compat_str,
)
from ..utils import (
    determine_ext,
    ExtractorError,
    xpath_with_ns,
    unsmuggle_url,
    int_or_none,
)

_x = lambda p: xpath_with_ns(p, {'smil': 'http://www.w3.org/2005/SMIL21/Language'})


class ThePlatformIE(InfoExtractor):
    _VALID_URL = r'''(?x)
        (?:https?://(?:link|player)\.theplatform\.com/[sp]/(?P<provider_id>[^/]+)/
           (?:(?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/)|(?P<media>(?:[^/]+/)+select/media/))?
         |theplatform:)(?P<id>[^/\?&]+)'''

    _TESTS = [{
        # from http://www.metacafe.com/watch/cb-e9I_cZgTgIPd/blackberrys_big_bold_z30/
        'url': 'http://link.theplatform.com/s/dJ5BDC/e9I_cZgTgIPd/meta.smil?format=smil&Tracking=true&mbr=true',
        'info_dict': {
            'id': 'e9I_cZgTgIPd',
            'ext': 'flv',
            'title': 'Blackberry\'s big, bold Z30',
            'description': 'The Z30 is Blackberry\'s biggest, baddest mobile messaging device yet.',
            'duration': 247,
        },
        'params': {
            # rtmp download
            'skip_download': True,
        },
    }, {
        # from http://www.cnet.com/videos/tesla-model-s-a-second-step-towards-a-cleaner-motoring-future/
        'url': 'http://link.theplatform.com/s/kYEXFC/22d_qsQ6MIRT',
        'info_dict': {
            'id': '22d_qsQ6MIRT',
            'ext': 'flv',
            'description': 'md5:ac330c9258c04f9d7512cf26b9595409',
            'title': 'Tesla Model S: A second step towards a cleaner motoring future',
        },
        'params': {
            # rtmp download
            'skip_download': True,
        }
    }, {
        'url': 'https://player.theplatform.com/p/D6x-PC/pulse_preview/embed/select/media/yMBg9E8KFxZD',
        'info_dict': {
            'id': 'yMBg9E8KFxZD',
            'ext': 'mp4',
            'description': 'md5:644ad9188d655b742f942bf2e06b002d',
            'title': 'HIGHLIGHTS: USA bag first ever series Cup win',
        }
    }, {
        'url': 'http://player.theplatform.com/p/NnzsPC/widget/select/media/4Y0TlYUr_ZT7',
        'only_matching': True,
    }]

    @staticmethod
    def _sign_url(url, sig_key, sig_secret, life=600, include_qs=False):
        flags = '10' if include_qs else '00'
        expiration_date = '%x' % (int(time.time()) + life)

        def str_to_hex(str):
            return binascii.b2a_hex(str.encode('ascii')).decode('ascii')

        def hex_to_str(hex):
            return binascii.a2b_hex(hex)

        relative_path = url.split('http://link.theplatform.com/s/')[1].split('?')[0]
        clear_text = hex_to_str(flags + expiration_date + str_to_hex(relative_path))
        checksum = hmac.new(sig_key.encode('ascii'), clear_text, hashlib.sha1).hexdigest()
        sig = flags + expiration_date + checksum + str_to_hex(sig_secret)
        return '%s&sig=%s' % (url, sig)

    def _real_extract(self, url):
        url, smuggled_data = unsmuggle_url(url, {})

        mobj = re.match(self._VALID_URL, url)
        provider_id = mobj.group('provider_id')
        video_id = mobj.group('id')

        if not provider_id:
            provider_id = 'dJ5BDC'

        path = provider_id
        if mobj.group('media'):
            path += '/media'
        path += '/' + video_id

        if smuggled_data.get('force_smil_url', False):
            smil_url = url
        elif mobj.group('config'):
            config_url = url + '&form=json'
            config_url = config_url.replace('swf/', 'config/')
            config_url = config_url.replace('onsite/', 'onsite/config/')
            config = self._download_json(config_url, video_id, 'Downloading config')
            smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4&manifest=f4m'
        else:
            smil_url = 'http://link.theplatform.com/s/%s/meta.smil?format=smil&mbr=true' % path

        sig = smuggled_data.get('sig')
        if sig:
            smil_url = self._sign_url(smil_url, sig['key'], sig['secret'])

        meta = self._download_xml(smil_url, video_id)
        try:
            error_msg = next(
                n.attrib['abstract']
                for n in meta.findall(_x('.//smil:ref'))
                if n.attrib.get('title') == 'Geographic Restriction' or n.attrib.get('title') == 'Expired')
        except StopIteration:
            pass
        else:
            raise ExtractorError(error_msg, expected=True)

        info_url = 'http://link.theplatform.com/s/%s?format=preview' % path
        info_json = self._download_webpage(info_url, video_id)
        info = json.loads(info_json)

        subtitles = {}
        captions = info.get('captions')
        if isinstance(captions, list):
            for caption in captions:
                lang, src, mime = caption.get('lang', 'en'), caption.get('src'), caption.get('type')
                subtitles[lang] = [{
                    'ext': 'srt' if mime == 'text/srt' else 'ttml',
                    'url': src,
                }]

        head = meta.find(_x('smil:head'))
        body = meta.find(_x('smil:body'))

        f4m_node = body.find(_x('smil:seq//smil:video'))
        if f4m_node is None:
            f4m_node = body.find(_x('smil:seq/smil:video'))
        if f4m_node is not None and '.f4m' in f4m_node.attrib['src']:
            f4m_url = f4m_node.attrib['src']
            if 'manifest.f4m?' not in f4m_url:
                f4m_url += '?'
            # the parameters are from syfy.com, other sites may use others,
            # they also work for nbc.com
            f4m_url += '&g=UXWGVKRWHFSP&hdcore=3.0.3'
            formats = self._extract_f4m_formats(f4m_url, video_id)
        else:
            formats = []
            switch = body.find(_x('smil:switch'))
            if switch is None:
                switch = body.find(_x('smil:par//smil:switch'))
            if switch is None:
                switch = body.find(_x('smil:par/smil:switch'))
            if switch is None:
                switch = body.find(_x('smil:par'))
            if switch is not None:
                base_url = head.find(_x('smil:meta')).attrib['base']
                for f in switch.findall(_x('smil:video')):
                    attr = f.attrib
                    width = int_or_none(attr.get('width'))
                    height = int_or_none(attr.get('height'))
                    vbr = int_or_none(attr.get('system-bitrate'), 1000)
                    format_id = '%dx%d_%dk' % (width, height, vbr)
                    formats.append({
                        'format_id': format_id,
                        'url': base_url,
                        'play_path': 'mp4:' + attr['src'],
                        'ext': 'flv',
                        'width': width,
                        'height': height,
                        'vbr': vbr,
                    })
            else:
                switch = body.find(_x('smil:seq//smil:switch'))
                if switch is None:
                    switch = body.find(_x('smil:seq/smil:switch'))
                for f in switch.findall(_x('smil:video')):
                    attr = f.attrib
                    vbr = int_or_none(attr.get('system-bitrate'), 1000)
                    ext = determine_ext(attr['src'])
                    if ext == 'once':
                        ext = 'mp4'
                    formats.append({
                        'format_id': compat_str(vbr),
                        'url': attr['src'],
                        'vbr': vbr,
                        'ext': ext,
                    })
            self._sort_formats(formats)

        return {
            'id': video_id,
            'title': info['title'],
            'subtitles': subtitles,
            'formats': formats,
            'description': info['description'],
            'thumbnail': info['defaultThumbnailUrl'],
            'duration': int_or_none(info.get('duration'), 1000),
        }