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
|
from .common import InfoExtractor
from .once import OnceIE
from ..compat import compat_urllib_parse_unquote
from ..utils import (
ExtractorError,
int_or_none,
try_get,
unified_timestamp,
)
class VoxMediaVolumeIE(OnceIE):
_VALID_URL = r'https?://volume\.vox-cdn\.com/embed/(?P<id>[0-9a-f]{9})'
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
setup = self._parse_json(self._search_regex(
r'setup\s*=\s*({.+});', webpage, 'setup'), video_id)
player_setup = setup.get('player_setup') or setup
video_data = player_setup.get('video') or {}
formatted_metadata = video_data.get('formatted_metadata') or {}
info = {
'id': video_id,
'title': player_setup.get('title') or video_data.get('title_short'),
'description': video_data.get('description_long') or video_data.get('description_short'),
'thumbnail': formatted_metadata.get('thumbnail') or video_data.get('brightcove_thumbnail'),
'timestamp': unified_timestamp(formatted_metadata.get('video_publish_date')),
}
asset = try_get(setup, lambda x: x['embed_assets']['chorus'], dict) or {}
formats = []
hls_url = asset.get('hls_url')
if hls_url:
formats.extend(self._extract_m3u8_formats(
hls_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
mp4_url = asset.get('mp4_url')
if mp4_url:
tbr = self._search_regex(r'-(\d+)k\.', mp4_url, 'bitrate', default=None)
format_id = 'http'
if tbr:
format_id += '-' + tbr
formats.append({
'format_id': format_id,
'url': mp4_url,
'tbr': int_or_none(tbr),
})
if formats:
info['formats'] = formats
info['duration'] = int_or_none(asset.get('duration'))
return info
for provider_video_type in ('youtube', 'brightcove'):
provider_video_id = video_data.get('%s_id' % provider_video_type)
if not provider_video_id:
continue
if provider_video_type == 'brightcove':
info['formats'] = self._extract_once_formats(provider_video_id)
else:
info.update({
'_type': 'url_transparent',
'url': provider_video_id if provider_video_type == 'youtube' else '%s:%s' % (provider_video_type, provider_video_id),
'ie_key': provider_video_type.capitalize(),
})
return info
raise ExtractorError('Unable to find provider video id')
class VoxMediaIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:(?:theverge|vox|sbnation|eater|polygon|curbed|racked|funnyordie)\.com|recode\.net)/(?:[^/]+/)*(?P<id>[^/?]+)'
_EMBED_REGEX = [r'<iframe[^>]+?src="(?P<url>https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"']
_TESTS = [{
# Volume embed, Youtube
'url': 'http://www.theverge.com/2014/6/27/5849272/material-world-how-google-discovered-what-software-is-made-of',
'info_dict': {
'id': 'j4mLW6x17VM',
'ext': 'mp4',
'title': 'Material world: how Google discovered what software is made of',
'description': 'md5:dfc17e7715e3b542d66e33a109861382',
'upload_date': '20190710',
'uploader_id': 'TheVerge',
'uploader': 'The Verge',
},
'add_ie': ['Youtube'],
}, {
# Volume embed, Youtube
'url': 'http://www.theverge.com/2014/10/21/7025853/google-nexus-6-hands-on-photos-video-android-phablet',
'md5': 'fd19aa0cf3a0eea515d4fd5c8c0e9d68',
'info_dict': {
'id': 'Gy8Md3Eky38',
'ext': 'mp4',
'title': 'The Nexus 6: hands-on with Google\'s phablet',
'description': 'md5:d9f0216e5fb932dd2033d6db37ac3f1d',
'uploader_id': 'TheVerge',
'upload_date': '20141021',
'uploader': 'The Verge',
'timestamp': 1413907200,
},
'add_ie': ['Youtube'],
'skip': 'similar to the previous test',
}, {
# Volume embed, Youtube
'url': 'http://www.vox.com/2016/3/31/11336640/mississippi-lgbt-religious-freedom-bill',
'info_dict': {
'id': '22986359b',
'ext': 'mp4',
'title': "Mississippi's laws are so bad that its anti-LGBTQ law isn't needed to allow discrimination",
'description': 'md5:fc1317922057de31cd74bce91eb1c66c',
'upload_date': '20150915',
'timestamp': 1442332800,
'duration': 285,
},
'add_ie': ['Youtube'],
'skip': 'similar to the previous test',
}, {
# youtube embed
'url': 'http://www.vox.com/2016/3/24/11291692/robot-dance',
'md5': '83b3080489fb103941e549352d3e0977',
'info_dict': {
'id': 'FcNHTJU1ufM',
'ext': 'mp4',
'title': 'How "the robot" became the greatest novelty dance of all time',
'description': 'md5:b081c0d588b8b2085870cda55e6da176',
'upload_date': '20160324',
'uploader_id': 'voxdotcom',
'uploader': 'Vox',
},
'add_ie': ['Youtube'],
'skip': 'Page no longer contain videos',
}, {
# SBN.VideoLinkset.entryGroup multiple ooyala embeds
'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
'info_dict': {
'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
'title': '25 lies you will tell yourself on National Signing Day',
'description': 'It\'s the most self-delusional time of the year, and everyone\'s gonna tell the same lies together!',
},
'playlist': [{
'md5': '721fededf2ab74ae4176c8c8cbfe092e',
'info_dict': {
'id': 'p3cThlMjE61VDi_SD9JlIteSNPWVDBB9',
'ext': 'mp4',
'title': 'Buddy Hield vs Steph Curry (and the world)',
'description': 'Let’s dissect only the most important Final Four storylines.',
},
}, {
'md5': 'bf0c5cc115636af028be1bab79217ea9',
'info_dict': {
'id': 'BmbmVjMjE6esPHxdALGubTrouQ0jYLHj',
'ext': 'mp4',
'title': 'Chasing Cinderella 2016: Syracuse basketball',
'description': 'md5:e02d56b026d51aa32c010676765a690d',
},
}],
'skip': 'Page no longer contain videos',
}, {
# volume embed, Brightcove Once
'url': 'https://www.recode.net/2014/6/17/11628066/post-post-pc-ceo-the-full-code-conference-video-of-microsofts-satya',
'md5': '2dbc77b8b0bff1894c2fce16eded637d',
'info_dict': {
'id': '1231c973d',
'ext': 'mp4',
'title': 'Post-Post-PC CEO: The Full Code Conference Video of Microsoft\'s Satya Nadella',
'description': 'The longtime veteran was chosen earlier this year as the software giant\'s third leader in its history.',
'timestamp': 1402938000,
'upload_date': '20140616',
'duration': 4114,
},
'add_ie': ['VoxMediaVolume'],
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = compat_urllib_parse_unquote(self._download_webpage(url, display_id))
def create_entry(provider_video_id, provider_video_type, title=None, description=None):
video_url = {
'youtube': '%s',
'volume': 'http://volume.vox-cdn.com/embed/%s',
}[provider_video_type] % provider_video_id
return {
'_type': 'url_transparent',
'url': video_url,
'title': title or self._og_search_title(webpage),
'description': description or self._og_search_description(webpage),
}
entries = []
entries_data = self._search_regex([
r'Chorus\.VideoContext\.addVideo\((\[{.+}\])\);',
r'var\s+entry\s*=\s*({.+});',
r'SBN\.VideoLinkset\.entryGroup\(\s*(\[.+\])',
], webpage, 'video data', default=None)
if entries_data:
entries_data = self._parse_json(entries_data, display_id)
if isinstance(entries_data, dict):
entries_data = [entries_data]
for video_data in entries_data:
provider_video_id = video_data.get('provider_video_id')
provider_video_type = video_data.get('provider_video_type')
if provider_video_id and provider_video_type:
entries.append(create_entry(
provider_video_id, provider_video_type,
video_data.get('title'), video_data.get('description')))
volume_uuid = self._search_regex(
r'data-volume-uuid="([^"]+)"', webpage, 'volume uuid', default=None)
if volume_uuid:
entries.append(create_entry(volume_uuid, 'volume'))
if len(entries) == 1:
return entries[0]
else:
return self.playlist_result(entries, display_id, self._og_search_title(webpage), self._og_search_description(webpage))
|
