2 from __future__ import unicode_literals
4 from .common import InfoExtractor
5 from ..compat import compat_urllib_parse_unquote
8 class VoxMediaIE(InfoExtractor):
9 _VALID_URL = r'https?://(?:www\.)?(?:theverge|vox|sbnation|eater|polygon|curbed|racked)\.com/(?:[^/]+/)*(?P<id>[^/?]+)'
11 'url': 'http://www.theverge.com/2014/6/27/5849272/material-world-how-google-discovered-what-software-is-made-of',
12 'md5': '73856edf3e89a711e70d5cf7cb280b37',
14 'id': '11eXZobjrG8DCSTgrNjVinU-YmmdYjhe',
16 'title': 'Google\'s new material design direction',
17 'description': 'md5:2f44f74c4d14a1f800ea73e1c6832ad2',
21 'url': 'http://www.theverge.com/2014/10/21/7025853/google-nexus-6-hands-on-photos-video-android-phablet',
22 'md5': 'd744484ff127884cd2ba09e3fa604e4b',
24 'id': 'RkZXU4cTphOCPDMZg5oEounJyoFI0g-B',
26 'title': 'The Nexus 6: hands-on with Google\'s phablet',
27 'description': 'md5:87a51fe95ff8cea8b5bdb9ac7ae6a6af',
31 'url': 'http://www.vox.com/2016/3/31/11336640/mississippi-lgbt-religious-freedom-bill',
32 'md5': '375c483c5080ab8cd85c9c84cfc2d1e4',
34 'id': 'wydzk3dDpmRz7PQoXRsTIX6XTkPjYL0b',
36 'title': 'The new frontier of LGBTQ civil rights, explained',
37 'description': 'md5:0dc58e94a465cbe91d02950f770eb93f',
41 'url': 'http://www.vox.com/2016/3/24/11291692/robot-dance',
42 'md5': '83b3080489fb103941e549352d3e0977',
46 'title': 'How "the robot" became the greatest novelty dance of all time',
47 'description': 'md5:b081c0d588b8b2085870cda55e6da176',
48 'upload_date': '20160324',
49 'uploader_id': 'voxdotcom',
53 # SBN.VideoLinkset.entryGroup multiple ooyala embeds
54 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
56 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
57 'title': '25 lies you will tell yourself on National Signing Day',
58 'description': 'It\'s the most self-delusional time of the year, and everyone\'s gonna tell the same lies together!',
61 'md5': '721fededf2ab74ae4176c8c8cbfe092e',
63 'id': 'p3cThlMjE61VDi_SD9JlIteSNPWVDBB9',
65 'title': 'Buddy Hield vs Steph Curry (and the world)',
66 'description': 'Let’s dissect only the most important Final Four storylines.',
69 'md5': 'bf0c5cc115636af028be1bab79217ea9',
71 'id': 'BmbmVjMjE6esPHxdALGubTrouQ0jYLHj',
73 'title': 'Chasing Cinderella 2016: Syracuse basketball',
74 'description': 'md5:e02d56b026d51aa32c010676765a690d',
79 def _real_extract(self, url):
80 display_id = self._match_id(url)
81 webpage = compat_urllib_parse_unquote(self._download_webpage(url, display_id))
83 def create_entry(provider_video_id, provider_video_type, title=None, description=None):
85 '_type': 'url_transparent',
86 'url': provider_video_id if provider_video_type == 'youtube' else '%s:%s' % (provider_video_type, provider_video_id),
87 'title': title or self._og_search_title(webpage),
88 'description': description or self._og_search_description(webpage),
92 entries_data = self._search_regex([
93 r'Chorus\.VideoContext\.addVideo\((\[{.+}\])\);',
94 r'var\s+entry\s*=\s*({.+});',
95 r'SBN\.VideoLinkset\.entryGroup\(\s*(\[.+\])',
96 ], webpage, 'video data', default=None)
98 entries_data = self._parse_json(entries_data, display_id)
99 if isinstance(entries_data, dict):
100 entries_data = [entries_data]
101 for video_data in entries_data:
102 provider_video_id = video_data.get('provider_video_id')
103 provider_video_type = video_data.get('provider_video_type')
104 if provider_video_id and provider_video_type:
105 entries.append(create_entry(
106 provider_video_id, provider_video_type,
107 video_data.get('title'), video_data.get('description')))
109 provider_video_id = self._search_regex(
110 r'data-ooyala-id="([^"]+)"', webpage, 'ooyala id', default=None)
111 if provider_video_id:
112 entries.append(create_entry(provider_video_id, 'ooyala'))
114 volume_uuid = self._search_regex(
115 r'data-volume-uuid="([^"]+)"', webpage, 'volume uuid', default=None)
117 volume_webpage = self._download_webpage(
118 'http://volume.vox-cdn.com/embed/%s' % volume_uuid, volume_uuid)
119 video_data = self._parse_json(self._search_regex(
120 r'Volume\.createVideo\(({.+})\s*,\s*{.*}\);', volume_webpage, 'video data'), volume_uuid)
121 for provider_video_type in ('ooyala', 'youtube'):
122 provider_video_id = video_data.get('%s_id' % provider_video_type)
123 if provider_video_id:
124 description = video_data.get('description_long') or video_data.get('description_short')
125 entries.append(create_entry(
126 provider_video_id, provider_video_type, video_data.get('title_short'), description))
129 if len(entries) == 1:
132 return self.playlist_result(entries, display_id, self._og_search_title(webpage), self._og_search_description(webpage))