2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
8 compat_urllib_parse_urlparse
,
22 class CondeNastIE(InfoExtractor
):
24 Condé Nast is a media group, some of its sites use a custom HTML5 player
25 that works the same in all of them.
28 # The keys are the supported sites and the values are the name to be shown
29 # to the user and in the extractor description.
32 'architecturaldigest': 'Architectural Digest',
33 'arstechnica': 'Ars Technica',
34 'bonappetit': 'Bon Appétit',
36 'cnevids': 'Condé Nast',
37 'cntraveler': 'Condé Nast Traveler',
39 'epicurious': 'Epicurious',
41 'golfdigest': 'Golf Digest',
43 'newyorker': 'The New Yorker',
45 'teenvogue': 'Teen Vogue',
46 'vanityfair': 'Vanity Fair',
49 'wmagazine': 'W Magazine',
52 _VALID_URL
= r
'''(?x)https?://(?:video|www|player(?:-backend)?)\.(?:%s)\.com/
56 (?:script|inline)/video
57 )/(?P<id>[0-9a-f]{24})(?:/(?P<player_id>[0-9a-f]{24}))?(?:.+?\btarget=(?P<target>[^&]+))?|
58 (?P<type>watch|series|video)/(?P<display_id>[^/?#]+)
59 )''' % '|'.join(_SITES
.keys())
60 IE_DESC
= 'Condé Nast media group: %s' % ', '.join(sorted(_SITES
.values()))
62 EMBED_URL
= r
'(?:https?:)?//player(?:-backend)?\.(?:%s)\.com/(?:embed(?:js)?|(?:script|inline)/video)/.+?' % '|'.join(_SITES
.keys())
65 'url': 'http://video.wired.com/watch/3d-printed-speakers-lit-with-led',
66 'md5': '1921f713ed48aabd715691f774c451f7',
68 'id': '5171b343c2b4c00dd0c1ccb3',
70 'title': '3D Printed Speakers Lit With LED',
71 'description': 'Check out these beautiful 3D printed LED speakers. You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.',
73 'upload_date': '20130314',
74 'timestamp': 1363219200,
77 'url': 'http://video.gq.com/watch/the-closer-with-keith-olbermann-the-only-true-surprise-trump-s-an-idiot?c=series',
79 'id': '58d1865bfd2e6126e2000015',
81 'title': 'The Only True Surprise? Trump’s an Idiot',
83 'upload_date': '20170321',
84 'timestamp': 1490126427,
88 'url': 'http://player.cnevids.com/embedjs/55f9cf8b61646d1acf00000c/5511d76261646d5566020000.js',
89 'md5': 'f1a6f9cafb7083bab74a710f65d08999',
91 'id': '55f9cf8b61646d1acf00000c',
93 'title': '3D printed TSA Travel Sentry keys really do open TSA locks',
94 'uploader': 'arstechnica',
95 'upload_date': '20150916',
96 'timestamp': 1442434955,
99 'url': 'https://player.cnevids.com/inline/video/59138decb57ac36b83000005.js?target=js-cne-player',
100 'only_matching': True,
102 'url': 'http://player-backend.cnevids.com/script/video/59138decb57ac36b83000005.js',
103 'only_matching': True,
106 def _extract_series(self
, url
, webpage
):
107 title
= self
._html
_search
_regex
(
108 r
'(?s)<div class="cne-series-info">.*?<h1>(.+?)</h1>',
109 webpage
, 'series title')
110 url_object
= compat_urllib_parse_urlparse(url
)
111 base_url
= '%s://%s' % (url_object
.scheme
, url_object
.netloc
)
112 m_paths
= re
.finditer(
113 r
'(?s)<p class="cne-thumb-title">.*?<a href="(/watch/.+?)["\?]', webpage
)
114 paths
= orderedSet(m
.group(1) for m
in m_paths
)
115 build_url
= lambda path
: compat_urlparse
.urljoin(base_url
, path
)
116 entries
= [self
.url_result(build_url(path
), 'CondeNast') for path
in paths
]
117 return self
.playlist_result(entries
, playlist_title
=title
)
119 def _extract_video_params(self
, webpage
, display_id
):
120 query
= self
._parse
_json
(
122 r
'(?s)var\s+params\s*=\s*({.+?})[;,]', webpage
, 'player params',
124 display_id
, transform_source
=js_to_json
, fatal
=False)
126 query
['videoId'] = self
._search
_regex
(
127 r
'(?:data-video-id=|currentVideoId\s*=\s*)["\']([\da
-f
]+)',
128 webpage, 'video
id', default=None)
130 params = extract_attributes(self._search_regex(
131 r'(<[^
>]+data
-js
="video-player"[^
>]+>)',
132 webpage, 'player params element
'))
134 'videoId
': params['data
-video
'],
135 'playerId
': params['data
-player
'],
136 'target
': params['id'],
140 def _extract_video(self, params):
141 video_id = params['videoId
']
146 query = params.copy()
147 query['embedType
'] = 'inline
'
148 info_page = self._download_json(
149 'http
://player
.cnevids
.com
/embed
-api
.json
', video_id,
150 'Downloading embed info
', fatal=False, query=query)
154 if params.get('playerId
'):
155 info_page = self._download_json(
156 'http
://player
.cnevids
.com
/player
/video
.js
', video_id,
157 'Downloading video info
', fatal=False, query=params)
159 video_info = info_page.get('video
')
161 info_page = self._download_webpage(
162 'http
://player
.cnevids
.com
/player
/loader
.js
',
163 video_id, 'Downloading loader info
', query=params)
165 info_page = self._download_webpage(
166 'https
://player
.cnevids
.com
/inline
/video
/%s.js
' % video_id,
167 video_id, 'Downloading inline info
', query={
168 'target
': params.get('target
', 'embedplayer
')
172 video_info = self._parse_json(
174 r'(?s
)var\s
+config\s
*=\s
*({.+?
});', info_page, 'config
'),
175 video_id, transform_source=js_to_json)['video
']
177 title = video_info['title
']
180 for fdata in video_info['sources
']:
181 src = fdata.get('src
')
184 ext = mimetype2ext(fdata.get('type')) or determine_ext(src)
186 formats.extend(self._extract_m3u8_formats(
187 src, video_id, 'mp4
', entry_protocol='m3u8_native
',
188 m3u8_id='hls
', fatal=False))
190 quality = fdata.get('quality
')
192 'format_id
': ext + ('-%s' % quality if quality else ''),
195 'quality
': 1 if quality == 'high
' else 0,
197 self._sort_formats(formats)
203 'thumbnail
': video_info.get('poster_frame
'),
204 'uploader
': video_info.get('brand
'),
205 'duration
': int_or_none(video_info.get('duration
')),
206 'tags
': video_info.get('tags
'),
207 'series
': video_info.get('series_title
'),
208 'season
': video_info.get('season_title
'),
209 'timestamp
': parse_iso8601(video_info.get('premiere_date
')),
210 'categories
': video_info.get('categories
'),
213 def _real_extract(self, url):
214 video_id, player_id, target, url_type, display_id = re.match(self._VALID_URL, url).groups()
217 return self._extract_video({
219 'playerId
': player_id,
223 webpage = self._download_webpage(url, display_id)
225 if url_type == 'series
':
226 return self._extract_series(url, webpage)
228 params = self._extract_video_params(webpage, display_id)
229 info = self._search_json_ld(
230 webpage, display_id, fatal=False)
231 info.update(self._extract_video(params))