]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vice.py
2 from __future__
import unicode_literals
9 from .adobepass
import AdobePassIE
10 from .common
import InfoExtractor
11 from ..compat
import compat_HTTPError
22 class ViceBaseIE(AdobePassIE
):
23 def _extract_preplay_video(self
, url
, webpage
):
24 watch_hub_data
= extract_attributes(self
._search
_regex
(
25 r
'(?s)(<watch-hub\s*.+?</watch-hub>)', webpage
, 'watch hub'))
26 video_id
= watch_hub_data
['vms-id']
27 title
= watch_hub_data
['video-title']
30 is_locked
= watch_hub_data
.get('video-locked') == '1'
32 resource
= self
._get
_mvpd
_resource
(
33 'VICELAND', title
, video_id
,
34 watch_hub_data
.get('video-rating'))
35 query
['tvetoken'] = self
._extract
_mvpd
_auth
(url
, video_id
, 'VICELAND', resource
)
37 # signature generation algorithm is reverse engineered from signatureGenerator in
38 # webpack:///../shared/~/vice-player/dist/js/vice-player.js in
39 # https://www.viceland.com/assets/common/js/web.vendor.bundle.js
40 exp
= int(time
.time()) + 14400
43 'sign': hashlib
.sha512(('%s:GET:%d' % (video_id
, exp
)).encode()).hexdigest(),
47 host
= 'www.viceland' if is_locked
else self
._PREPLAY
_HOST
48 preplay
= self
._download
_json
('https://%s.com/en_us/preplay/%s' % (host
, video_id
), video_id
, query
=query
)
49 except ExtractorError
as e
:
50 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
== 400:
51 error
= json
.loads(e
.cause
.read().decode())
52 raise ExtractorError('%s said: %s' % (self
.IE_NAME
, error
['details']), expected
=True)
55 video_data
= preplay
['video']
56 base
= video_data
['base']
57 uplynk_preplay_url
= preplay
['preplayURL']
58 episode
= video_data
.get('episode', {})
59 channel
= video_data
.get('channel', {})
62 cc_url
= preplay
.get('ccURL')
69 '_type': 'url_transparent',
70 'url': uplynk_preplay_url
,
73 'description': base
.get('body') or base
.get('display_body'),
74 'thumbnail': watch_hub_data
.get('cover-image') or watch_hub_data
.get('thumbnail'),
75 'duration': int_or_none(video_data
.get('video_duration')) or parse_duration(watch_hub_data
.get('video-duration')),
76 'timestamp': int_or_none(video_data
.get('created_at'), 1000),
77 'age_limit': parse_age_limit(video_data
.get('video_rating')),
78 'series': video_data
.get('show_title') or watch_hub_data
.get('show-title'),
79 'episode_number': int_or_none(episode
.get('episode_number') or watch_hub_data
.get('episode')),
80 'episode_id': str_or_none(episode
.get('id') or video_data
.get('episode_id')),
81 'season_number': int_or_none(watch_hub_data
.get('season')),
82 'season_id': str_or_none(episode
.get('season_id')),
83 'uploader': channel
.get('base', {}).get('title') or watch_hub_data
.get('channel-title'),
84 'uploader_id': str_or_none(channel
.get('id')),
85 'subtitles': subtitles
,
86 'ie_key': 'UplynkPreplay',
90 class ViceIE(ViceBaseIE
):
91 _VALID_URL
= r
'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?videos?/(?P<id>[^/?#&]+)'
94 'url': 'http://www.vice.com/video/cowboy-capitalists-part-1',
95 'md5': 'e9d77741f9e42ba583e683cd170660f7',
97 'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp',
99 'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
102 'add_ie': ['Ooyala'],
104 'url': 'http://www.vice.com/video/how-to-hack-a-car',
105 'md5': 'a7ecf64ee4fa19b916c16f4b56184ae2',
109 'title': 'How to Hack a Car: Phreaked Out (Episode 2)',
110 'description': 'md5:ee95453f7ff495db8efe14ae8bf56f30',
111 'uploader_id': 'MotherboardTV',
112 'uploader': 'Motherboard',
113 'upload_date': '20140529',
115 'add_ie': ['Youtube'],
117 'url': 'https://video.vice.com/en_us/video/the-signal-from-tolva/5816510690b70e6c5fd39a56',
120 'id': '5816510690b70e6c5fd39a56',
122 'uploader': 'Waypoint',
123 'title': 'The Signal From Tölva',
124 'uploader_id': '57f7d621e05ca860fa9ccaf9',
125 'timestamp': 1477941983938,
129 'skip_download': True,
131 'add_ie': ['UplynkPreplay'],
133 'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab',
134 'only_matching': True,
136 'url': 'http://www.vice.com/ru/video/big-night-out-ibiza-clive-martin-229',
137 'only_matching': True,
139 'url': 'https://munchies.vice.com/en/videos/watch-the-trailer-for-our-new-series-the-pizza-show',
140 'only_matching': True,
142 _PREPLAY_HOST
= 'video.vice'
144 def _real_extract(self
, url
):
145 video_id
= self
._match
_id
(url
)
146 webpage
, urlh
= self
._download
_webpage
_handle
(url
, video_id
)
147 embed_code
= self
._search
_regex
(
148 r
'embedCode=([^&\'"]+)', webpage,
149 'ooyala embed code', default=None)
151 return self.url_result('ooyala:%s' % embed_code, 'Ooyala')
152 youtube_id = self._search_regex(
153 r'data-youtube-id="([^
"]+)"', webpage, 'youtube
id', default=None)
155 return self.url_result(youtube_id, 'Youtube
')
156 return self._extract_preplay_video(urlh.geturl(), webpage)
159 class ViceShowIE(InfoExtractor):
160 _VALID_URL = r'https?
://(?
:.+?\
.)?vice\
.com
/(?
:[^
/]+/)?show
/(?P
<id>[^
/?
#&]+)'
163 'url': 'https://munchies.vice.com/en/show/fuck-thats-delicious-2',
165 'id': 'fuck-thats-delicious-2',
166 'title': "Fuck, That's Delicious",
167 'description': 'Follow the culinary adventures of rapper Action Bronson during his ongoing world tour.',
169 'playlist_count': 17,
172 def _real_extract(self
, url
):
173 show_id
= self
._match
_id
(url
)
174 webpage
= self
._download
_webpage
(url
, show_id
)
177 self
.url_result(video_url
, ViceIE
.ie_key())
178 for video_url
, _
in re
.findall(
179 r
'<h2[^>]+class="article-title"[^>]+data-id="\d+"[^>]*>\s*<a[^>]+href="(%s.*?)"'
180 % ViceIE
._VALID
_URL
, webpage
)]
182 title
= self
._search
_regex
(
183 r
'<title>(.+?)</title>', webpage
, 'title', default
=None)
185 title
= re
.sub(r
'(.+)\s*\|\s*.+$', r
'\1', title
).strip()
186 description
= self
._html
_search
_meta
('description', webpage
, 'description')
188 return self
.playlist_result(entries
, show_id
, title
, description
)