]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/medialaan.py
1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
6 from ..compat
import compat_str
17 class MedialaanIE(InfoExtractor
):
22 (?P<site_id>vtm|q2|vtmkzoom)\.be/
24 video(?:/[^/]+/id/|/?\?.*?\baid=)|
30 _NETRC_MACHINE
= 'medialaan'
31 _APIKEY
= '3_HZ0FtkMW_gOyKlqQzW5_0FHRC7Nd5XpXJZcDdXY4pk5eES2ZWmejRW5egwVm4ug-'
35 'vtmkzoom': 'vtmkzoom',
39 'url': 'http://vtm.be/video/volledige-afleveringen/id/vtm_20170219_VM0678361_vtmwatch',
41 'id': 'vtm_20170219_VM0678361_vtmwatch',
43 'title': 'Allemaal Chris afl. 6',
44 'description': 'md5:4be86427521e7b07e0adb0c9c554ddb2',
45 'timestamp': 1487533280,
46 'upload_date': '20170219',
48 'series': 'Allemaal Chris',
49 'season': 'Allemaal Chris',
51 'season_id': '256936078124527',
52 'episode': 'Allemaal Chris afl. 6',
54 'episode_id': '256936078591527',
57 'skip_download': True,
59 'skip': 'Requires account credentials',
62 'url': 'http://vtm.be/video?aid=168332',
66 'title': '"Veronique liegt!"',
67 'description': 'md5:1385e2b743923afe54ba4adc38476155',
68 'timestamp': 1489002029,
69 'upload_date': '20170308',
74 'url': 'http://vtm.be/video/volledige-afleveringen/id/257107153551000',
75 'only_matching': True,
78 'url': 'http://vtm.be/video?aid=163157',
79 'only_matching': True,
82 'url': 'http://www.q2.be/video/volledige-afleveringen/id/2be_20170301_VM0684442_q2',
83 'only_matching': True,
86 'url': 'http://vtmkzoom.be/k3-dansstudio/een-nieuw-seizoen-van-k3-dansstudio',
87 'only_matching': True,
90 'url': 'https://vtmkzoom.be/video?aid=45724',
92 'id': '257136373657000',
94 'title': 'K3 Dansstudio Ushuaia afl.6',
97 'skip_download': True,
99 'skip': 'Requires account credentials',
102 'url': 'https://nieuws.vtm.be/stadion/stadion/genk-nog-moeilijk-programma',
103 'only_matching': True,
106 def _real_initialize(self
):
107 self
._logged
_in
= False
110 username
, password
= self
._get
_login
_info
()
112 self
.raise_login_required()
115 'APIKey': self
._APIKEY
,
119 'password': password
,
122 auth_info
= self
._download
_json
(
123 'https://accounts.eu1.gigya.com/accounts.login', None,
124 note
='Logging in', errnote
='Unable to log in',
125 data
=urlencode_postdata(auth_data
))
127 error_message
= auth_info
.get('errorDetails') or auth_info
.get('errorMessage')
129 raise ExtractorError(
130 'Unable to login: %s' % error_message
, expected
=True)
132 self
._uid
= auth_info
['UID']
133 self
._uid
_signature
= auth_info
['UIDSignature']
134 self
._signature
_timestamp
= auth_info
['signatureTimestamp']
136 self
._logged
_in
= True
138 def _real_extract(self
, url
):
139 mobj
= re
.match(self
._VALID
_URL
, url
)
140 video_id
, site_id
= mobj
.group('id', 'site_id')
142 webpage
= self
._download
_webpage
(url
, video_id
)
144 config
= self
._parse
_json
(
146 r
'videoJSConfig\s*=\s*JSON\.parse\(\'({.+?}
)\'\
);',
147 webpage, 'config
', default='{}'), video_id,
148 transform_source=lambda s: s.replace(
149 '\\\\', '\\').replace(r'\"', '"').replace(r"\'", "'"))
151 vod_id = config.get('vodId
') or self._search_regex(
152 (r'\\"vodId\\"\s
*:\s
*\\"(.+?)\\"',
153 r'<[^
>]+id=["\']vod-(\d+)'),
154 webpage, 'video_id', default=None)
156 # clip, no authentication required
158 player = self._parse_json(
160 r'vmmaplayer\(({.+?})\);', webpage, 'vmma player',
162 video_id, transform_source=lambda s: '[%s]' % s, fatal=False)
165 if video['videoUrl'] in ('http', 'https'):
166 return self.url_result(video['url'], MedialaanIE.ie_key())
169 'url': video['videoUrl'],
170 'title': video['title'],
171 'thumbnail': video.get('imageUrl'),
172 'timestamp': int_or_none(video.get('createdDate')),
173 'duration': int_or_none(video.get('duration')),
176 info = self._parse_html5_media_entries(
177 url, webpage, video_id, m3u8_id='hls')[0]
180 'title': self._html_search_meta('description', webpage),
181 'duration': parse_duration(self._html_search_meta('duration', webpage)),
183 # vod, authentication required
185 if not self._logged_in:
188 settings = self._parse_json(
190 r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
191 webpage, 'drupal settings', default='{}'),
194 def get(container, item):
196 settings, lambda x: x[container][item],
197 compat_str) or self._search_regex(
198 r'"%s"\s*:\s*"([^
"]+)' % item, webpage, item,
201 app_id = get('vod', 'app_id') or self._SITE_TO_APP_ID.get(site_id, 'vtm_watch')
202 sso = get('vod', 'gigyaDatabase') or 'vtm-sso'
204 data = self._download_json(
205 'http://vod.medialaan.io/api/1.0/item/%s/video' % vod_id,
210 'UIDSignature': self._uid_signature,
211 'signatureTimestamp': self._signature_timestamp,
214 formats = self._extract_m3u8_formats(
215 data['response']['uri'], video_id, entry_protocol='m3u8_native',
216 ext='mp4', m3u8_id='hls')
218 self._sort_formats(formats)
225 api_key = get('vod', 'apiKey')
226 channel = get('medialaanGigya', 'channel')
229 videos = self._download_json(
230 'http://vod.medialaan.io/vod/v2/videos', video_id, fatal=False,
239 videos, lambda x: x['response']['videos'][0], dict)
241 def get(container, item, expected_type=None):
243 video, lambda x: x[container][item], expected_type)
245 def get_string(container, item):
246 return get(container, item, compat_str)
249 'series': get_string('program', 'title'),
250 'season': get_string('season', 'title'),
251 'season_number': int_or_none(get('season', 'number')),
252 'season_id': get_string('season', 'id'),
253 'episode': get_string('episode', 'title'),
254 'episode_number': int_or_none(get('episode', 'number')),
255 'episode_id': get_string('episode', 'id'),
256 'duration': int_or_none(
257 video.get('duration')) or int_or_none(
258 video.get('durationMillis'), scale=1000),
259 'title': get_string('episode', 'title'),
260 'description': get_string('episode', 'text'),
261 'timestamp': unified_timestamp(get_string(
262 'publication', 'begin')),
265 if not info.get('title'):
266 info['title'] = try_get(
267 config, lambda x: x['videoConfig']['title'],
268 compat_str) or self._html_search_regex(
269 r'\\"title
\\"\s*:\s*\\"(.+?
)\\"', webpage, 'title',
270 default=None) or self._og_search_title(webpage)
272 if not info.get('description'):
273 info['description'] = self._html_search_regex(
274 r'<div[^>]+class="field
-item\s
+even
">\s*<p>(.+?)</p>',
275 webpage, 'description', default=None)