]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/dplay.py
2 from __future__
import unicode_literals
8 from .common
import InfoExtractor
29 class DPlayIE(InfoExtractor
):
30 _VALID_URL
= r
'https?://(?P<domain>www\.(?P<host>dplay\.(?P<country>dk|se|no)))/(?:video(?:er|s)/)?(?P<id>[^/]+/[^/?#]+)'
33 # non geo restricted, via secure api, unsigned download hls URL
34 'url': 'http://www.dplay.se/nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet/',
37 'display_id': 'nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet',
39 'title': 'Svensken lär sig njuta av livet',
40 'description': 'md5:d3819c9bccffd0fe458ca42451dd50d8',
42 'timestamp': 1365454320,
43 'upload_date': '20130408',
44 'creator': 'Kanal 5 (Home)',
45 'series': 'Nugammalt - 77 händelser som format Sverige',
51 # geo restricted, via secure api, unsigned download hls URL
52 'url': 'http://www.dplay.dk/mig-og-min-mor/season-6-episode-12/',
55 'display_id': 'mig-og-min-mor/season-6-episode-12',
57 'title': 'Episode 12',
58 'description': 'md5:9c86e51a93f8a4401fc9641ef9894c90',
60 'timestamp': 1429696800,
61 'upload_date': '20150422',
62 'creator': 'Kanal 4 (Home)',
63 'series': 'Mig og min mor',
69 # geo restricted, via direct unsigned hls URL
70 'url': 'http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/',
71 'only_matching': True,
74 'url': 'https://www.dplay.no/videoer/i-kongens-klr/sesong-1-episode-7',
77 'display_id': 'i-kongens-klr/sesong-1-episode-7',
80 'description': 'md5:e3e1411b2b9aebeea36a6ec5d50c60cf',
82 'timestamp': 1516726800,
83 'upload_date': '20180123',
84 'series': 'I kongens klær',
89 'format': 'bestvideo',
90 'skip_download': True,
94 'url': 'https://www.dplay.dk/videoer/singleliv/season-5-episode-3',
95 'only_matching': True,
97 'url': 'https://www.dplay.se/videos/sofias-anglar/sofias-anglar-1001',
98 'only_matching': True,
101 def _get_disco_api_info(self
, url
, display_id
, disco_host
, realm
):
102 disco_base
= 'https://' + disco_host
103 token
= self
._download
_json
(
104 '%s/token' % disco_base
, display_id
, 'Downloading token',
107 })['data']['attributes']['token']
110 'Authorization': 'Bearer ' + token
,
112 video
= self
._download
_json
(
113 '%s/content/videos/%s' % (disco_base
, display_id
), display_id
,
114 headers
=headers
, query
={
117 video_id
= video
['data']['id']
118 info
= video
['data']['attributes']
121 for format_id
, format_dict
in self
._download
_json
(
122 '%s/playback/videoPlaybackInfo/%s' % (disco_base
, video_id
),
123 display_id
, headers
=headers
)['data']['attributes']['streaming'].items():
124 if not isinstance(format_dict
, dict):
126 format_url
= format_dict
.get('url')
129 ext
= determine_ext(format_url
)
130 if format_id
== 'dash' or ext
== 'mpd':
131 formats
.extend(self
._extract
_mpd
_formats
(
132 format_url
, display_id
, mpd_id
='dash', fatal
=False))
133 elif format_id
== 'hls' or ext
== 'm3u8':
134 formats
.extend(self
._extract
_m
3u8_formats
(
135 format_url
, display_id
, 'mp4',
136 entry_protocol
='m3u8_native', m3u8_id
='hls',
141 'format_id': format_id
,
143 self
._sort
_formats
(formats
)
147 included
= video
.get('included')
148 if isinstance(included
, list):
149 show
= next(e
for e
in included
if e
.get('type') == 'show')
151 show
, lambda x
: x
['attributes']['name'], compat_str
)
152 except StopIteration:
157 'display_id': display_id
,
159 'description': info
.get('description'),
160 'duration': float_or_none(
161 info
.get('videoDuration'), scale
=1000),
162 'timestamp': unified_timestamp(info
.get('publishStart')),
164 'season_number': int_or_none(info
.get('seasonNumber')),
165 'episode_number': int_or_none(info
.get('episodeNumber')),
166 'age_limit': int_or_none(info
.get('minimum_age')),
170 def _real_extract(self
, url
):
171 mobj
= re
.match(self
._VALID
_URL
, url
)
172 display_id
= mobj
.group('id')
173 domain
= mobj
.group('domain')
175 self
._initialize
_geo
_bypass
({
176 'countries': [mobj
.group('country').upper()],
179 webpage
= self
._download
_webpage
(url
, display_id
)
181 video_id
= self
._search
_regex
(
182 r
'data-video-id=["\'](\d
+)', webpage, 'video
id', default=None)
185 host = mobj.group('host
')
186 return self._get_disco_api_info(
187 url, display_id, 'disco
-api
.' + host, host.replace('.', ''))
189 info = self._download_json(
190 'http
://%s/api
/v2
/ajax
/videos?video_id
=%s' % (domain, video_id),
193 title = info['title
']
195 PROTOCOLS = ('hls
', 'hds
')
198 def extract_formats(protocol, manifest_url):
199 if protocol == 'hls
':
200 m3u8_formats = self._extract_m3u8_formats(
201 manifest_url, video_id, ext='mp4
',
202 entry_protocol='m3u8_native
', m3u8_id=protocol, fatal=False)
203 # Sometimes final URLs inside m3u8 are unsigned, let's fix this
204 # ourselves. Also fragments' URLs are only served signed for
206 query
= compat_urlparse
.parse_qs(compat_urlparse
.urlparse(manifest_url
).query
)
207 for m3u8_format
in m3u8_formats
:
209 'url': update_url_query(m3u8_format
['url'], query
),
211 'User-Agent': USER_AGENTS
['Safari'],
214 formats
.extend(m3u8_formats
)
215 elif protocol
== 'hds':
216 formats
.extend(self
._extract
_f
4m
_formats
(
217 manifest_url
+ '&hdcore=3.8.0&plugin=flowplayer-3.8.0.0',
218 video_id
, f4m_id
=protocol
, fatal
=False))
220 domain_tld
= domain
.split('.')[-1]
221 if domain_tld
in ('se', 'dk', 'no'):
222 for protocol
in PROTOCOLS
:
223 # Providing dsc-geo allows to bypass geo restriction in some cases
225 'secure.dplay.%s' % domain_tld
, 'dsc-geo',
227 'countryCode': domain_tld
.upper(),
228 'expiry': (time
.time() + 20 * 60) * 1000,
230 stream
= self
._download
_json
(
231 'https://secure.dplay.%s/secure/api/v2/user/authorization/stream/%s?stream_type=%s'
232 % (domain_tld
, video_id
, protocol
), video_id
,
233 'Downloading %s stream JSON' % protocol
, fatal
=False)
234 if stream
and stream
.get(protocol
):
235 extract_formats(protocol
, stream
[protocol
])
237 # The last resort is to try direct unsigned hls/hds URLs from info dictionary.
238 # Sometimes this does work even when secure API with dsc-geo has failed (e.g.
239 # http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/).
241 for protocol
in PROTOCOLS
:
242 if info
.get(protocol
):
243 extract_formats(protocol
, info
[protocol
])
245 self
._sort
_formats
(formats
)
248 for lang
in ('se', 'sv', 'da', 'nl', 'no'):
249 for format_id
in ('web_vtt', 'vtt', 'srt'):
250 subtitle_url
= info
.get('subtitles_%s_%s' % (lang
, format_id
))
252 subtitles
.setdefault(lang
, []).append({'url': subtitle_url
})
256 'display_id': display_id
,
258 'description': info
.get('video_metadata_longDescription'),
259 'duration': int_or_none(info
.get('video_metadata_length'), scale
=1000),
260 'timestamp': int_or_none(info
.get('video_publish_date')),
261 'creator': info
.get('video_metadata_homeChannel'),
262 'series': info
.get('video_metadata_show'),
263 'season_number': int_or_none(info
.get('season')),
264 'episode_number': int_or_none(info
.get('episode')),
265 'age_limit': int_or_none(info
.get('minimum_age')),
267 'subtitles': subtitles
,
271 class DPlayItIE(InfoExtractor
):
272 _VALID_URL
= r
'https?://it\.dplay\.com/[^/]+/[^/]+/(?P<id>[^/?#]+)'
273 _GEO_COUNTRIES
= ['IT']
275 'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/',
276 'md5': '2b808ffb00fc47b884a172ca5d13053c',
279 'display_id': 'luigi-di-maio-la-psicosi-di-stanislawskij',
281 'title': 'Biografie imbarazzanti: Luigi Di Maio: la psicosi di Stanislawskij',
282 'description': 'md5:3c7a4303aef85868f867a26f5cc14813',
283 'thumbnail': r
're:^https?://.*\.jpe?g',
284 'upload_date': '20160524',
285 'series': 'Biografie imbarazzanti',
287 'episode': 'Luigi Di Maio: la psicosi di Stanislawskij',
292 def _real_extract(self
, url
):
293 display_id
= self
._match
_id
(url
)
295 webpage
= self
._download
_webpage
(url
, display_id
)
297 title
= remove_end(self
._og
_search
_title
(webpage
), ' | Dplay')
301 info
= self
._search
_regex
(
302 r
'playback_json\s*:\s*JSON\.parse\s*\(\s*("(?:\\.|[^"\\])+?")',
303 webpage
, 'playback JSON', default
=None)
306 info
= self
._parse
_json
(info
, display_id
, fatal
=False)
310 video_id
= try_get(info
, lambda x
: x
['data']['id'])
313 info_url
= self
._search
_regex
(
314 (r
'playback_json_url\s*:\s*(["\'])(?P
<url
>(?
:(?
!\
1).)+)\
1',
315 r'url\s
*[:=]\s
*["\'](?P<url>(?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)'),
316 webpage, 'info url', group='url')
318 info_url = urljoin(url, info_url)
319 video_id = info_url.rpartition('/')[-1]
322 info = self._download_json(
323 info_url, display_id, headers={
324 'Authorization': 'Bearer %s' % self._get_cookies(url).get(
325 'dplayit_token').value,
328 if isinstance(info, compat_str):
329 info = self._parse_json(info, display_id)
330 except ExtractorError as e:
331 if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 403):
332 info = self._parse_json(e.cause.read().decode('utf-8'), display_id)
333 error = info['errors'][0]
334 if error.get('code') == 'access.denied.geoblocked':
335 self.raise_geo_restricted(
336 msg=error.get('detail'), countries=self._GEO_COUNTRIES)
337 raise ExtractorError(info['errors'][0]['detail'], expected=True)
340 hls_url = info['data']['attributes']['streaming']['hls']['url']
342 formats = self._extract_m3u8_formats(
343 hls_url, display_id, ext='mp4', entry_protocol='m3u8_native',
345 self._sort_formats(formats)
347 series = self._html_search_regex(
348 r'(?s)<h1[^>]+class=["\'].*?
\bshow
_title
\b.*?
["\'][^>]*>(.+?)</h1>',
349 webpage, 'series', fatal=False)
350 episode = self._search_regex(
351 r'<p[^>]+class=["\'].*?
\bdesc
_ep
\b.*?
["\'][^>]*>\s*<br/>\s*<b>([^<]+)',
352 webpage, 'episode', fatal=False)
355 r'(?s)<span[^>]+class=["\']dates
["\'][^>]*>.+?\bS\.(?P<season_number>\d+)\s+E\.(?P<episode_number>\d+)\s*-\s*(?P<upload_date>\d{2}/\d{2}/\d{4})',
358 season_number = int(mobj.group('season_number'))
359 episode_number = int(mobj.group('episode_number'))
360 upload_date = unified_strdate(mobj.group('upload_date'))
362 season_number = episode_number = upload_date = None
365 'id': compat_str(video_id or display_id),
366 'display_id': display_id,
368 'description': self._og_search_description(webpage),
369 'thumbnail': self._og_search_thumbnail(webpage),
371 'season_number': season_number,
373 'episode_number': episode_number,
374 'upload_date': upload_date,