2 from __future__
import unicode_literals
9 from .common
import InfoExtractor
10 from ..aes
import aes_cbc_decrypt
11 from ..compat
import compat_urllib_parse_unquote
27 class DRTVIE(InfoExtractor
):
31 (?:www\.)?dr\.dk/(?:tv/se|nyheder|radio(?:/ondemand)?)/(?:[^/]+/)*|
32 (?:www\.)?(?:dr\.dk|dr-massive\.com)/drtv/(?:se|episode|program)/
37 _GEO_COUNTRIES
= ['DK']
40 'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10',
41 'md5': '25e659cccc9a2ed956110a299fdf5983',
43 'id': 'klassen-darlig-taber-10',
45 'title': 'Klassen - Dårlig taber (10)',
46 'description': 'md5:815fe1b7fa656ed80580f31e8b3c79aa',
47 'timestamp': 1539085800,
48 'upload_date': '20181009',
51 'season': 'Klassen I',
53 'season_id': 'urn:dr:mu:bundle:57d7e8216187a4031cfd6f6b',
54 'episode': 'Episode 10',
58 'expected_warnings': ['Unable to download f4m manifest'],
61 'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang',
63 'id': 'urn:dr:mu:programcard:57c926176187a50a9c6e83c6',
65 'title': 'christiania pusher street ryddes drdkrjpo',
66 'description': 'md5:2a71898b15057e9b97334f61d04e6eb5',
67 'timestamp': 1472800279,
68 'upload_date': '20160902',
72 'skip_download': True,
74 'expected_warnings': ['Unable to download f4m manifest'],
76 # with SignLanguage formats
77 'url': 'https://www.dr.dk/tv/se/historien-om-danmark/-/historien-om-danmark-stenalder',
79 'id': 'historien-om-danmark-stenalder',
81 'title': 'Historien om Danmark: Stenalder',
82 'description': 'md5:8c66dcbc1669bbc6f873879880f37f2a',
83 'timestamp': 1546628400,
84 'upload_date': '20190104',
86 'formats': 'mincount:20',
89 'skip_download': True,
92 'url': 'https://www.dr.dk/radio/p4kbh/regionale-nyheder-kh4/p4-nyheder-2019-06-26-17-30-9',
93 'only_matching': True,
95 'url': 'https://www.dr.dk/drtv/se/bonderoeven_71769',
99 'title': 'Bonderøven (1:8)',
100 'description': 'md5:3cf18fc0d3b205745d4505f896af8121',
101 'timestamp': 1546542000,
102 'upload_date': '20190103',
106 'skip_download': True,
109 'url': 'https://www.dr.dk/drtv/episode/bonderoeven_71769',
110 'only_matching': True,
112 'url': 'https://dr-massive.com/drtv/se/bonderoeven_71769',
113 'only_matching': True,
115 'url': 'https://www.dr.dk/drtv/program/jagten_220924',
116 'only_matching': True,
119 def _real_extract(self
, url
):
120 video_id
= self
._match
_id
(url
)
122 webpage
= self
._download
_webpage
(url
, video_id
)
124 if '>Programmet er ikke længere tilgængeligt' in webpage
:
125 raise ExtractorError(
126 'Video %s is not available' % video_id
, expected
=True)
128 video_id
= self
._search
_regex
(
129 (r
'data-(?:material-identifier|episode-slug)="([^"]+)"',
130 r
'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
131 webpage
, 'video id', default
=None)
134 video_id
= self
._search
_regex
(
135 r
'(urn(?:%3A|:)dr(?:%3A|:)mu(?:%3A|:)programcard(?:%3A|:)[\da-f]+)',
136 webpage
, 'urn', default
=None)
138 video_id
= compat_urllib_parse_unquote(video_id
)
140 _PROGRAMCARD_BASE
= 'https://www.dr.dk/mu-online/api/1.4/programcard'
141 query
= {'expanded': 'true'}
144 programcard_url
= '%s/%s' % (_PROGRAMCARD_BASE
, video_id
)
146 programcard_url
= _PROGRAMCARD_BASE
147 page
= self
._parse
_json
(
149 r
'data\s*=\s*({.+?})\s*(?:;|</script)', webpage
,
150 'data'), '1')['cache']['page']
151 page
= page
[list(page
.keys())[0]]
153 page
, (lambda x
: x
['item'], lambda x
: x
['entries'][0]['item']),
155 video_id
= item
['customId'].split(':')[-1]
156 query
['productionnumber'] = video_id
158 data
= self
._download
_json
(
159 programcard_url
, video_id
, 'Downloading video JSON', query
=query
)
161 title
= str_or_none(data
.get('Title')) or re
.sub(
162 r
'\s*\|\s*(?:TV\s*\|\s*DR|DRTV)$', '',
163 self
._og
_search
_title
(webpage
))
164 description
= self
._og
_search
_description
(
165 webpage
, default
=None) or data
.get('Description')
167 timestamp
= unified_timestamp(
168 data
.get('PrimaryBroadcastStartTime') or data
.get('SortDateTime'))
173 restricted_to_denmark
= False
179 primary_asset
= data
.get('PrimaryAsset')
180 if isinstance(primary_asset
, dict):
181 assets
.append(primary_asset
)
182 secondary_assets
= data
.get('SecondaryAssets')
183 if isinstance(secondary_assets
, list):
184 for secondary_asset
in secondary_assets
:
185 if isinstance(secondary_asset
, dict):
186 assets
.append(secondary_asset
)
188 def hex_to_bytes(hex):
189 return binascii
.a2b_hex(hex.encode('ascii'))
194 data
= bytes_to_intlist(hex_to_bytes(e
[10:10 + n
]))
195 key
= bytes_to_intlist(hashlib
.sha256(
196 ('%s:sRBzYNXBzkKgnjj8pGtkACch' % a
).encode('utf-8')).digest())
197 iv
= bytes_to_intlist(hex_to_bytes(a
))
198 decrypted
= aes_cbc_decrypt(data
, key
, iv
)
199 return intlist_to_bytes(
200 decrypted
[:-decrypted
[-1]]).decode('utf-8').split('?')[0]
203 kind
= asset
.get('Kind')
205 thumbnail
= url_or_none(asset
.get('Uri'))
206 elif kind
in ('VideoResource', 'AudioResource'):
207 duration
= float_or_none(asset
.get('DurationInMilliseconds'), 1000)
208 restricted_to_denmark
= asset
.get('RestrictedToDenmark')
209 asset_target
= asset
.get('Target')
210 for link
in asset
.get('Links', []):
211 uri
= link
.get('Uri')
213 encrypted_uri
= link
.get('EncryptedUri')
214 if not encrypted_uri
:
217 uri
= decrypt_uri(encrypted_uri
)
220 'Unable to decrypt EncryptedUri', video_id
)
222 uri
= url_or_none(uri
)
225 target
= link
.get('Target')
226 format_id
= target
or ''
227 if asset_target
in ('SpokenSubtitles', 'SignLanguage', 'VisuallyInterpreted'):
229 format_id
+= '-%s' % asset_target
230 elif asset_target
== 'Default':
235 f4m_formats
= self
._extract
_f
4m
_formats
(
236 uri
+ '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43',
237 video_id
, preference
, f4m_id
=format_id
, fatal
=False)
238 if kind
== 'AudioResource':
239 for f
in f4m_formats
:
241 formats
.extend(f4m_formats
)
242 elif target
== 'HLS':
243 formats
.extend(self
._extract
_m
3u8_formats
(
244 uri
, video_id
, 'mp4', entry_protocol
='m3u8_native',
245 quality
=preference
, m3u8_id
=format_id
,
248 bitrate
= link
.get('Bitrate')
250 format_id
+= '-%s' % bitrate
253 'format_id': format_id
,
254 'tbr': int_or_none(bitrate
),
255 'ext': link
.get('FileFormat'),
256 'vcodec': 'none' if kind
== 'AudioResource' else None,
257 'quality': preference
,
259 subtitles_list
= asset
.get('SubtitlesList') or asset
.get('Subtitleslist')
260 if isinstance(subtitles_list
, list):
264 for subs
in subtitles_list
:
265 if not isinstance(subs
, dict):
267 sub_uri
= url_or_none(subs
.get('Uri'))
270 lang
= subs
.get('Language') or 'da'
271 subtitles
.setdefault(LANGS
.get(lang
, lang
), []).append({
273 'ext': mimetype2ext(subs
.get('MimeType')) or 'vtt'
276 if not formats
and restricted_to_denmark
:
277 self
.raise_geo_restricted(
278 'Unfortunately, DR is not allowed to show this program outside Denmark.',
279 countries
=self
._GEO
_COUNTRIES
)
281 self
._sort
_formats
(formats
)
286 'description': description
,
287 'thumbnail': thumbnail
,
288 'timestamp': timestamp
,
289 'duration': duration
,
291 'subtitles': subtitles
,
292 'series': str_or_none(data
.get('SeriesTitle')),
293 'season': str_or_none(data
.get('SeasonTitle')),
294 'season_number': int_or_none(data
.get('SeasonNumber')),
295 'season_id': str_or_none(data
.get('SeasonUrn')),
296 'episode': str_or_none(data
.get('EpisodeTitle')),
297 'episode_number': int_or_none(data
.get('EpisodeNumber')),
298 'release_year': int_or_none(data
.get('ProductionYear')),
302 class DRTVLiveIE(InfoExtractor
):
303 IE_NAME
= 'drtv:live'
304 _VALID_URL
= r
'https?://(?:www\.)?dr\.dk/(?:tv|TV)/live/(?P<id>[\da-z-]+)'
305 _GEO_COUNTRIES
= ['DK']
307 'url': 'https://www.dr.dk/tv/live/dr1',
311 'title': 're:^DR1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
315 'skip_download': True,
319 def _real_extract(self
, url
):
320 channel_id
= self
._match
_id
(url
)
321 channel_data
= self
._download
_json
(
322 'https://www.dr.dk/mu-online/api/1.0/channel/' + channel_id
,
324 title
= self
._live
_title
(channel_data
['Title'])
327 for streaming_server
in channel_data
.get('StreamingServers', []):
328 server
= streaming_server
.get('Server')
331 link_type
= streaming_server
.get('LinkType')
332 for quality
in streaming_server
.get('Qualities', []):
333 for stream
in quality
.get('Streams', []):
334 stream_path
= stream
.get('Stream')
337 stream_url
= update_url_query(
338 '%s/%s' % (server
, stream_path
), {'b': ''}
)
339 if link_type
== 'HLS':
340 formats
.extend(self
._extract
_m
3u8_formats
(
341 stream_url
, channel_id
, 'mp4',
342 m3u8_id
=link_type
, fatal
=False, live
=True))
343 elif link_type
== 'HDS':
344 formats
.extend(self
._extract
_f
4m
_formats
(update_url_query(
345 '%s/%s' % (server
, stream_path
), {'hdcore': '3.7.0'}
),
346 channel_id
, f4m_id
=link_type
, fatal
=False))
347 self
._sort
_formats
(formats
)
352 'thumbnail': channel_data
.get('PrimaryImageUri'),