]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/drtv.py
2 from __future__
import unicode_literals
4 from .common
import InfoExtractor
16 class DRTVIE(InfoExtractor
):
17 _VALID_URL
= r
'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder|radio/ondemand)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
19 _GEO_COUNTRIES
= ['DK']
22 'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10',
23 'md5': '7ae17b4e18eb5d29212f424a7511c184',
25 'id': 'klassen-darlig-taber-10',
27 'title': 'Klassen - Dårlig taber (10)',
28 'description': 'md5:815fe1b7fa656ed80580f31e8b3c79aa',
29 'timestamp': 1471991907,
30 'upload_date': '20160823',
35 'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang',
37 'id': 'christiania-pusher-street-ryddes-drdkrjpo',
39 'title': 'LIVE Christianias rydning af Pusher Street er i gang',
40 'description': 'md5:2a71898b15057e9b97334f61d04e6eb5',
41 'timestamp': 1472800279,
42 'upload_date': '20160902',
46 'skip_download': True,
49 # with SignLanguage formats
50 'url': 'https://www.dr.dk/tv/se/historien-om-danmark/-/historien-om-danmark-stenalder',
52 'id': 'historien-om-danmark-stenalder',
54 'title': 'Historien om Danmark: Stenalder (1)',
55 'description': 'md5:8c66dcbc1669bbc6f873879880f37f2a',
56 'timestamp': 1490401996,
57 'upload_date': '20170325',
59 'formats': 'mincount:20',
62 'skip_download': True,
66 def _real_extract(self
, url
):
67 video_id
= self
._match
_id
(url
)
69 webpage
= self
._download
_webpage
(url
, video_id
)
71 if '>Programmet er ikke længere tilgængeligt' in webpage
:
73 'Video %s is not available' % video_id
, expected
=True)
75 video_id
= self
._search
_regex
(
76 (r
'data-(?:material-identifier|episode-slug)="([^"]+)"',
77 r
'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
80 programcard
= self
._download
_json
(
81 'http://www.dr.dk/mu/programcard/expanded/%s' % video_id
,
82 video_id
, 'Downloading video JSON')
83 data
= programcard
['Data'][0]
85 title
= remove_end(self
._og
_search
_title
(
86 webpage
, default
=None), ' | TV | DR') or data
['Title']
87 description
= self
._og
_search
_description
(
88 webpage
, default
=None) or data
.get('Description')
90 timestamp
= parse_iso8601(data
.get('CreatedTime'))
95 restricted_to_denmark
= False
100 for asset
in data
['Assets']:
101 kind
= asset
.get('Kind')
103 thumbnail
= asset
.get('Uri')
104 elif kind
in ('VideoResource', 'AudioResource'):
105 duration
= float_or_none(asset
.get('DurationInMilliseconds'), 1000)
106 restricted_to_denmark
= asset
.get('RestrictedToDenmark')
107 asset_target
= asset
.get('Target')
108 for link
in asset
.get('Links', []):
109 uri
= link
.get('Uri')
112 target
= link
.get('Target')
113 format_id
= target
or ''
115 if asset_target
in ('SpokenSubtitles', 'SignLanguage'):
117 format_id
+= '-%s' % asset_target
119 f4m_formats
= self
._extract
_f
4m
_formats
(
120 uri
+ '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43',
121 video_id
, preference
, f4m_id
=format_id
, fatal
=False)
122 if kind
== 'AudioResource':
123 for f
in f4m_formats
:
125 formats
.extend(f4m_formats
)
126 elif target
== 'HLS':
127 formats
.extend(self
._extract
_m
3u8_formats
(
128 uri
, video_id
, 'mp4', entry_protocol
='m3u8_native',
129 preference
=preference
, m3u8_id
=format_id
,
132 bitrate
= link
.get('Bitrate')
134 format_id
+= '-%s' % bitrate
137 'format_id': format_id
,
138 'tbr': int_or_none(bitrate
),
139 'ext': link
.get('FileFormat'),
140 'vcodec': 'none' if kind
== 'AudioResource' else None,
141 'preference': preference
,
143 subtitles_list
= asset
.get('SubtitlesList')
144 if isinstance(subtitles_list
, list):
148 for subs
in subtitles_list
:
149 if not subs
.get('Uri'):
151 lang
= subs
.get('Language') or 'da'
152 subtitles
.setdefault(LANGS
.get(lang
, lang
), []).append({
154 'ext': mimetype2ext(subs
.get('MimeType')) or 'vtt'
157 if not formats
and restricted_to_denmark
:
158 self
.raise_geo_restricted(
159 'Unfortunately, DR is not allowed to show this program outside Denmark.',
160 countries
=self
._GEO
_COUNTRIES
)
162 self
._sort
_formats
(formats
)
167 'description': description
,
168 'thumbnail': thumbnail
,
169 'timestamp': timestamp
,
170 'duration': duration
,
172 'subtitles': subtitles
,
176 class DRTVLiveIE(InfoExtractor
):
177 IE_NAME
= 'drtv:live'
178 _VALID_URL
= r
'https?://(?:www\.)?dr\.dk/(?:tv|TV)/live/(?P<id>[\da-z-]+)'
179 _GEO_COUNTRIES
= ['DK']
181 'url': 'https://www.dr.dk/tv/live/dr1',
185 'title': 're:^DR1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
189 'skip_download': True,
193 def _real_extract(self
, url
):
194 channel_id
= self
._match
_id
(url
)
195 channel_data
= self
._download
_json
(
196 'https://www.dr.dk/mu-online/api/1.0/channel/' + channel_id
,
198 title
= self
._live
_title
(channel_data
['Title'])
201 for streaming_server
in channel_data
.get('StreamingServers', []):
202 server
= streaming_server
.get('Server')
205 link_type
= streaming_server
.get('LinkType')
206 for quality
in streaming_server
.get('Qualities', []):
207 for stream
in quality
.get('Streams', []):
208 stream_path
= stream
.get('Stream')
211 stream_url
= update_url_query(
212 '%s/%s' % (server
, stream_path
), {'b': ''})
213 if link_type
== 'HLS':
214 formats
.extend(self
._extract
_m
3u8_formats
(
215 stream_url
, channel_id
, 'mp4',
216 m3u8_id
=link_type
, fatal
=False, live
=True))
217 elif link_type
== 'HDS':
218 formats
.extend(self
._extract
_f
4m
_formats
(update_url_query(
219 '%s/%s' % (server
, stream_path
), {'hdcore': '3.7.0'}),
220 channel_id
, f4m_id
=link_type
, fatal
=False))
221 self
._sort
_formats
(formats
)
226 'thumbnail': channel_data
.get('PrimaryImageUri'),