]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/rte.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
14 class RteIE(InfoExtractor
):
16 IE_DESC
= 'Raidió Teilifís Éireann TV'
17 _VALID_URL
= r
'https?://(?:www\.)?rte\.ie/player/[^/]{2,3}/show/[^/]+/(?P<id>[0-9]+)'
19 'url': 'http://www.rte.ie/player/ie/show/iwitness-862/10478715/',
23 'title': 'Watch iWitness online',
24 'thumbnail': 're:^https?://.*\.jpg$',
25 'description': 'iWitness : The spirit of Ireland, one voice and one minute at a time.',
29 'skip_download': 'f4m fails with --test atm'
33 def _real_extract(self
, url
):
34 video_id
= self
._match
_id
(url
)
35 webpage
= self
._download
_webpage
(url
, video_id
)
37 title
= self
._og
_search
_title
(webpage
)
38 description
= self
._html
_search
_meta
('description', webpage
, 'description')
39 duration
= float_or_none(self
._html
_search
_meta
(
40 'duration', webpage
, 'duration', fatal
=False), 1000)
42 thumbnail_id
= self
._search
_regex
(
43 r
'<meta name="thumbnail" content="uri:irus:(.*?)" />', webpage
, 'thumbnail')
44 thumbnail
= 'http://img.rasset.ie/' + thumbnail_id
+ '.jpg'
46 feeds_url
= self
._html
_search
_meta
("feeds-prefix", webpage
, 'feeds url') + video_id
47 json_string
= self
._download
_json
(feeds_url
, video_id
)
49 # f4m_url = server + relative_url
50 f4m_url
= json_string
['shows'][0]['media:group'][0]['rte:server'] + json_string
['shows'][0]['media:group'][0]['url']
51 f4m_formats
= self
._extract
_f
4m
_formats
(f4m_url
, video_id
)
56 'formats': f4m_formats
,
57 'description': description
,
58 'thumbnail': thumbnail
,
63 class RteRadioIE(InfoExtractor
):
65 IE_DESC
= 'Raidió Teilifís Éireann radio'
66 # Radioplayer URLs have two distinct specifier formats,
67 # the old format #!rii=<channel_id>:<id>:<playable_item_id>:<date>:
68 # the new format #!rii=b<channel_id>_<id>_<playable_item_id>_<date>_
69 # where the IDs are int/empty, the date is DD-MM-YYYY, and the specifier may be truncated.
70 # An <id> uniquely defines an individual recording, and is the only part we require.
71 _VALID_URL
= r
'https?://(?:www\.)?rte\.ie/radio/utils/radioplayer/rteradioweb\.html#!rii=(?:b?[0-9]*)(?:%3A|:|%5F|_)(?P<id>[0-9]+)'
74 # Old-style player URL; HLS and RTMPE formats
75 'url': 'http://www.rte.ie/radio/utils/radioplayer/rteradioweb.html#!rii=16:10507902:2414:27-12-2015:',
80 'thumbnail': 're:^https?://.*\.jpg$',
81 'description': 'md5:9ce124a7fb41559ec68f06387cabddf0',
82 'timestamp': 1451203200,
83 'upload_date': '20151227',
87 'skip_download': 'f4m fails with --test atm'
90 # New-style player URL; RTMPE formats only
91 'url': 'http://rte.ie/radio/utils/radioplayer/rteradioweb.html#!rii=b16_3250678_8861_06-04-2012_',
95 'title': 'The Lyric Concert with Paul Herriott',
96 'thumbnail': 're:^https?://.*\.jpg$',
98 'timestamp': 1333742400,
99 'upload_date': '20120406',
100 'duration': 7199.016,
103 'skip_download': 'f4m fails with --test atm'
107 def _real_extract(self
, url
):
108 item_id
= self
._match
_id
(url
)
110 json_string
= self
._download
_json
(
111 'http://www.rte.ie/rteavgen/getplaylist/?type=web&format=json&id=' + item_id
,
114 # NB the string values in the JSON are stored using XML escaping(!)
115 show
= json_string
['shows'][0]
116 title
= unescapeHTML(show
['title'])
117 description
= unescapeHTML(show
.get('description'))
118 thumbnail
= show
.get('thumbnail')
119 duration
= float_or_none(show
.get('duration'), 1000)
120 timestamp
= parse_iso8601(show
.get('published'))
122 mg
= show
['media:group'][0]
127 m
= re
.match(r
'(?P<url>rtmpe?://[^/]+)/(?P<app>.+)/(?P<playpath>mp4:.*)', mg
['url'])
131 'url': m
['url'] + '/' + m
['app'],
133 'play_path': m
['playpath'],
139 if mg
.get('hls_server') and mg
.get('hls_url'):
140 formats
.extend(self
._extract
_m
3u8_formats
(
141 mg
['hls_server'] + mg
['hls_url'], item_id
, 'mp4',
142 entry_protocol
='m3u8_native', m3u8_id
='hls', fatal
=False))
144 if mg
.get('hds_server') and mg
.get('hds_url'):
145 formats
.extend(self
._extract
_f
4m
_formats
(
146 mg
['hds_server'] + mg
['hds_url'], item_id
,
147 f4m_id
='hds', fatal
=False))
149 self
._sort
_formats
(formats
)
154 'description': description
,
155 'thumbnail': thumbnail
,
156 'timestamp': timestamp
,
157 'duration': duration
,