]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/orf.py
2 from __future__
import unicode_literals
9 from .common
import InfoExtractor
17 class ORFTVthekIE(InfoExtractor
):
18 IE_NAME
= 'orf:tvthek'
19 IE_DESC
= 'ORF TVthek'
20 _VALID_URL
= r
'https?://tvthek\.orf\.at/(?:programs/.+?/episodes|topics/.+?|program/[^/]+)/(?P<id>\d+)'
23 'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389',
25 'md5': '2942210346ed779588f428a92db88712',
29 'title': 'Aufgetischt: Mit der Steirischen Tafelrunde',
30 'description': 'md5:c1272f0245537812d4e36419c207b67d',
32 'upload_date': '20141208',
35 'skip': 'Blocked outside of Austria',
38 def _real_extract(self
, url
):
39 playlist_id
= self
._match
_id
(url
)
40 webpage
= self
._download
_webpage
(url
, playlist_id
)
42 data_json
= self
._search
_regex
(
43 r
'initializeAdworx\((.+?)\);\n', webpage
, 'video info')
44 all_data
= json
.loads(data_json
)
46 def get_segments(all_data
):
48 if data
['name'] == 'Tracker::EPISODE_DETAIL_PAGE_OVER_PROGRAM':
49 return data
['values']['segments']
51 sdata
= get_segments(all_data
)
53 raise ExtractorError('Unable to extract segments')
55 def quality_to_int(s
):
56 m
= re
.search('([0-9]+)', s
)
59 return int(m
.group(1))
65 'preference': -10 if fd
['delivery'] == 'hls' else None,
66 'format_id': '%s-%s-%s' % (
67 fd
['delivery'], fd
['quality'], fd
['quality_string']),
69 'protocol': fd
['protocol'],
70 'quality': quality_to_int(fd
['quality']),
71 } for fd
in sd
['playlist_item_array']['sources']]
73 # Check for geoblocking.
74 # There is a property is_geoprotection, but that's always false
75 geo_str
= sd
.get('geoprotection_string')
81 if re
.match(r
'^https?://.*\.mp4$', f
['url']))
85 req
= HEADRequest(http_url
)
86 self
._request
_webpage
(
88 note
='Testing for geoblocking',
90 'This video seems to be blocked outside of %s. '
91 'You may want to try the streaming-* formats.')
95 self
._sort
_formats
(formats
)
97 upload_date
= unified_strdate(sd
['created_date'])
101 'title': sd
['header'],
103 'description': sd
.get('description'),
104 'duration': int(sd
['duration_in_seconds']),
105 'upload_date': upload_date
,
106 'thumbnail': sd
.get('image_full_url'),
116 # Audios on ORF radio are only available for 7 days, so we can't add tests.
119 class ORFOE1IE(InfoExtractor
):
121 IE_DESC
= 'Radio Österreich 1'
122 _VALID_URL
= r
'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)'
124 def _real_extract(self
, url
):
125 show_id
= self
._match
_id
(url
)
126 data
= self
._download
_json
(
127 'http://oe1.orf.at/programm/%s/konsole' % show_id
,
131 timestamp
= datetime
.datetime
.strptime('%s %s' % (
132 data
['item']['day_label'],
135 unix_timestamp
= calendar
.timegm(timestamp
.utctimetuple())
139 'title': data
['item']['title'],
140 'url': data
['item']['url_stream'],
142 'description': data
['item'].get('info'),
143 'timestamp': unix_timestamp
147 class ORFFM4IE(InfoExtractor
):
149 IE_DESC
= 'radio FM4'
150 _VALID_URL
= r
'http://fm4\.orf\.at/7tage/?#(?P<date>[0-9]+)/(?P<show>\w+)'
152 def _real_extract(self
, url
):
153 mobj
= re
.match(self
._VALID
_URL
, url
)
154 show_date
= mobj
.group('date')
155 show_id
= mobj
.group('show')
157 data
= self
._download
_json
(
158 'http://audioapi.orf.at/fm4/json/2.0/broadcasts/%s/4%s' % (show_date
, show_id
),
162 def extract_entry_dict(info
, title
, subtitle
):
164 'id': info
['loopStreamId'].replace('.mp3', ''),
165 'url': 'http://loopstream01.apa.at/?channel=fm4&id=%s' % info
['loopStreamId'],
167 'description': subtitle
,
168 'duration': (info
['end'] - info
['start']) / 1000,
169 'timestamp': info
['start'] / 1000,
173 entries
= [extract_entry_dict(t
, data
['title'], data
['subtitle']) for t
in data
['streams']]
178 'title': data
['title'],
179 'description': data
['subtitle'],