]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/orf.py
2 from __future__
import unicode_literals
6 from . common
import InfoExtractor
7 from .. compat
import compat_str
22 class ORFTVthekIE ( InfoExtractor
):
23 IE_NAME
= 'orf:tvthek'
24 IE_DESC
= 'ORF TVthek'
25 _VALID_URL
= r
'https?://tvthek\.orf\.at/(?:[^/]+/)+(?P<id>\d+)'
28 'url' : 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389' ,
30 'md5' : '2942210346ed779588f428a92db88712' ,
34 'title' : 'Aufgetischt: Mit der Steirischen Tafelrunde' ,
35 'description' : 'md5:c1272f0245537812d4e36419c207b67d' ,
37 'upload_date' : '20141208' ,
40 'skip' : 'Blocked outside of Austria / Germany' ,
42 'url' : 'http://tvthek.orf.at/topic/Im-Wandel-der-Zeit/8002126/Best-of-Ingrid-Thurnher/7982256' ,
46 'title' : 'Best of Ingrid Thurnher' ,
47 'upload_date' : '20140527' ,
48 'description' : 'Viele Jahre war Ingrid Thurnher das "Gesicht" der ZIB 2. Vor ihrem Wechsel zur ZIB 2 im Jahr 1995 moderierte sie unter anderem "Land und Leute", "Österreich-Bild" und "Niederösterreich heute".' ,
51 'skip_download' : True , # rtsp downloads
53 'skip' : 'Blocked outside of Austria / Germany' ,
55 'url' : 'http://tvthek.orf.at/topic/Fluechtlingskrise/10463081/Heimat-Fremde-Heimat/13879132/Senioren-betreuen-Migrantenkinder/13879141' ,
56 'only_matching' : True ,
58 'url' : 'http://tvthek.orf.at/profile/Universum/35429' ,
59 'only_matching' : True ,
62 def _real_extract ( self
, url
):
63 playlist_id
= self
._ match
_ id
( url
)
64 webpage
= self
._ download
_ webpage
( url
, playlist_id
)
66 data_jsb
= self
._ parse
_ json
(
68 r
'<div[^>]+class=(["\' ]).* ?VideoPlaylist
.* ?\
1 [ ^
>]+ data
- jsb
=([ " \' ])(?P<json>.+?)\2',
69 webpage, 'playlist', group='json'),
70 playlist_id, transform_source=unescapeHTML)['playlist']['videos']
74 video_id, title = sd.get('id'), sd.get('title')
75 if not video_id or not title:
77 video_id = compat_str(video_id)
79 for fd in sd['sources']:
80 src = url_or_none(fd.get('src'))
84 for key in ('delivery', 'quality', 'quality_string'):
87 format_id_list.append(value)
88 format_id = '-'.join(format_id_list)
89 if determine_ext(fd['src']) == 'm3u8':
90 formats.extend(self._extract_m3u8_formats(
91 fd['src'], video_id, 'mp4', m3u8_id=format_id))
92 elif determine_ext(fd['src']) == 'f4m':
93 formats.extend(self._extract_f4m_formats(
94 fd['src'], video_id, f4m_id=format_id))
97 'format_id': format_id,
99 'protocol': fd.get('protocol'),
102 # Check for geoblocking.
103 # There is a property is_geoprotection, but that's always false
104 geo_str = sd.get('geoprotection_string')
110 if re.match(r'^https?://.*\.mp4$', f['url']))
111 except StopIteration:
114 req = HEADRequest(http_url)
115 self._request_webpage(
117 note='Testing for geoblocking',
119 'This video seems to be blocked outside of %s . '
120 'You may want to try the streaming-* formats.')
124 self._check_formats(formats, video_id)
125 self._sort_formats(formats)
128 for sub in sd.get('subtitles', []):
129 sub_src = sub.get('src')
132 subtitles.setdefault(sub.get('lang', 'de-AT'), []).append({
136 upload_date = unified_strdate(sd.get('created_date'))
142 'subtitles': subtitles,
143 'description': sd.get('description'),
144 'duration': int_or_none(sd.get('duration_in_seconds')),
145 'upload_date': upload_date,
146 'thumbnail': sd.get('image_full_url'),
156 class ORFRadioIE(InfoExtractor):
157 def _real_extract(self, url):
158 mobj = re.match(self._VALID_URL, url)
159 station = mobj.group('station')
160 show_date = mobj.group('date')
161 show_id = mobj.group('show')
164 show_id = '4 %s ' % show_id
166 data = self._download_json(
167 'http://audioapi.orf.at/ %s /api/json/current/broadcast/ %s / %s ' % (station, show_id, show_date),
171 def extract_entry_dict(info, title, subtitle):
173 'id': info['loopStreamId'].replace('.mp3', ''),
174 'url': 'http://loopstream01.apa.at/?channel= %s &id= %s ' % (station, info['loopStreamId']),
176 'description': subtitle,
177 'duration': (info['end'] - info['start']) / 1000,
178 'timestamp': info['start'] / 1000,
180 'series': data.get('programTitle')
183 entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']]
188 'title': data['title'],
189 'description': data['subtitle'],
194 class ORFFM4IE(ORFRadioIE):
196 IE_DESC = 'radio FM4'
197 _VALID_URL = r'https?://(?P<station>fm4)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
200 'url': 'http://fm4.orf.at/player/20170107/CC',
201 'md5': '2b0be47375432a7ef104453432a19212',
203 'id': '2017-01-07_2100_tl_54_7DaysSat18_31295',
205 'title': 'Solid Steel Radioshow',
206 'description': 'Die Mixshow von Coldcut und Ninja Tune.',
208 'timestamp': 1483819257,
209 'upload_date': '20170107',
211 'skip': 'Shows from ORF radios are only available for 7 days.'
215 class ORFOE1IE(ORFRadioIE):
217 IE_DESC = 'Radio Österreich 1'
218 _VALID_URL = r'https?://(?P<station>oe1)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
221 'url': 'http://oe1.orf.at/player/20170108/456544',
222 'md5': '34d8a6e67ea888293741c86a099b745b',
224 'id': '2017-01-08_0759_tl_51_7DaysSun6_256141',
226 'title': 'Morgenjournal',
228 'timestamp': 1483858796,
229 'upload_date': '20170108',
231 'skip': 'Shows from ORF radios are only available for 7 days.'
235 class ORFIPTVIE(InfoExtractor):
237 IE_DESC = 'iptv.ORF.at'
238 _VALID_URL = r'https?://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'
241 'url': 'http://iptv.orf.at/stories/2275236/',
242 'md5': 'c8b22af4718a4b4af58342529453e3e5',
246 'title': 'Weitere Evakuierungen um Vulkan Calbuco',
247 'description': 'md5:d689c959bdbcf04efeddedbf2299d633',
249 'thumbnail': r're:^https?://.*\.jpg$',
250 'upload_date': '20150425',
254 def _real_extract(self, url):
255 story_id = self._match_id(url)
257 webpage = self._download_webpage(
258 'http://iptv.orf.at/stories/ %s ' % story_id, story_id)
260 video_id = self._search_regex(
261 r'data-video(?:id)?=" ( \d
+) "', webpage, 'video id')
263 data = self._download_json(
264 'http://bits.orf.at/filehandler/static-api/json/current/data.json?file= %s ' % video_id,
267 duration = float_or_none(data['duration'], 1000)
269 video = data['sources']['default']
270 load_balancer_url = video['loadBalancerUrl']
271 abr = int_or_none(video.get('audioBitrate'))
272 vbr = int_or_none(video.get('bitrate'))
273 fps = int_or_none(video.get('videoFps'))
274 width = int_or_none(video.get('videoWidth'))
275 height = int_or_none(video.get('videoHeight'))
276 thumbnail = video.get('preview')
278 rendition = self._download_json(
279 load_balancer_url, video_id, transform_source=strip_jsonp)
290 for format_id, format_url in rendition['redirect'].items():
291 if format_id == 'rtmp':
295 'format_id': format_id,
298 elif determine_ext(format_url) == 'f4m':
299 formats.extend(self._extract_f4m_formats(
300 format_url, video_id, f4m_id=format_id))
301 elif determine_ext(format_url) == 'm3u8':
302 formats.extend(self._extract_m3u8_formats(
303 format_url, video_id, 'mp4', m3u8_id=format_id))
306 self._sort_formats(formats)
308 title = remove_end(self._og_search_title(webpage), ' - iptv.ORF.at')
309 description = self._og_search_description(webpage)
310 upload_date = unified_strdate(self._html_search_meta(
311 'dc.date', webpage, 'upload date'))
316 'description': description,
317 'duration': duration,
318 'thumbnail': thumbnail,
319 'upload_date': upload_date,
324 class ORFFM4StoryIE(InfoExtractor):
325 IE_NAME = 'orf:fm4:story'
326 IE_DESC = 'fm4.orf.at stories'
327 _VALID_URL = r'https?://fm4\.orf\.at/stories/(?P<id>\d+)'
330 'url': 'http://fm4.orf.at/stories/2865738/',
332 'md5': 'e1c2c706c45c7b34cf478bbf409907ca',
336 'title': 'Manu Delago und Inner Tongue live',
337 'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.',
339 'thumbnail': r're:^https?://.*\.jpg$',
340 'upload_date': '20170913',
343 'md5': 'c6dd2179731f86f4f55a7b49899d515f',
347 'title': 'Manu Delago und Inner Tongue live (2)',
349 'thumbnail': r're:^https?://.*\.jpg$',
350 'upload_date': '20170913',
351 'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.',
356 def _real_extract(self, url):
357 story_id = self._match_id(url)
358 webpage = self._download_webpage(url, story_id)
361 all_ids = orderedSet(re.findall(r'data-video(?:id)?=" ( \d
+) "', webpage))
362 for idx, video_id in enumerate(all_ids):
363 data = self._download_json(
364 'http://bits.orf.at/filehandler/static-api/json/current/data.json?file= %s ' % video_id,
367 duration = float_or_none(data['duration'], 1000)
369 video = data['sources']['q8c']
370 load_balancer_url = video['loadBalancerUrl']
371 abr = int_or_none(video.get('audioBitrate'))
372 vbr = int_or_none(video.get('bitrate'))
373 fps = int_or_none(video.get('videoFps'))
374 width = int_or_none(video.get('videoWidth'))
375 height = int_or_none(video.get('videoHeight'))
376 thumbnail = video.get('preview')
378 rendition = self._download_json(
379 load_balancer_url, video_id, transform_source=strip_jsonp)
390 for format_id, format_url in rendition['redirect'].items():
391 if format_id == 'rtmp':
395 'format_id': format_id,
398 elif determine_ext(format_url) == 'f4m':
399 formats.extend(self._extract_f4m_formats(
400 format_url, video_id, f4m_id=format_id))
401 elif determine_ext(format_url) == 'm3u8':
402 formats.extend(self._extract_m3u8_formats(
403 format_url, video_id, 'mp4', m3u8_id=format_id))
406 self._sort_formats(formats)
408 title = remove_end(self._og_search_title(webpage), ' - fm4.ORF.at')
410 # Titles are duplicates, make them unique
411 title += ' (' + str(idx + 1) + ')'
412 description = self._og_search_description(webpage)
413 upload_date = unified_strdate(self._html_search_meta(
414 'dc.date', webpage, 'upload date'))
419 'description': description,
420 'duration': duration,
421 'thumbnail': thumbnail,
422 'upload_date': upload_date,
426 return self.playlist_result(entries)