2 from __future__ import unicode_literals
9 from .common import InfoExtractor
22 class ORFTVthekIE(InfoExtractor):
23 IE_NAME = 'orf:tvthek'
24 IE_DESC = 'ORF TVthek'
25 _VALID_URL = r'https?://tvthek\.orf\.at/(?:programs/.+?/episodes|topics?/.+?|program/[^/]+)/(?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',
43 'md5': '68f543909aea49d621dfc7703a11cfaf',
47 'title': 'Best of Ingrid Thurnher',
48 'upload_date': '20140527',
49 '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".',
52 'skip_download': True, # rtsp downloads
54 '_skip': 'Blocked outside of Austria / Germany',
57 def _real_extract(self, url):
58 playlist_id = self._match_id(url)
59 webpage = self._download_webpage(url, playlist_id)
61 data_json = self._search_regex(
62 r'initializeAdworx\((.+?)\);\n', webpage, 'video info')
63 all_data = json.loads(data_json)
65 def get_segments(all_data):
68 'Tracker::EPISODE_DETAIL_PAGE_OVER_PROGRAM',
69 'Tracker::EPISODE_DETAIL_PAGE_OVER_TOPIC'):
70 return data['values']['segments']
72 sdata = get_segments(all_data)
74 raise ExtractorError('Unable to extract segments')
76 def quality_to_int(s):
77 m = re.search('([0-9]+)', s)
80 return int(m.group(1))
86 'preference': -10 if fd['delivery'] == 'hls' else None,
87 'format_id': '%s-%s-%s' % (
88 fd['delivery'], fd['quality'], fd['quality_string']),
90 'protocol': fd['protocol'],
91 'quality': quality_to_int(fd['quality']),
92 } for fd in sd['playlist_item_array']['sources']]
94 # Check for geoblocking.
95 # There is a property is_geoprotection, but that's always false
96 geo_str = sd.get('geoprotection_string')
102 if re.match(r'^https?://.*\.mp4$', f['url']))
103 except StopIteration:
106 req = HEADRequest(http_url)
107 self._request_webpage(
109 note='Testing for geoblocking',
111 'This video seems to be blocked outside of %s. '
112 'You may want to try the streaming-* formats.')
116 self._check_formats(formats, video_id)
117 self._sort_formats(formats)
119 upload_date = unified_strdate(sd['created_date'])
123 'title': sd['header'],
125 'description': sd.get('description'),
126 'duration': int(sd['duration_in_seconds']),
127 'upload_date': upload_date,
128 'thumbnail': sd.get('image_full_url'),
138 class ORFOE1IE(InfoExtractor):
140 IE_DESC = 'Radio Österreich 1'
141 _VALID_URL = r'https?://oe1\.orf\.at/(?:programm/|konsole.*?#\?track_id=)(?P<id>[0-9]+)'
143 # Audios on ORF radio are only available for 7 days, so we can't add tests.
145 'url': 'http://oe1.orf.at/konsole?show=on_demand#?track_id=394211',
146 'only_matching': True,
149 def _real_extract(self, url):
150 show_id = self._match_id(url)
151 data = self._download_json(
152 'http://oe1.orf.at/programm/%s/konsole' % show_id,
156 timestamp = datetime.datetime.strptime('%s %s' % (
157 data['item']['day_label'],
160 unix_timestamp = calendar.timegm(timestamp.utctimetuple())
164 'title': data['item']['title'],
165 'url': data['item']['url_stream'],
167 'description': data['item'].get('info'),
168 'timestamp': unix_timestamp
172 class ORFFM4IE(InfoExtractor):
174 IE_DESC = 'radio FM4'
175 _VALID_URL = r'https?://fm4\.orf\.at/(?:7tage/?#|player/)(?P<date>[0-9]+)/(?P<show>\w+)'
178 'url': 'http://fm4.orf.at/player/20160110/IS/',
179 'md5': '01e736e8f1cef7e13246e880a59ad298',
181 'id': '2016-01-10_2100_tl_54_7DaysSun13_11244',
184 'description': 'md5:384c543f866c4e422a55f66a62d669cd',
186 'timestamp': 1452456073,
187 'upload_date': '20160110',
189 'skip': 'Live streams on FM4 got deleted soon',
192 def _real_extract(self, url):
193 mobj = re.match(self._VALID_URL, url)
194 show_date = mobj.group('date')
195 show_id = mobj.group('show')
197 data = self._download_json(
198 'http://audioapi.orf.at/fm4/json/2.0/broadcasts/%s/4%s' % (show_date, show_id),
202 def extract_entry_dict(info, title, subtitle):
204 'id': info['loopStreamId'].replace('.mp3', ''),
205 'url': 'http://loopstream01.apa.at/?channel=fm4&id=%s' % info['loopStreamId'],
207 'description': subtitle,
208 'duration': (info['end'] - info['start']) / 1000,
209 'timestamp': info['start'] / 1000,
213 entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']]
218 'title': data['title'],
219 'description': data['subtitle'],
224 class ORFIPTVIE(InfoExtractor):
226 IE_DESC = 'iptv.ORF.at'
227 _VALID_URL = r'https?://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'
230 'url': 'http://iptv.orf.at/stories/2275236/',
231 'md5': 'c8b22af4718a4b4af58342529453e3e5',
235 'title': 'Weitere Evakuierungen um Vulkan Calbuco',
236 'description': 'md5:d689c959bdbcf04efeddedbf2299d633',
238 'thumbnail': 're:^https?://.*\.jpg$',
239 'upload_date': '20150425',
243 def _real_extract(self, url):
244 story_id = self._match_id(url)
246 webpage = self._download_webpage(
247 'http://iptv.orf.at/stories/%s' % story_id, story_id)
249 video_id = self._search_regex(
250 r'data-video(?:id)?="(\d+)"', webpage, 'video id')
252 data = self._download_json(
253 'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
256 duration = float_or_none(data['duration'], 1000)
258 video = data['sources']['default']
259 load_balancer_url = video['loadBalancerUrl']
260 abr = int_or_none(video.get('audioBitrate'))
261 vbr = int_or_none(video.get('bitrate'))
262 fps = int_or_none(video.get('videoFps'))
263 width = int_or_none(video.get('videoWidth'))
264 height = int_or_none(video.get('videoHeight'))
265 thumbnail = video.get('preview')
267 rendition = self._download_json(
268 load_balancer_url, video_id, transform_source=strip_jsonp)
279 for format_id, format_url in rendition['redirect'].items():
280 if format_id == 'rtmp':
284 'format_id': format_id,
287 elif determine_ext(format_url) == 'f4m':
288 formats.extend(self._extract_f4m_formats(
289 format_url, video_id, f4m_id=format_id))
290 elif determine_ext(format_url) == 'm3u8':
291 formats.extend(self._extract_m3u8_formats(
292 format_url, video_id, 'mp4', m3u8_id=format_id))
295 self._sort_formats(formats)
297 title = remove_end(self._og_search_title(webpage), ' - iptv.ORF.at')
298 description = self._og_search_description(webpage)
299 upload_date = unified_strdate(self._html_search_meta(
300 'dc.date', webpage, 'upload date'))
305 'description': description,
306 'duration': duration,
307 'thumbnail': thumbnail,
308 'upload_date': upload_date,