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',
44 'md5': '68f543909aea49d621dfc7703a11cfaf',
48 'title': 'Best of Ingrid Thurnher',
49 'upload_date': '20140527',
50 '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".',
53 '_skip': 'Blocked outside of Austria / Germany',
56 def _real_extract(self, url):
57 playlist_id = self._match_id(url)
58 webpage = self._download_webpage(url, playlist_id)
60 data_json = self._search_regex(
61 r'initializeAdworx\((.+?)\);\n', webpage, 'video info')
62 all_data = json.loads(data_json)
64 def get_segments(all_data):
67 'Tracker::EPISODE_DETAIL_PAGE_OVER_PROGRAM',
68 'Tracker::EPISODE_DETAIL_PAGE_OVER_TOPIC'):
69 return data['values']['segments']
71 sdata = get_segments(all_data)
73 raise ExtractorError('Unable to extract segments')
75 def quality_to_int(s):
76 m = re.search('([0-9]+)', s)
79 return int(m.group(1))
85 'preference': -10 if fd['delivery'] == 'hls' else None,
86 'format_id': '%s-%s-%s' % (
87 fd['delivery'], fd['quality'], fd['quality_string']),
89 'protocol': fd['protocol'],
90 'quality': quality_to_int(fd['quality']),
91 } for fd in sd['playlist_item_array']['sources']]
93 # Check for geoblocking.
94 # There is a property is_geoprotection, but that's always false
95 geo_str = sd.get('geoprotection_string')
101 if re.match(r'^https?://.*\.mp4$', f['url']))
102 except StopIteration:
105 req = HEADRequest(http_url)
106 self._request_webpage(
108 note='Testing for geoblocking',
110 'This video seems to be blocked outside of %s. '
111 'You may want to try the streaming-* formats.')
115 self._check_formats(formats, video_id)
116 self._sort_formats(formats)
118 upload_date = unified_strdate(sd['created_date'])
122 'title': sd['header'],
124 'description': sd.get('description'),
125 'duration': int(sd['duration_in_seconds']),
126 'upload_date': upload_date,
127 'thumbnail': sd.get('image_full_url'),
137 class ORFOE1IE(InfoExtractor):
139 IE_DESC = 'Radio Österreich 1'
140 _VALID_URL = r'https?://oe1\.orf\.at/(?:programm/|konsole.*?#\?track_id=)(?P<id>[0-9]+)'
142 # Audios on ORF radio are only available for 7 days, so we can't add tests.
144 'url': 'http://oe1.orf.at/konsole?show=on_demand#?track_id=394211',
145 'only_matching': True,
148 def _real_extract(self, url):
149 show_id = self._match_id(url)
150 data = self._download_json(
151 'http://oe1.orf.at/programm/%s/konsole' % show_id,
155 timestamp = datetime.datetime.strptime('%s %s' % (
156 data['item']['day_label'],
159 unix_timestamp = calendar.timegm(timestamp.utctimetuple())
163 'title': data['item']['title'],
164 'url': data['item']['url_stream'],
166 'description': data['item'].get('info'),
167 'timestamp': unix_timestamp
171 class ORFFM4IE(InfoExtractor):
173 IE_DESC = 'radio FM4'
174 _VALID_URL = r'https?://fm4\.orf\.at/(?:7tage/?#|player/)(?P<date>[0-9]+)/(?P<show>\w+)'
177 'url': 'http://fm4.orf.at/player/20160110/IS/',
178 'md5': '01e736e8f1cef7e13246e880a59ad298',
180 'id': '2016-01-10_2100_tl_54_7DaysSun13_11244',
183 'description': 'md5:384c543f866c4e422a55f66a62d669cd',
185 'timestamp': 1452456073,
186 'upload_date': '20160110',
190 def _real_extract(self, url):
191 mobj = re.match(self._VALID_URL, url)
192 show_date = mobj.group('date')
193 show_id = mobj.group('show')
195 data = self._download_json(
196 'http://audioapi.orf.at/fm4/json/2.0/broadcasts/%s/4%s' % (show_date, show_id),
200 def extract_entry_dict(info, title, subtitle):
202 'id': info['loopStreamId'].replace('.mp3', ''),
203 'url': 'http://loopstream01.apa.at/?channel=fm4&id=%s' % info['loopStreamId'],
205 'description': subtitle,
206 'duration': (info['end'] - info['start']) / 1000,
207 'timestamp': info['start'] / 1000,
211 entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']]
216 'title': data['title'],
217 'description': data['subtitle'],
222 class ORFIPTVIE(InfoExtractor):
224 IE_DESC = 'iptv.ORF.at'
225 _VALID_URL = r'https?://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'
228 'url': 'http://iptv.orf.at/stories/2275236/',
229 'md5': 'c8b22af4718a4b4af58342529453e3e5',
233 'title': 'Weitere Evakuierungen um Vulkan Calbuco',
234 'description': 'md5:d689c959bdbcf04efeddedbf2299d633',
236 'thumbnail': 're:^https?://.*\.jpg$',
237 'upload_date': '20150425',
241 def _real_extract(self, url):
242 story_id = self._match_id(url)
244 webpage = self._download_webpage(
245 'http://iptv.orf.at/stories/%s' % story_id, story_id)
247 video_id = self._search_regex(
248 r'data-video(?:id)?="(\d+)"', webpage, 'video id')
250 data = self._download_json(
251 'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
254 duration = float_or_none(data['duration'], 1000)
256 video = data['sources']['default']
257 load_balancer_url = video['loadBalancerUrl']
258 abr = int_or_none(video.get('audioBitrate'))
259 vbr = int_or_none(video.get('bitrate'))
260 fps = int_or_none(video.get('videoFps'))
261 width = int_or_none(video.get('videoWidth'))
262 height = int_or_none(video.get('videoHeight'))
263 thumbnail = video.get('preview')
265 rendition = self._download_json(
266 load_balancer_url, video_id, transform_source=strip_jsonp)
277 for format_id, format_url in rendition['redirect'].items():
278 if format_id == 'rtmp':
282 'format_id': format_id,
285 elif determine_ext(format_url) == 'f4m':
286 formats.extend(self._extract_f4m_formats(
287 format_url, video_id, f4m_id=format_id))
288 elif determine_ext(format_url) == 'm3u8':
289 formats.extend(self._extract_m3u8_formats(
290 format_url, video_id, 'mp4', m3u8_id=format_id))
293 self._sort_formats(formats)
295 title = remove_end(self._og_search_title(webpage), ' - iptv.ORF.at')
296 description = self._og_search_description(webpage)
297 upload_date = unified_strdate(self._html_search_meta(
298 'dc.date', webpage, 'upload date'))
303 'description': description,
304 'duration': duration,
305 'thumbnail': thumbnail,
306 'upload_date': upload_date,