]>
Commit | Line | Data |
---|---|---|
89284910 | 1 | # coding: utf-8 |
5d73273f | 2 | from __future__ import unicode_literals |
89284910 | 3 | |
5d73273f | 4 | import re |
54543467 JMF |
5 | |
6 | from .common import InfoExtractor | |
73c801d6 | 7 | from ..compat import compat_str |
54543467 | 8 | from ..utils import ( |
0732a905 PH |
9 | determine_ext, |
10 | float_or_none, | |
5d73273f | 11 | HEADRequest, |
14137b57 | 12 | int_or_none, |
0732a905 | 13 | orderedSet, |
14137b57 | 14 | remove_end, |
0732a905 | 15 | strip_jsonp, |
73c801d6 | 16 | unescapeHTML, |
0732a905 | 17 | unified_strdate, |
4b6aca17 | 18 | url_or_none, |
54543467 JMF |
19 | ) |
20 | ||
5d73273f | 21 | |
eb368012 S |
22 | class ORFTVthekIE(InfoExtractor): |
23 | IE_NAME = 'orf:tvthek' | |
24 | IE_DESC = 'ORF TVthek' | |
73c801d6 | 25 | _VALID_URL = r'https?://tvthek\.orf\.at/(?:[^/]+/)+(?P<id>\d+)' |
5d73273f | 26 | |
13d27a42 | 27 | _TESTS = [{ |
a6620ac2 PH |
28 | 'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389', |
29 | 'playlist': [{ | |
30 | 'md5': '2942210346ed779588f428a92db88712', | |
31 | 'info_dict': { | |
32 | 'id': '8896777', | |
33 | 'ext': 'mp4', | |
34 | 'title': 'Aufgetischt: Mit der Steirischen Tafelrunde', | |
35 | 'description': 'md5:c1272f0245537812d4e36419c207b67d', | |
36 | 'duration': 2668, | |
37 | 'upload_date': '20141208', | |
38 | }, | |
39 | }], | |
13d27a42 PH |
40 | 'skip': 'Blocked outside of Austria / Germany', |
41 | }, { | |
42 | 'url': 'http://tvthek.orf.at/topic/Im-Wandel-der-Zeit/8002126/Best-of-Ingrid-Thurnher/7982256', | |
7b0d333a NP |
43 | 'info_dict': { |
44 | 'id': '7982259', | |
45 | 'ext': 'mp4', | |
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".', | |
49 | }, | |
50 | 'params': { | |
51 | 'skip_download': True, # rtsp downloads | |
52 | }, | |
7512aa98 | 53 | 'skip': 'Blocked outside of Austria / Germany', |
73c801d6 S |
54 | }, { |
55 | 'url': 'http://tvthek.orf.at/topic/Fluechtlingskrise/10463081/Heimat-Fremde-Heimat/13879132/Senioren-betreuen-Migrantenkinder/13879141', | |
7512aa98 | 56 | 'only_matching': True, |
73c801d6 S |
57 | }, { |
58 | 'url': 'http://tvthek.orf.at/profile/Universum/35429', | |
7512aa98 | 59 | 'only_matching': True, |
13d27a42 | 60 | }] |
54543467 | 61 | |
54543467 | 62 | def _real_extract(self, url): |
a6620ac2 | 63 | playlist_id = self._match_id(url) |
54543467 JMF |
64 | webpage = self._download_webpage(url, playlist_id) |
65 | ||
73c801d6 S |
66 | data_jsb = self._parse_json( |
67 | self._search_regex( | |
68 | r'<div[^>]+class=(["\']).*?VideoPlaylist.*?\1[^>]+data-jsb=(["\'])(?P<json>.+?)\2', | |
69 | webpage, 'playlist', group='json'), | |
70 | playlist_id, transform_source=unescapeHTML)['playlist']['videos'] | |
5d73273f | 71 | |
5d73273f | 72 | entries = [] |
73c801d6 S |
73 | for sd in data_jsb: |
74 | video_id, title = sd.get('id'), sd.get('title') | |
75 | if not video_id or not title: | |
76 | continue | |
77 | video_id = compat_str(video_id) | |
c620694c SH |
78 | formats = [] |
79 | for fd in sd['sources']: | |
4b6aca17 S |
80 | src = url_or_none(fd.get('src')) |
81 | if not src: | |
82 | continue | |
83 | format_id_list = [] | |
84 | for key in ('delivery', 'quality', 'quality_string'): | |
85 | value = fd.get(key) | |
86 | if value: | |
87 | format_id_list.append(value) | |
88 | format_id = '-'.join(format_id_list) | |
c620694c SH |
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)) | |
4b6aca17 S |
95 | else: |
96 | formats.append({ | |
97 | 'format_id': format_id, | |
98 | 'url': src, | |
99 | 'protocol': fd.get('protocol'), | |
100 | }) | |
5d73273f PH |
101 | |
102 | # Check for geoblocking. | |
103 | # There is a property is_geoprotection, but that's always false | |
104 | geo_str = sd.get('geoprotection_string') | |
105 | if geo_str: | |
106 | try: | |
107 | http_url = next( | |
108 | f['url'] | |
109 | for f in formats | |
110 | if re.match(r'^https?://.*\.mp4$', f['url'])) | |
111 | except StopIteration: | |
112 | pass | |
113 | else: | |
114 | req = HEADRequest(http_url) | |
4f81667d | 115 | self._request_webpage( |
5d73273f PH |
116 | req, video_id, |
117 | note='Testing for geoblocking', | |
118 | errnote=(( | |
119 | 'This video seems to be blocked outside of %s. ' | |
120 | 'You may want to try the streaming-* formats.') | |
121 | % geo_str), | |
122 | fatal=False) | |
123 | ||
e277f2a6 | 124 | self._check_formats(formats, video_id) |
5d73273f PH |
125 | self._sort_formats(formats) |
126 | ||
791d29db RA |
127 | subtitles = {} |
128 | for sub in sd.get('subtitles', []): | |
129 | sub_src = sub.get('src') | |
130 | if not sub_src: | |
131 | continue | |
132 | subtitles.setdefault(sub.get('lang', 'de-AT'), []).append({ | |
133 | 'url': sub_src, | |
134 | }) | |
135 | ||
73c801d6 | 136 | upload_date = unified_strdate(sd.get('created_date')) |
5d73273f | 137 | entries.append({ |
54543467 | 138 | '_type': 'video', |
5d73273f | 139 | 'id': video_id, |
73c801d6 | 140 | 'title': title, |
5d73273f | 141 | 'formats': formats, |
791d29db | 142 | 'subtitles': subtitles, |
5d73273f | 143 | 'description': sd.get('description'), |
73c801d6 | 144 | 'duration': int_or_none(sd.get('duration_in_seconds')), |
5d73273f PH |
145 | 'upload_date': upload_date, |
146 | 'thumbnail': sd.get('image_full_url'), | |
147 | }) | |
148 | ||
149 | return { | |
150 | '_type': 'playlist', | |
151 | 'entries': entries, | |
152 | 'id': playlist_id, | |
153 | } | |
eb368012 S |
154 | |
155 | ||
efe93167 | 156 | class ORFRadioIE(InfoExtractor): |
eb368012 S |
157 | def _real_extract(self, url): |
158 | mobj = re.match(self._VALID_URL, url) | |
efe93167 | 159 | station = mobj.group('station') |
eb368012 S |
160 | show_date = mobj.group('date') |
161 | show_id = mobj.group('show') | |
162 | ||
efe93167 | 163 | if station == 'fm4': |
164 | show_id = '4%s' % show_id | |
165 | ||
eb368012 | 166 | data = self._download_json( |
efe93167 | 167 | 'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s' % (station, show_id, show_date), |
eb368012 S |
168 | show_id |
169 | ) | |
170 | ||
171 | def extract_entry_dict(info, title, subtitle): | |
172 | return { | |
173 | 'id': info['loopStreamId'].replace('.mp3', ''), | |
efe93167 | 174 | 'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (station, info['loopStreamId']), |
eb368012 S |
175 | 'title': title, |
176 | 'description': subtitle, | |
177 | 'duration': (info['end'] - info['start']) / 1000, | |
178 | 'timestamp': info['start'] / 1000, | |
179 | 'ext': 'mp3' | |
180 | } | |
181 | ||
182 | entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']] | |
183 | ||
184 | return { | |
185 | '_type': 'playlist', | |
186 | 'id': show_id, | |
187 | 'title': data['title'], | |
188 | 'description': data['subtitle'], | |
189 | 'entries': entries | |
5f6a1245 | 190 | } |
14137b57 S |
191 | |
192 | ||
efe93167 | 193 | class ORFFM4IE(ORFRadioIE): |
194 | IE_NAME = 'orf:fm4' | |
195 | IE_DESC = 'radio FM4' | |
1339ecb2 | 196 | _VALID_URL = r'https?://(?P<station>fm4)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)' |
efe93167 | 197 | |
1339ecb2 S |
198 | _TEST = { |
199 | 'url': 'http://fm4.orf.at/player/20170107/CC', | |
200 | 'md5': '2b0be47375432a7ef104453432a19212', | |
201 | 'info_dict': { | |
202 | 'id': '2017-01-07_2100_tl_54_7DaysSat18_31295', | |
203 | 'ext': 'mp3', | |
204 | 'title': 'Solid Steel Radioshow', | |
205 | 'description': 'Die Mixshow von Coldcut und Ninja Tune.', | |
206 | 'duration': 3599, | |
207 | 'timestamp': 1483819257, | |
208 | 'upload_date': '20170107', | |
209 | }, | |
210 | 'skip': 'Shows from ORF radios are only available for 7 days.' | |
211 | } | |
efe93167 | 212 | |
213 | ||
214 | class ORFOE1IE(ORFRadioIE): | |
215 | IE_NAME = 'orf:oe1' | |
216 | IE_DESC = 'Radio Österreich 1' | |
1339ecb2 | 217 | _VALID_URL = r'https?://(?P<station>oe1)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)' |
efe93167 | 218 | |
1339ecb2 S |
219 | _TEST = { |
220 | 'url': 'http://oe1.orf.at/player/20170108/456544', | |
221 | 'md5': '34d8a6e67ea888293741c86a099b745b', | |
222 | 'info_dict': { | |
223 | 'id': '2017-01-08_0759_tl_51_7DaysSun6_256141', | |
224 | 'ext': 'mp3', | |
225 | 'title': 'Morgenjournal', | |
226 | 'duration': 609, | |
227 | 'timestamp': 1483858796, | |
228 | 'upload_date': '20170108', | |
229 | }, | |
230 | 'skip': 'Shows from ORF radios are only available for 7 days.' | |
231 | } | |
efe93167 | 232 | |
233 | ||
14137b57 S |
234 | class ORFIPTVIE(InfoExtractor): |
235 | IE_NAME = 'orf:iptv' | |
236 | IE_DESC = 'iptv.ORF.at' | |
5886b38d | 237 | _VALID_URL = r'https?://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)' |
14137b57 S |
238 | |
239 | _TEST = { | |
529d26c3 S |
240 | 'url': 'http://iptv.orf.at/stories/2275236/', |
241 | 'md5': 'c8b22af4718a4b4af58342529453e3e5', | |
14137b57 | 242 | 'info_dict': { |
529d26c3 | 243 | 'id': '350612', |
14137b57 | 244 | 'ext': 'flv', |
529d26c3 S |
245 | 'title': 'Weitere Evakuierungen um Vulkan Calbuco', |
246 | 'description': 'md5:d689c959bdbcf04efeddedbf2299d633', | |
247 | 'duration': 68.197, | |
ec85ded8 | 248 | 'thumbnail': r're:^https?://.*\.jpg$', |
529d26c3 | 249 | 'upload_date': '20150425', |
14137b57 S |
250 | }, |
251 | } | |
252 | ||
253 | def _real_extract(self, url): | |
254 | story_id = self._match_id(url) | |
255 | ||
256 | webpage = self._download_webpage( | |
257 | 'http://iptv.orf.at/stories/%s' % story_id, story_id) | |
258 | ||
259 | video_id = self._search_regex( | |
260 | r'data-video(?:id)?="(\d+)"', webpage, 'video id') | |
261 | ||
262 | data = self._download_json( | |
263 | 'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id, | |
264 | video_id)[0] | |
265 | ||
266 | duration = float_or_none(data['duration'], 1000) | |
267 | ||
268 | video = data['sources']['default'] | |
269 | load_balancer_url = video['loadBalancerUrl'] | |
270 | abr = int_or_none(video.get('audioBitrate')) | |
271 | vbr = int_or_none(video.get('bitrate')) | |
272 | fps = int_or_none(video.get('videoFps')) | |
273 | width = int_or_none(video.get('videoWidth')) | |
274 | height = int_or_none(video.get('videoHeight')) | |
275 | thumbnail = video.get('preview') | |
276 | ||
277 | rendition = self._download_json( | |
278 | load_balancer_url, video_id, transform_source=strip_jsonp) | |
279 | ||
280 | f = { | |
281 | 'abr': abr, | |
282 | 'vbr': vbr, | |
283 | 'fps': fps, | |
284 | 'width': width, | |
285 | 'height': height, | |
286 | } | |
287 | ||
288 | formats = [] | |
289 | for format_id, format_url in rendition['redirect'].items(): | |
290 | if format_id == 'rtmp': | |
291 | ff = f.copy() | |
292 | ff.update({ | |
293 | 'url': format_url, | |
294 | 'format_id': format_id, | |
295 | }) | |
296 | formats.append(ff) | |
297 | elif determine_ext(format_url) == 'f4m': | |
298 | formats.extend(self._extract_f4m_formats( | |
299 | format_url, video_id, f4m_id=format_id)) | |
300 | elif determine_ext(format_url) == 'm3u8': | |
301 | formats.extend(self._extract_m3u8_formats( | |
302 | format_url, video_id, 'mp4', m3u8_id=format_id)) | |
303 | else: | |
304 | continue | |
305 | self._sort_formats(formats) | |
306 | ||
307 | title = remove_end(self._og_search_title(webpage), ' - iptv.ORF.at') | |
308 | description = self._og_search_description(webpage) | |
309 | upload_date = unified_strdate(self._html_search_meta( | |
310 | 'dc.date', webpage, 'upload date')) | |
311 | ||
312 | return { | |
313 | 'id': video_id, | |
314 | 'title': title, | |
315 | 'description': description, | |
316 | 'duration': duration, | |
317 | 'thumbnail': thumbnail, | |
318 | 'upload_date': upload_date, | |
319 | 'formats': formats, | |
320 | } | |
0732a905 PH |
321 | |
322 | ||
323 | class ORFFM4StoryIE(InfoExtractor): | |
324 | IE_NAME = 'orf:fm4:story' | |
325 | IE_DESC = 'fm4.orf.at stories' | |
326 | _VALID_URL = r'https?://fm4\.orf\.at/stories/(?P<id>\d+)' | |
327 | ||
328 | _TEST = { | |
329 | 'url': 'http://fm4.orf.at/stories/2865738/', | |
330 | 'playlist': [{ | |
331 | 'md5': 'e1c2c706c45c7b34cf478bbf409907ca', | |
332 | 'info_dict': { | |
333 | 'id': '547792', | |
334 | 'ext': 'flv', | |
335 | 'title': 'Manu Delago und Inner Tongue live', | |
336 | '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.', | |
337 | 'duration': 1748.52, | |
338 | 'thumbnail': r're:^https?://.*\.jpg$', | |
339 | 'upload_date': '20170913', | |
340 | }, | |
341 | }, { | |
342 | 'md5': 'c6dd2179731f86f4f55a7b49899d515f', | |
343 | 'info_dict': { | |
344 | 'id': '547798', | |
345 | 'ext': 'flv', | |
346 | 'title': 'Manu Delago und Inner Tongue live (2)', | |
347 | 'duration': 1504.08, | |
348 | 'thumbnail': r're:^https?://.*\.jpg$', | |
349 | 'upload_date': '20170913', | |
350 | '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.', | |
351 | }, | |
352 | }], | |
353 | } | |
354 | ||
355 | def _real_extract(self, url): | |
356 | story_id = self._match_id(url) | |
357 | webpage = self._download_webpage(url, story_id) | |
358 | ||
359 | entries = [] | |
360 | all_ids = orderedSet(re.findall(r'data-video(?:id)?="(\d+)"', webpage)) | |
361 | for idx, video_id in enumerate(all_ids): | |
362 | data = self._download_json( | |
363 | 'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id, | |
364 | video_id)[0] | |
365 | ||
366 | duration = float_or_none(data['duration'], 1000) | |
367 | ||
368 | video = data['sources']['q8c'] | |
369 | load_balancer_url = video['loadBalancerUrl'] | |
370 | abr = int_or_none(video.get('audioBitrate')) | |
371 | vbr = int_or_none(video.get('bitrate')) | |
372 | fps = int_or_none(video.get('videoFps')) | |
373 | width = int_or_none(video.get('videoWidth')) | |
374 | height = int_or_none(video.get('videoHeight')) | |
375 | thumbnail = video.get('preview') | |
376 | ||
377 | rendition = self._download_json( | |
378 | load_balancer_url, video_id, transform_source=strip_jsonp) | |
379 | ||
380 | f = { | |
381 | 'abr': abr, | |
382 | 'vbr': vbr, | |
383 | 'fps': fps, | |
384 | 'width': width, | |
385 | 'height': height, | |
386 | } | |
387 | ||
388 | formats = [] | |
389 | for format_id, format_url in rendition['redirect'].items(): | |
390 | if format_id == 'rtmp': | |
391 | ff = f.copy() | |
392 | ff.update({ | |
393 | 'url': format_url, | |
394 | 'format_id': format_id, | |
395 | }) | |
396 | formats.append(ff) | |
397 | elif determine_ext(format_url) == 'f4m': | |
398 | formats.extend(self._extract_f4m_formats( | |
399 | format_url, video_id, f4m_id=format_id)) | |
400 | elif determine_ext(format_url) == 'm3u8': | |
401 | formats.extend(self._extract_m3u8_formats( | |
402 | format_url, video_id, 'mp4', m3u8_id=format_id)) | |
403 | else: | |
404 | continue | |
405 | self._sort_formats(formats) | |
406 | ||
407 | title = remove_end(self._og_search_title(webpage), ' - fm4.ORF.at') | |
408 | if idx >= 1: | |
409 | # Titles are duplicates, make them unique | |
410 | title += ' (' + str(idx + 1) + ')' | |
411 | description = self._og_search_description(webpage) | |
412 | upload_date = unified_strdate(self._html_search_meta( | |
413 | 'dc.date', webpage, 'upload date')) | |
414 | ||
415 | entries.append({ | |
416 | 'id': video_id, | |
417 | 'title': title, | |
418 | 'description': description, | |
419 | 'duration': duration, | |
420 | 'thumbnail': thumbnail, | |
421 | 'upload_date': upload_date, | |
422 | 'formats': formats, | |
423 | }) | |
424 | ||
425 | return self.playlist_result(entries) |