]>
Commit | Line | Data |
---|---|---|
dcdb292f | 1 | # coding: utf-8 |
b461641f S |
2 | from __future__ import unicode_literals |
3 | ||
4 | import re | |
5 | ||
6 | from .common import InfoExtractor | |
54e8f62e S |
7 | from ..compat import ( |
8 | compat_str, | |
9 | compat_urlparse, | |
10 | ) | |
1cc79574 | 11 | from ..utils import ( |
bec2c14f | 12 | determine_ext, |
1594a493 | 13 | ExtractorError, |
33a1ff71 | 14 | js_to_json, |
37f97295 | 15 | strip_jsonp, |
54e8f62e | 16 | try_get, |
cd7481a3 | 17 | unified_strdate, |
6869d634 | 18 | update_url_query, |
50918c4e | 19 | urlhandle_detect_ext, |
b461641f S |
20 | ) |
21 | ||
22 | ||
54e8f62e S |
23 | class WDRIE(InfoExtractor): |
24 | _VALID_URL = r'https?://deviceids-medp\.wdr\.de/ondemand/\d+/(?P<id>\d+)\.js' | |
1915662d | 25 | _GEO_COUNTRIES = ['DE'] |
54e8f62e S |
26 | _TEST = { |
27 | 'url': 'http://deviceids-medp.wdr.de/ondemand/155/1557833.js', | |
28 | 'info_dict': { | |
29 | 'id': 'mdb-1140188', | |
30 | 'display_id': 'dfb-team-geht-gut-gelaunt-ins-spiel-gegen-polen-100', | |
31 | 'ext': 'mp4', | |
32 | 'title': 'DFB-Team geht gut gelaunt ins Spiel gegen Polen', | |
33 | 'description': 'Vor dem zweiten Gruppenspiel gegen Polen herrscht gute Stimmung im deutschen Team. Insbesondere Bastian Schweinsteiger strotzt vor Optimismus nach seinem Tor gegen die Ukraine.', | |
34 | 'upload_date': '20160615', | |
35 | }, | |
36 | 'skip': 'Geo-restricted to Germany', | |
37 | } | |
6d0d4fc2 | 38 | |
54e8f62e S |
39 | def _real_extract(self, url): |
40 | video_id = self._match_id(url) | |
6d0d4fc2 YCH |
41 | |
42 | metadata = self._download_json( | |
54e8f62e | 43 | url, video_id, transform_source=strip_jsonp) |
6d0d4fc2 | 44 | |
54e8f62e S |
45 | is_live = metadata.get('mediaType') == 'live' |
46 | ||
47 | tracker_data = metadata['trackerData'] | |
48 | media_resource = metadata['mediaResource'] | |
6d0d4fc2 YCH |
49 | |
50 | formats = [] | |
51 | ||
52 | # check if the metadata contains a direct URL to a file | |
54e8f62e | 53 | for kind, media_resource in media_resource.items(): |
6d0d4fc2 YCH |
54 | if kind not in ('dflt', 'alt'): |
55 | continue | |
56 | ||
57 | for tag_name, medium_url in media_resource.items(): | |
58 | if tag_name not in ('videoURL', 'audioURL'): | |
59 | continue | |
60 | ||
61 | ext = determine_ext(medium_url) | |
62 | if ext == 'm3u8': | |
63 | formats.extend(self._extract_m3u8_formats( | |
54e8f62e | 64 | medium_url, video_id, 'mp4', 'm3u8_native', |
6d0d4fc2 YCH |
65 | m3u8_id='hls')) |
66 | elif ext == 'f4m': | |
67 | manifest_url = update_url_query( | |
68 | medium_url, {'hdcore': '3.2.0', 'plugin': 'aasp-3.2.0.77.18'}) | |
69 | formats.extend(self._extract_f4m_formats( | |
54e8f62e | 70 | manifest_url, video_id, f4m_id='hds', fatal=False)) |
6d0d4fc2 YCH |
71 | elif ext == 'smil': |
72 | formats.extend(self._extract_smil_formats( | |
73 | medium_url, 'stream', fatal=False)) | |
74 | else: | |
75 | a_format = { | |
76 | 'url': medium_url | |
77 | } | |
78 | if ext == 'unknown_video': | |
79 | urlh = self._request_webpage( | |
54e8f62e | 80 | medium_url, video_id, note='Determining extension') |
6d0d4fc2 YCH |
81 | ext = urlhandle_detect_ext(urlh) |
82 | a_format['ext'] = ext | |
83 | formats.append(a_format) | |
84 | ||
85 | self._sort_formats(formats) | |
86 | ||
87 | subtitles = {} | |
54e8f62e | 88 | caption_url = media_resource.get('captionURL') |
6d0d4fc2 YCH |
89 | if caption_url: |
90 | subtitles['de'] = [{ | |
91 | 'url': caption_url, | |
92 | 'ext': 'ttml', | |
93 | }] | |
94 | ||
54e8f62e | 95 | title = tracker_data['trackerClipTitle'] |
6d0d4fc2 YCH |
96 | |
97 | return { | |
54e8f62e S |
98 | 'id': tracker_data.get('trackerClipId', video_id), |
99 | 'title': self._live_title(title) if is_live else title, | |
100 | 'alt_title': tracker_data.get('trackerClipSubcategory'), | |
6d0d4fc2 YCH |
101 | 'formats': formats, |
102 | 'subtitles': subtitles, | |
54e8f62e S |
103 | 'upload_date': unified_strdate(tracker_data.get('trackerClipAirTime')), |
104 | 'is_live': is_live, | |
6d0d4fc2 YCH |
105 | } |
106 | ||
107 | ||
54e8f62e | 108 | class WDRPageIE(InfoExtractor): |
949fc42e | 109 | _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5' |
54e8f62e S |
110 | _PAGE_REGEX = r'/(?:mediathek/)?(?:[^/]+/)*(?P<display_id>[^/]+)\.html' |
111 | _VALID_URL = r'https?://(?:www\d?\.)?(?:wdr\d?|sportschau)\.de' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL | |
c0837a12 | 112 | |
b461641f S |
113 | _TESTS = [ |
114 | { | |
c0837a12 | 115 | 'url': 'http://www1.wdr.de/mediathek/video/sendungen/doku-am-freitag/video-geheimnis-aachener-dom-100.html', |
a4a8201c | 116 | # HDS download, MD5 is unstable |
b461641f | 117 | 'info_dict': { |
c0837a12 | 118 | 'id': 'mdb-1058683', |
b461641f | 119 | 'ext': 'flv', |
c0837a12 BW |
120 | 'display_id': 'doku-am-freitag/video-geheimnis-aachener-dom-100', |
121 | 'title': 'Geheimnis Aachener Dom', | |
122 | 'alt_title': 'Doku am Freitag', | |
123 | 'upload_date': '20160304', | |
124 | 'description': 'md5:87be8ff14d8dfd7a7ee46f0299b52318', | |
125 | 'is_live': False, | |
126 | 'subtitles': {'de': [{ | |
bc7e7adf YCH |
127 | 'url': 'http://ondemand-ww.wdr.de/medp/fsk0/105/1058683/1058683_12220974.xml', |
128 | 'ext': 'ttml', | |
c0837a12 | 129 | }]}, |
b461641f | 130 | }, |
54e8f62e | 131 | 'skip': 'HTTP Error 404: Not Found', |
b461641f S |
132 | }, |
133 | { | |
c0837a12 BW |
134 | 'url': 'http://www1.wdr.de/mediathek/audio/wdr3/wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100.html', |
135 | 'md5': 'f4c1f96d01cf285240f53ea4309663d8', | |
b461641f | 136 | 'info_dict': { |
c0837a12 | 137 | 'id': 'mdb-1072000', |
b461641f | 138 | 'ext': 'mp3', |
c0837a12 BW |
139 | 'display_id': 'wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100', |
140 | 'title': 'Schriftstellerin Juli Zeh', | |
141 | 'alt_title': 'WDR 3 Gespräch am Samstag', | |
142 | 'upload_date': '20160312', | |
143 | 'description': 'md5:e127d320bc2b1f149be697ce044a3dd7', | |
144 | 'is_live': False, | |
145 | 'subtitles': {} | |
b461641f | 146 | }, |
54e8f62e | 147 | 'skip': 'HTTP Error 404: Not Found', |
b461641f | 148 | }, |
176cf9e0 | 149 | { |
c0837a12 | 150 | 'url': 'http://www1.wdr.de/mediathek/video/live/index.html', |
dd8982f1 | 151 | 'info_dict': { |
54e8f62e | 152 | 'id': 'mdb-1406149', |
bec2c14f | 153 | 'ext': 'mp4', |
54e8f62e | 154 | 'title': r're:^WDR Fernsehen im Livestream \(nur in Deutschland erreichbar\) [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', |
c0837a12 | 155 | 'alt_title': 'WDR Fernsehen Live', |
54e8f62e | 156 | 'upload_date': '20150101', |
c0837a12 | 157 | 'is_live': True, |
bec2c14f BW |
158 | }, |
159 | 'params': { | |
160 | 'skip_download': True, # m3u8 download | |
161 | }, | |
b8988b63 AA |
162 | }, |
163 | { | |
c0837a12 | 164 | 'url': 'http://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html', |
54e8f62e | 165 | 'playlist_mincount': 7, |
b8988b63 | 166 | 'info_dict': { |
54e8f62e | 167 | 'id': 'aktuelle-stunde-120', |
b8988b63 | 168 | }, |
14f7a2b8 BW |
169 | }, |
170 | { | |
171 | 'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5', | |
172 | 'info_dict': { | |
54e8f62e | 173 | 'id': 'mdb-1552552', |
f802c486 | 174 | 'ext': 'mp4', |
14f7a2b8 BW |
175 | 'upload_date': 're:^[0-9]{8}$', |
176 | 'title': 're:^Die Sendung mit der Maus vom [0-9.]{10}$', | |
14f7a2b8 BW |
177 | }, |
178 | 'skip': 'The id changes from week to week because of the new episode' | |
179 | }, | |
949fc42e | 180 | { |
f802c486 | 181 | 'url': 'http://www.wdrmaus.de/filme/sachgeschichten/achterbahn.php5', |
6d0d4fc2 | 182 | 'md5': '803138901f6368ee497b4d195bb164f2', |
949fc42e BW |
183 | 'info_dict': { |
184 | 'id': 'mdb-186083', | |
6d0d4fc2 | 185 | 'ext': 'mp4', |
949fc42e BW |
186 | 'upload_date': '20130919', |
187 | 'title': 'Sachgeschichte - Achterbahn ', | |
949fc42e | 188 | }, |
949fc42e | 189 | }, |
50918c4e YCH |
190 | { |
191 | 'url': 'http://www1.wdr.de/radio/player/radioplayer116~_layout-popupVersion.html', | |
6869d634 | 192 | # Live stream, MD5 unstable |
50918c4e YCH |
193 | 'info_dict': { |
194 | 'id': 'mdb-869971', | |
54e8f62e S |
195 | 'ext': 'mp4', |
196 | 'title': r're:^COSMO Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', | |
50918c4e YCH |
197 | 'upload_date': '20160101', |
198 | }, | |
54e8f62e S |
199 | 'params': { |
200 | 'skip_download': True, # m3u8 download | |
201 | } | |
202 | }, | |
203 | { | |
204 | 'url': 'http://www.sportschau.de/handballem2018/handball-nationalmannschaft-em-stolperstein-vorrunde-100.html', | |
205 | 'info_dict': { | |
206 | 'id': 'mdb-1556012', | |
207 | 'ext': 'mp4', | |
208 | 'title': 'DHB-Vizepräsident Bob Hanning - "Die Weltspitze ist extrem breit"', | |
209 | 'upload_date': '20180111', | |
210 | }, | |
211 | 'params': { | |
212 | 'skip_download': True, | |
213 | }, | |
214 | }, | |
215 | { | |
216 | 'url': 'http://www.sportschau.de/handballem2018/audio-vorschau---die-handball-em-startet-mit-grossem-favoritenfeld-100.html', | |
217 | 'only_matching': True, | |
50918c4e | 218 | } |
b461641f S |
219 | ] |
220 | ||
221 | def _real_extract(self, url): | |
222 | mobj = re.match(self._VALID_URL, url) | |
c0837a12 BW |
223 | display_id = mobj.group('display_id') |
224 | webpage = self._download_webpage(url, display_id) | |
b461641f | 225 | |
54e8f62e | 226 | entries = [] |
b8988b63 | 227 | |
54e8f62e | 228 | # Article with several videos |
b461641f | 229 | |
54e8f62e S |
230 | # for wdr.de the data-extension is in a tag with the class "mediaLink" |
231 | # for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn" | |
232 | # for wdrmaus, in a tag with the class "videoButton" (previously a link | |
233 | # to the page in a multiline "videoLink"-tag) | |
234 | for mobj in re.finditer( | |
235 | r'''(?sx)class= | |
236 | (?: | |
237 | (["\'])(?:mediaLink|wdrrPlayerPlayBtn|videoButton)\b.*?\1[^>]+| | |
238 | (["\'])videoLink\b.*?\2[\s]*>\n[^\n]* | |
239 | )data-extension=(["\'])(?P<data>(?:(?!\3).)+)\3 | |
240 | ''', webpage): | |
241 | media_link_obj = self._parse_json( | |
242 | mobj.group('data'), display_id, transform_source=js_to_json, | |
243 | fatal=False) | |
244 | if not media_link_obj: | |
245 | continue | |
246 | jsonp_url = try_get( | |
247 | media_link_obj, lambda x: x['mediaObj']['url'], compat_str) | |
248 | if jsonp_url: | |
249 | entries.append(self.url_result(jsonp_url, ie=WDRIE.ie_key())) | |
6d0d4fc2 | 250 | |
54e8f62e S |
251 | # Playlist (e.g. https://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html) |
252 | if not entries: | |
253 | entries = [ | |
254 | self.url_result( | |
255 | compat_urlparse.urljoin(url, mobj.group('href')), | |
256 | ie=WDRPageIE.ie_key()) | |
257 | for mobj in re.finditer( | |
258 | r'<a[^>]+\bhref=(["\'])(?P<href>(?:(?!\1).)+)\1[^>]+\bdata-extension=', | |
259 | webpage) if re.match(self._PAGE_REGEX, mobj.group('href')) | |
260 | ] | |
cd7481a3 | 261 | |
54e8f62e | 262 | return self.playlist_result(entries, playlist_id=display_id) |
cd7481a3 | 263 | |
2d8bb80c | 264 | |
54e8f62e S |
265 | class WDRElefantIE(InfoExtractor): |
266 | _VALID_URL = r'https?://(?:www\.)wdrmaus\.de/elefantenseite/#(?P<id>.+)' | |
267 | _TEST = { | |
268 | 'url': 'http://www.wdrmaus.de/elefantenseite/#folge_ostern_2015', | |
269 | 'info_dict': { | |
270 | 'title': 'Folge Oster-Spezial 2015', | |
271 | 'id': 'mdb-1088195', | |
272 | 'ext': 'mp4', | |
273 | 'age_limit': None, | |
274 | 'upload_date': '20150406' | |
2d8bb80c | 275 | }, |
54e8f62e S |
276 | 'params': { |
277 | 'skip_download': True, | |
278 | }, | |
279 | } | |
2d8bb80c SL |
280 | |
281 | def _real_extract(self, url): | |
54e8f62e | 282 | display_id = self._match_id(url) |
2d8bb80c SL |
283 | |
284 | # Table of Contents seems to always be at this address, so fetch it directly. | |
285 | # The website fetches configurationJS.php5, which links to tableOfContentsJS.php5. | |
286 | table_of_contents = self._download_json( | |
54e8f62e S |
287 | 'https://www.wdrmaus.de/elefantenseite/data/tableOfContentsJS.php5', |
288 | display_id) | |
2d8bb80c SL |
289 | if display_id not in table_of_contents: |
290 | raise ExtractorError( | |
291 | 'No entry in site\'s table of contents for this URL. ' | |
292 | 'Is the fragment part of the URL (after the #) correct?', | |
293 | expected=True) | |
294 | xml_metadata_path = table_of_contents[display_id]['xmlPath'] | |
295 | xml_metadata = self._download_xml( | |
54e8f62e S |
296 | 'https://www.wdrmaus.de/elefantenseite/' + xml_metadata_path, |
297 | display_id) | |
2d8bb80c SL |
298 | zmdb_url_element = xml_metadata.find('./movie/zmdb_url') |
299 | if zmdb_url_element is None: | |
300 | raise ExtractorError( | |
54e8f62e S |
301 | '%s is not a video' % display_id, expected=True) |
302 | return self.url_result(zmdb_url_element.text, ie=WDRIE.ie_key()) | |
2d8bb80c SL |
303 | |
304 | ||
e4cbb5f3 PH |
305 | class WDRMobileIE(InfoExtractor): |
306 | _VALID_URL = r'''(?x) | |
307 | https?://mobile-ondemand\.wdr\.de/ | |
308 | .*?/fsk(?P<age_limit>[0-9]+) | |
309 | /[0-9]+/[0-9]+/ | |
310 | (?P<id>[0-9]+)_(?P<title>[0-9]+)''' | |
311 | IE_NAME = 'wdr:mobile' | |
312 | _TEST = { | |
313 | 'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4', | |
314 | 'info_dict': { | |
315 | 'title': '4283021', | |
316 | 'id': '421735', | |
7807ee66 | 317 | 'ext': 'mp4', |
e4cbb5f3 PH |
318 | 'age_limit': 0, |
319 | }, | |
7807ee66 | 320 | 'skip': 'Problems with loading data.' |
e4cbb5f3 PH |
321 | } |
322 | ||
323 | def _real_extract(self, url): | |
324 | mobj = re.match(self._VALID_URL, url) | |
325 | return { | |
326 | 'id': mobj.group('id'), | |
327 | 'title': mobj.group('title'), | |
328 | 'age_limit': int(mobj.group('age_limit')), | |
329 | 'url': url, | |
e1554a40 JMF |
330 | 'http_headers': { |
331 | 'User-Agent': 'mobile', | |
332 | }, | |
e4cbb5f3 | 333 | } |