]>
Commit | Line | Data |
---|---|---|
7807ee66 | 1 | # -*- coding: utf-8 -*- |
b461641f S |
2 | from __future__ import unicode_literals |
3 | ||
4 | import re | |
5 | ||
6 | from .common import InfoExtractor | |
1cc79574 | 7 | from ..utils import ( |
bec2c14f | 8 | determine_ext, |
1594a493 | 9 | ExtractorError, |
33a1ff71 | 10 | js_to_json, |
37f97295 | 11 | strip_jsonp, |
cd7481a3 | 12 | unified_strdate, |
6869d634 | 13 | update_url_query, |
50918c4e | 14 | urlhandle_detect_ext, |
b461641f S |
15 | ) |
16 | ||
17 | ||
18 | class WDRIE(InfoExtractor): | |
949fc42e | 19 | _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5' |
1594a493 | 20 | _PAGE_REGEX = r'/(?:mediathek/)?[^/]+/(?P<type>[^/]+)/(?P<display_id>.+)\.html' |
3874e6ea | 21 | _VALID_URL = r'(?P<page_url>https?://(?:www\d\.)?wdr\d?\.de)' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL |
c0837a12 | 22 | |
b461641f S |
23 | _TESTS = [ |
24 | { | |
c0837a12 | 25 | 'url': 'http://www1.wdr.de/mediathek/video/sendungen/doku-am-freitag/video-geheimnis-aachener-dom-100.html', |
a4a8201c | 26 | # HDS download, MD5 is unstable |
b461641f | 27 | 'info_dict': { |
c0837a12 | 28 | 'id': 'mdb-1058683', |
b461641f | 29 | 'ext': 'flv', |
c0837a12 BW |
30 | 'display_id': 'doku-am-freitag/video-geheimnis-aachener-dom-100', |
31 | 'title': 'Geheimnis Aachener Dom', | |
32 | 'alt_title': 'Doku am Freitag', | |
33 | 'upload_date': '20160304', | |
34 | 'description': 'md5:87be8ff14d8dfd7a7ee46f0299b52318', | |
35 | 'is_live': False, | |
36 | 'subtitles': {'de': [{ | |
37 | 'url': 'http://ondemand-ww.wdr.de/medp/fsk0/105/1058683/1058683_12220974.xml' | |
38 | }]}, | |
b461641f S |
39 | }, |
40 | }, | |
41 | { | |
c0837a12 BW |
42 | 'url': 'http://www1.wdr.de/mediathek/audio/wdr3/wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100.html', |
43 | 'md5': 'f4c1f96d01cf285240f53ea4309663d8', | |
b461641f | 44 | 'info_dict': { |
c0837a12 | 45 | 'id': 'mdb-1072000', |
b461641f | 46 | 'ext': 'mp3', |
c0837a12 BW |
47 | 'display_id': 'wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100', |
48 | 'title': 'Schriftstellerin Juli Zeh', | |
49 | 'alt_title': 'WDR 3 Gespräch am Samstag', | |
50 | 'upload_date': '20160312', | |
51 | 'description': 'md5:e127d320bc2b1f149be697ce044a3dd7', | |
52 | 'is_live': False, | |
53 | 'subtitles': {} | |
b461641f S |
54 | }, |
55 | }, | |
176cf9e0 | 56 | { |
c0837a12 | 57 | 'url': 'http://www1.wdr.de/mediathek/video/live/index.html', |
dd8982f1 | 58 | 'info_dict': { |
c0837a12 | 59 | 'id': 'mdb-103364', |
bec2c14f | 60 | 'ext': 'mp4', |
c0837a12 BW |
61 | 'display_id': 'index', |
62 | 'title': r're:^WDR Fernsehen im Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', | |
63 | 'alt_title': 'WDR Fernsehen Live', | |
64 | 'upload_date': None, | |
65 | 'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9', | |
66 | 'is_live': True, | |
67 | 'subtitles': {} | |
bec2c14f BW |
68 | }, |
69 | 'params': { | |
70 | 'skip_download': True, # m3u8 download | |
71 | }, | |
b8988b63 AA |
72 | }, |
73 | { | |
c0837a12 | 74 | 'url': 'http://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html', |
3a686853 | 75 | 'playlist_mincount': 8, |
b8988b63 | 76 | 'info_dict': { |
c0837a12 | 77 | 'id': 'aktuelle-stunde/aktuelle-stunde-120', |
b8988b63 | 78 | }, |
14f7a2b8 BW |
79 | }, |
80 | { | |
81 | 'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5', | |
82 | 'info_dict': { | |
83 | 'id': 'mdb-1096487', | |
84 | 'ext': 'flv', | |
85 | 'upload_date': 're:^[0-9]{8}$', | |
86 | 'title': 're:^Die Sendung mit der Maus vom [0-9.]{10}$', | |
87 | 'description': '- Die Sendung mit der Maus -', | |
88 | }, | |
89 | 'skip': 'The id changes from week to week because of the new episode' | |
90 | }, | |
949fc42e BW |
91 | { |
92 | 'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/achterbahn.php5', | |
a4a8201c | 93 | # HDS download, MD5 is unstable |
949fc42e BW |
94 | 'info_dict': { |
95 | 'id': 'mdb-186083', | |
96 | 'ext': 'flv', | |
97 | 'upload_date': '20130919', | |
98 | 'title': 'Sachgeschichte - Achterbahn ', | |
99 | 'description': '- Die Sendung mit der Maus -', | |
100 | }, | |
949fc42e | 101 | }, |
50918c4e YCH |
102 | { |
103 | 'url': 'http://www1.wdr.de/radio/player/radioplayer116~_layout-popupVersion.html', | |
6869d634 | 104 | # Live stream, MD5 unstable |
50918c4e YCH |
105 | 'info_dict': { |
106 | 'id': 'mdb-869971', | |
6869d634 | 107 | 'ext': 'flv', |
50918c4e YCH |
108 | 'title': 'Funkhaus Europa Livestream', |
109 | 'description': 'md5:2309992a6716c347891c045be50992e4', | |
110 | 'upload_date': '20160101', | |
111 | }, | |
112 | } | |
b461641f S |
113 | ] |
114 | ||
115 | def _real_extract(self, url): | |
116 | mobj = re.match(self._VALID_URL, url) | |
c0837a12 BW |
117 | url_type = mobj.group('type') |
118 | page_url = mobj.group('page_url') | |
119 | display_id = mobj.group('display_id') | |
120 | webpage = self._download_webpage(url, display_id) | |
b461641f | 121 | |
33a1ff71 | 122 | # for wdr.de the data-extension is in a tag with the class "mediaLink" |
50918c4e | 123 | # for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn" |
33a1ff71 BW |
124 | # for wdrmaus its in a link to the page in a multiline "videoLink"-tag |
125 | json_metadata = self._html_search_regex( | |
50918c4e | 126 | r'class=(?:"(?:mediaLink|wdrrPlayerPlayBtn)\b[^"]*"[^>]+|"videoLink\b[^"]*"[\s]*>\n[^\n]*)data-extension="([^"]+)"', |
33a1ff71 | 127 | webpage, 'media link', default=None, flags=re.MULTILINE) |
b461641f | 128 | |
33a1ff71 | 129 | if not json_metadata: |
b461641f | 130 | entries = [ |
c0837a12 | 131 | self.url_result(page_url + href[0], 'WDR') |
03681819 | 132 | for href in re.findall( |
3a686853 | 133 | r'<a href="(%s)"[^>]+data-extension=' % self._PAGE_REGEX, |
03681819 | 134 | webpage) |
b461641f | 135 | ] |
176cf9e0 PH |
136 | |
137 | if entries: # Playlist page | |
c0837a12 | 138 | return self.playlist_result(entries, playlist_id=display_id) |
176cf9e0 | 139 | |
c0837a12 BW |
140 | raise ExtractorError('No downloadable streams found', expected=True) |
141 | ||
33a1ff71 BW |
142 | media_link_obj = self._parse_json(json_metadata, display_id, |
143 | transform_source=js_to_json) | |
144 | jsonp_url = media_link_obj['mediaObj']['url'] | |
145 | ||
37f97295 | 146 | metadata = self._download_json( |
33a1ff71 | 147 | jsonp_url, 'metadata', transform_source=strip_jsonp) |
c0837a12 | 148 | |
3874e6ea BW |
149 | metadata_tracker_data = metadata['trackerData'] |
150 | metadata_media_resource = metadata['mediaResource'] | |
c0837a12 BW |
151 | |
152 | formats = [] | |
153 | ||
154 | # check if the metadata contains a direct URL to a file | |
6869d634 YCH |
155 | for kind, media_resource in metadata_media_resource.items(): |
156 | if kind not in ('dflt', 'alt'): | |
157 | continue | |
158 | ||
159 | for tag_name, medium_url in media_resource.items(): | |
160 | if tag_name not in ('videoURL', 'audioURL'): | |
161 | continue | |
162 | ||
163 | ext = determine_ext(medium_url) | |
164 | if ext == 'm3u8': | |
1594a493 | 165 | formats.extend(self._extract_m3u8_formats( |
6869d634 | 166 | medium_url, display_id, 'mp4', 'm3u8_native', |
1594a493 | 167 | m3u8_id='hls')) |
6869d634 YCH |
168 | elif ext == 'f4m': |
169 | manifest_url = update_url_query( | |
170 | medium_url, {'hdcore': '3.2.0', 'plugin': 'aasp-3.2.0.77.18'}) | |
171 | formats.extend(self._extract_f4m_formats( | |
172 | manifest_url, display_id, f4m_id='hds', fatal=False)) | |
173 | elif ext == 'smil': | |
174 | formats.extend(self._extract_smil_formats( | |
175 | medium_url, 'stream', fatal=False)) | |
176 | else: | |
177 | a_format = { | |
178 | 'url': medium_url | |
179 | } | |
180 | if ext == 'unknown_video': | |
181 | urlh = self._request_webpage( | |
182 | medium_url, display_id, note='Determining extension') | |
183 | ext = urlhandle_detect_ext(urlh) | |
184 | a_format['ext'] = ext | |
185 | formats.append(a_format) | |
c0837a12 | 186 | |
1594a493 YCH |
187 | self._sort_formats(formats) |
188 | ||
c0837a12 | 189 | subtitles = {} |
3874e6ea | 190 | caption_url = metadata_media_resource.get('captionURL') |
c0837a12 BW |
191 | if caption_url: |
192 | subtitles['de'] = [{ | |
193 | 'url': caption_url | |
194 | }] | |
195 | ||
3874e6ea | 196 | title = metadata_tracker_data.get('trackerClipTitle') |
c0837a12 | 197 | is_live = url_type == 'live' |
b8988b63 AA |
198 | |
199 | if is_live: | |
200 | title = self._live_title(title) | |
c0837a12 BW |
201 | upload_date = None |
202 | elif 'trackerClipAirTime' in metadata_tracker_data: | |
203 | upload_date = metadata_tracker_data['trackerClipAirTime'] | |
b461641f | 204 | else: |
c0837a12 | 205 | upload_date = self._html_search_meta('DC.Date', webpage, 'upload date') |
b461641f S |
206 | |
207 | if upload_date: | |
208 | upload_date = unified_strdate(upload_date) | |
209 | ||
b461641f | 210 | return { |
3874e6ea | 211 | 'id': metadata_tracker_data.get('trackerClipId', display_id), |
c0837a12 | 212 | 'display_id': display_id, |
b461641f | 213 | 'title': title, |
3874e6ea | 214 | 'alt_title': metadata_tracker_data.get('trackerClipSubcategory'), |
c0837a12 | 215 | 'formats': formats, |
b461641f | 216 | 'upload_date': upload_date, |
3874e6ea | 217 | 'description': self._html_search_meta('Description', webpage), |
c0837a12 BW |
218 | 'is_live': is_live, |
219 | 'subtitles': subtitles, | |
cd7481a3 PH |
220 | } |
221 | ||
222 | ||
e4cbb5f3 PH |
223 | class WDRMobileIE(InfoExtractor): |
224 | _VALID_URL = r'''(?x) | |
225 | https?://mobile-ondemand\.wdr\.de/ | |
226 | .*?/fsk(?P<age_limit>[0-9]+) | |
227 | /[0-9]+/[0-9]+/ | |
228 | (?P<id>[0-9]+)_(?P<title>[0-9]+)''' | |
229 | IE_NAME = 'wdr:mobile' | |
230 | _TEST = { | |
231 | 'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4', | |
232 | 'info_dict': { | |
233 | 'title': '4283021', | |
234 | 'id': '421735', | |
7807ee66 | 235 | 'ext': 'mp4', |
e4cbb5f3 PH |
236 | 'age_limit': 0, |
237 | }, | |
7807ee66 | 238 | 'skip': 'Problems with loading data.' |
e4cbb5f3 PH |
239 | } |
240 | ||
241 | def _real_extract(self, url): | |
242 | mobj = re.match(self._VALID_URL, url) | |
243 | return { | |
244 | 'id': mobj.group('id'), | |
245 | 'title': mobj.group('title'), | |
246 | 'age_limit': int(mobj.group('age_limit')), | |
247 | 'url': url, | |
e1554a40 JMF |
248 | 'http_headers': { |
249 | 'User-Agent': 'mobile', | |
250 | }, | |
e4cbb5f3 | 251 | } |