]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/wdr.py
1 # -*- coding: utf-8 -*-
2 from __future__
import unicode_literals
7 from .common
import InfoExtractor
18 class WDRIE(InfoExtractor
):
19 _PLAYER_REGEX
= '-(?:video|audio)player(?:_size-[LMS])?'
20 _VALID_URL
= r
'(?P<url>https?://www\d?\.(?:wdr\d?|funkhauseuropa)\.de/)(?P<id>.+?)(?P<player>%s)?\.html' % _PLAYER_REGEX
24 'url': 'http://www1.wdr.de/mediathek/video/sendungen/servicezeit/videoservicezeit560-videoplayer_size-L.html',
28 'title': 'Servicezeit',
29 'description': 'md5:c8f43e5e815eeb54d0b96df2fba906cb',
30 'upload_date': '20140310',
34 'skip_download': True,
36 'skip': 'Page Not Found',
39 'url': 'http://www1.wdr.de/themen/av/videomargaspiegelisttot101-videoplayer.html',
43 'title': 'Marga Spiegel ist tot',
44 'description': 'md5:2309992a6716c347891c045be50992e4',
45 'upload_date': '20140311',
49 'skip_download': True,
51 'skip': 'Page Not Found',
54 'url': 'http://www1.wdr.de/themen/kultur/audioerlebtegeschichtenmargaspiegel100-audioplayer.html',
55 'md5': '83e9e8fefad36f357278759870805898',
59 'title': 'Erlebte Geschichten: Marga Spiegel (29.11.2009)',
60 'description': 'md5:2309992a6716c347891c045be50992e4',
61 'upload_date': '20091129',
66 'url': 'http://www.funkhauseuropa.de/av/audioflaviacoelhoamaramar100-audioplayer.html',
67 'md5': '99a1443ff29af19f6c52cf6f4dc1f4aa',
71 'title': 'Flavia Coelho: Amar é Amar',
72 'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a',
73 'upload_date': '20140717',
76 'skip': 'Page Not Found',
79 'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html',
80 'playlist_mincount': 146,
82 'id': 'mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100',
86 'url': 'http://www1.wdr.de/mediathek/video/livestream/index.html',
89 'title': 're:^WDR Fernsehen Live [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
90 'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9',
92 'upload_date': '20150101',
96 'skip_download': True,
101 def _real_extract(self
, url
):
102 mobj
= re
.match(self
._VALID
_URL
, url
)
103 page_url
= mobj
.group('url')
104 page_id
= mobj
.group('id')
106 webpage
= self
._download
_webpage
(url
, page_id
)
108 if mobj
.group('player') is None:
110 self
.url_result(page_url
+ href
, 'WDR')
111 for href
in re
.findall(r
'<a href="/?(.+?%s\.html)" rel="nofollow"' % self
._PLAYER
_REGEX
, webpage
)
114 if entries
: # Playlist page
115 return self
.playlist_result(entries
, page_id
)
119 for page_num
in itertools
.count(2):
121 r
'<li class="mediathekvideo"\s*>\s*<img[^>]*>\s*<a href="(/mediathek/video/[^"]+)"',
124 self
.url_result(page_url
+ href
, 'WDR')
126 next_url_m
= re
.search(
127 r
'<li class="nextToLast">\s*<a href="([^"]+)"', webpage
)
130 next_url
= page_url
+ next_url_m
.group(1)
131 webpage
= self
._download
_webpage
(
133 note
='Downloading playlist page %d' % page_num
)
134 return self
.playlist_result(entries
, page_id
)
136 flashvars
= compat_parse_qs(
137 self
._html
_search
_regex
(r
'<param name="flashvars" value="([^"]+)"', webpage
, 'flashvars'))
139 page_id
= flashvars
['trackerClipId'][0]
140 video_url
= flashvars
['dslSrc'][0]
141 title
= flashvars
['trackerClipTitle'][0]
142 thumbnail
= flashvars
['startPicture'][0] if 'startPicture' in flashvars
else None
143 is_live
= flashvars
.get('isLive', ['0'])[0] == '1'
146 title
= self
._live
_title
(title
)
148 if 'trackerClipAirTime' in flashvars
:
149 upload_date
= flashvars
['trackerClipAirTime'][0]
151 upload_date
= self
._html
_search
_meta
('DC.Date', webpage
, 'upload date')
154 upload_date
= unified_strdate(upload_date
)
157 preference
= qualities(['S', 'M', 'L', 'XL'])
159 if video_url
.endswith('.f4m'):
160 f4m_formats
= self
._extract
_f
4m
_formats
(video_url
+ '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', page_id
, f4m_id
='hds', fatal
=False)
162 formats
.extend(f4m_formats
)
163 elif video_url
.endswith('.smil'):
164 smil_formats
= self
._extract
_smil
_formats
(video_url
, page_id
, False, {
166 'plugin': 'aasp-3.3.0.99.43',
169 formats
.extend(smil_formats
)
174 'User-Agent': 'mobile',
178 m3u8_url
= self
._search
_regex
(r
'rel="adaptiv"[^>]+href="([^"]+)"', webpage
, 'm3u8 url', default
=None)
180 m3u8_formats
= self
._extract
_m
3u8_formats
(m3u8_url
, page_id
, 'mp4', 'm3u8_native', m3u8_id
='hls', fatal
=False)
182 formats
.extend(m3u8_formats
)
184 direct_urls
= re
.findall(r
'rel="web(S|M|L|XL)"[^>]+href="([^"]+)"', webpage
)
186 for quality
, video_url
in direct_urls
:
189 'preference': preference(quality
),
191 'User-Agent': 'mobile',
195 self
._sort
_formats
(formats
)
197 description
= self
._html
_search
_meta
('Description', webpage
, 'description')
203 'description': description
,
204 'thumbnail': thumbnail
,
205 'upload_date': upload_date
,
210 class WDRMobileIE(InfoExtractor
):
211 _VALID_URL
= r
'''(?x)
212 https?://mobile-ondemand\.wdr\.de/
213 .*?/fsk(?P<age_limit>[0-9]+)
215 (?P<id>[0-9]+)_(?P<title>[0-9]+)'''
216 IE_NAME
= 'wdr:mobile'
218 'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
225 'skip': 'Problems with loading data.'
228 def _real_extract(self
, url
):
229 mobj
= re
.match(self
._VALID
_URL
, url
)
231 'id': mobj
.group('id'),
232 'title': mobj
.group('title'),
233 'age_limit': int(mobj
.group('age_limit')),
236 'User-Agent': 'mobile',
241 class WDRMausIE(InfoExtractor
):
242 _VALID_URL
= 'http://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)(?:/index\.php5|(?<!index)\.php5|/(?:$|[?#]))'
243 IE_DESC
= 'Sendung mit der Maus'
245 'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
247 'id': 'aktuelle-sendung',
249 'thumbnail': 're:^http://.+\.jpg',
250 'upload_date': 're:^[0-9]{8}$',
251 'title': 're:^[0-9.]{10} - Aktuelle Sendung$',
254 'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/40_jahre_maus.php5',
255 'md5': '3b1227ca3ed28d73ec5737c65743b2a3',
257 'id': '40_jahre_maus',
259 'thumbnail': 're:^http://.+\.jpg',
260 'upload_date': '20131007',
261 'title': '12.03.2011 - 40 Jahre Maus',
265 def _real_extract(self
, url
):
266 video_id
= self
._match
_id
(url
)
268 webpage
= self
._download
_webpage
(url
, video_id
)
269 param_code
= self
._html
_search
_regex
(
270 r
'<a href="\?startVideo=1&([^"]+)"', webpage
, 'parameters')
272 title_date
= self
._search
_regex
(
273 r
'<div class="sendedatum"><p>Sendedatum:\s*([0-9\.]+)</p>',
275 title_str
= self
._html
_search
_regex
(
276 r
'<h1>(.*?)</h1>', webpage
, 'title')
277 title
= '%s - %s' % (title_date
, title_str
)
278 upload_date
= unified_strdate(
279 self
._html
_search
_meta
('dc.date', webpage
))
281 fields
= compat_parse_qs(param_code
)
282 video_url
= fields
['firstVideo'][0]
283 thumbnail
= compat_urlparse
.urljoin(url
, fields
['startPicture'][0])
290 jscode
= self
._download
_webpage
(
291 'http://www.wdrmaus.de/codebase/js/extended-medien.min.js',
292 video_id
, fatal
=False,
293 note
='Downloading URL translation table',
294 errnote
='Could not download URL translation table')
296 for m
in re
.finditer(
297 r
"stream:\s*'dslSrc=(?P<stream>[^']+)',\s*download:\s*'(?P<dl>[^']+)'\s*\}",
299 if video_url
.startswith(m
.group('stream')):
300 http_url
= video_url
.replace(
301 m
.group('stream'), m
.group('dl'))
308 self
._sort
_formats
(formats
)
314 'thumbnail': thumbnail
,
315 'upload_date': upload_date
,