]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/wdr.py
1 # -*- coding: utf-8 -*-
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
15 class WDRIE(InfoExtractor
):
16 _PLAYER_REGEX
= '-(?:video|audio)player(?:_size-[LMS])?'
17 _VALID_URL
= r
'(?P<url>https?://www\d?\.(?:wdr\d?|funkhauseuropa)\.de/)(?P<id>.+?)(?P<player>%s)?\.html' % _PLAYER_REGEX
21 'url': 'http://www1.wdr.de/mediathek/video/sendungen/servicezeit/videoservicezeit560-videoplayer_size-L.html',
25 'title': 'Servicezeit',
26 'description': 'md5:c8f43e5e815eeb54d0b96df2fba906cb',
27 'upload_date': '20140310',
30 'skip_download': True,
34 'url': 'http://www1.wdr.de/themen/av/videomargaspiegelisttot101-videoplayer.html',
38 'title': 'Marga Spiegel ist tot',
39 'description': 'md5:2309992a6716c347891c045be50992e4',
40 'upload_date': '20140311',
43 'skip_download': True,
47 'url': 'http://www1.wdr.de/themen/kultur/audioerlebtegeschichtenmargaspiegel100-audioplayer.html',
48 'md5': '83e9e8fefad36f357278759870805898',
52 'title': 'Erlebte Geschichten: Marga Spiegel (29.11.2009)',
53 'description': 'md5:2309992a6716c347891c045be50992e4',
54 'upload_date': '20091129',
58 'url': 'http://www.funkhauseuropa.de/av/audioflaviacoelhoamaramar100-audioplayer.html',
59 'md5': '99a1443ff29af19f6c52cf6f4dc1f4aa',
63 'title': 'Flavia Coelho: Amar é Amar',
64 'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a',
65 'upload_date': '20140717',
70 def _real_extract(self
, url
):
71 mobj
= re
.match(self
._VALID
_URL
, url
)
72 page_url
= mobj
.group('url')
73 page_id
= mobj
.group('id')
75 webpage
= self
._download
_webpage
(url
, page_id
)
77 if mobj
.group('player') is None:
79 self
.url_result(page_url
+ href
, 'WDR')
80 for href
in re
.findall(r
'<a href="/?(.+?%s\.html)" rel="nofollow"' % self
._PLAYER
_REGEX
, webpage
)
82 return self
.playlist_result(entries
, page_id
)
84 flashvars
= compat_urlparse
.parse_qs(
85 self
._html
_search
_regex
(r
'<param name="flashvars" value="([^"]+)"', webpage
, 'flashvars'))
87 page_id
= flashvars
['trackerClipId'][0]
88 video_url
= flashvars
['dslSrc'][0]
89 title
= flashvars
['trackerClipTitle'][0]
90 thumbnail
= flashvars
['startPicture'][0] if 'startPicture' in flashvars
else None
92 if 'trackerClipAirTime' in flashvars
:
93 upload_date
= flashvars
['trackerClipAirTime'][0]
95 upload_date
= self
._html
_search
_meta
('DC.Date', webpage
, 'upload date')
98 upload_date
= unified_strdate(upload_date
)
100 if video_url
.endswith('.f4m'):
101 video_url
+= '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18'
104 ext
= determine_ext(video_url
)
106 description
= self
._html
_search
_meta
('Description', webpage
, 'description')
113 'description': description
,
114 'thumbnail': thumbnail
,
115 'upload_date': upload_date
,
119 class WDRMobileIE(InfoExtractor
):
120 _VALID_URL
= r
'''(?x)
121 https?://mobile-ondemand\.wdr\.de/
122 .*?/fsk(?P<age_limit>[0-9]+)
124 (?P<id>[0-9]+)_(?P<title>[0-9]+)'''
125 IE_NAME
= 'wdr:mobile'
127 'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
134 'skip': 'Problems with loading data.'
137 def _real_extract(self
, url
):
138 mobj
= re
.match(self
._VALID
_URL
, url
)
140 'id': mobj
.group('id'),
141 'title': mobj
.group('title'),
142 'age_limit': int(mobj
.group('age_limit')),
144 'ext': determine_ext(url
),
145 'user_agent': 'mobile',
149 class WDRMausIE(InfoExtractor
):
150 _VALID_URL
= 'http://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)(?:/index\.php5|(?<!index)\.php5|/(?:$|[?#]))'
151 IE_DESC
= 'Sendung mit der Maus'
153 'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
155 'id': 'aktuelle-sendung',
157 'thumbnail': 're:^http://.+\.jpg',
158 'upload_date': 're:^[0-9]{8}$',
159 'title': 're:^[0-9.]{10} - Aktuelle Sendung$',
162 'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/40_jahre_maus.php5',
163 'md5': '3b1227ca3ed28d73ec5737c65743b2a3',
165 'id': '40_jahre_maus',
167 'thumbnail': 're:^http://.+\.jpg',
168 'upload_date': '20131007',
169 'title': '12.03.2011 - 40 Jahre Maus',
173 def _real_extract(self
, url
):
174 mobj
= re
.match(self
._VALID
_URL
, url
)
175 video_id
= mobj
.group('id')
177 webpage
= self
._download
_webpage
(url
, video_id
)
178 param_code
= self
._html
_search
_regex
(
179 r
'<a href="\?startVideo=1&([^"]+)"', webpage
, 'parameters')
181 title_date
= self
._search
_regex
(
182 r
'<div class="sendedatum"><p>Sendedatum:\s*([0-9\.]+)</p>',
184 title_str
= self
._html
_search
_regex
(
185 r
'<h1>(.*?)</h1>', webpage
, 'title')
186 title
= '%s - %s' % (title_date
, title_str
)
187 upload_date
= unified_strdate(
188 self
._html
_search
_meta
('dc.date', webpage
))
190 fields
= compat_parse_qs(param_code
)
191 video_url
= fields
['firstVideo'][0]
192 thumbnail
= compat_urlparse
.urljoin(url
, fields
['startPicture'][0])
199 jscode
= self
._download
_webpage
(
200 'http://www.wdrmaus.de/codebase/js/extended-medien.min.js',
201 video_id
, fatal
=False,
202 note
='Downloading URL translation table',
203 errnote
='Could not download URL translation table')
205 for m
in re
.finditer(
206 r
"stream:\s*'dslSrc=(?P<stream>[^']+)',\s*download:\s*'(?P<dl>[^']+)'\s*\}",
208 if video_url
.startswith(m
.group('stream')):
209 http_url
= video_url
.replace(
210 m
.group('stream'), m
.group('dl'))
217 self
._sort
_formats
(formats
)
223 'thumbnail': thumbnail
,
224 'upload_date': upload_date
,