1 # -*- coding: utf-8 -*-
2 from __future__ import unicode_literals
6 from .common import InfoExtractor
17 class WDRIE(InfoExtractor):
18 _PLAYER_REGEX = '-(?:video|audio)player(?:_size-[LMS])?'
19 _VALID_URL = r'(?P<url>https?://www\d?\.(?:wdr\d?|funkhauseuropa)\.de/)(?P<id>.+?)(?P<player>%s)?\.html' % _PLAYER_REGEX
23 'url': 'http://www1.wdr.de/mediathek/video/sendungen/servicezeit/videoservicezeit560-videoplayer_size-L.html',
27 'title': 'Servicezeit',
28 'description': 'md5:c8f43e5e815eeb54d0b96df2fba906cb',
29 'upload_date': '20140310',
32 'skip_download': True,
36 'url': 'http://www1.wdr.de/themen/av/videomargaspiegelisttot101-videoplayer.html',
40 'title': 'Marga Spiegel ist tot',
41 'description': 'md5:2309992a6716c347891c045be50992e4',
42 'upload_date': '20140311',
45 'skip_download': True,
49 'url': 'http://www1.wdr.de/themen/kultur/audioerlebtegeschichtenmargaspiegel100-audioplayer.html',
50 'md5': '83e9e8fefad36f357278759870805898',
54 'title': 'Erlebte Geschichten: Marga Spiegel (29.11.2009)',
55 'description': 'md5:2309992a6716c347891c045be50992e4',
56 'upload_date': '20091129',
60 'url': 'http://www.funkhauseuropa.de/av/audioflaviacoelhoamaramar100-audioplayer.html',
61 'md5': '99a1443ff29af19f6c52cf6f4dc1f4aa',
65 'title': 'Flavia Coelho: Amar é Amar',
66 'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a',
67 'upload_date': '20140717',
72 def _real_extract(self, url):
73 mobj = re.match(self._VALID_URL, url)
74 page_url = mobj.group('url')
75 page_id = mobj.group('id')
77 webpage = self._download_webpage(url, page_id)
79 if mobj.group('player') is None:
81 self.url_result(page_url + href, 'WDR')
82 for href in re.findall(r'<a href="/?(.+?%s\.html)" rel="nofollow"' % self._PLAYER_REGEX, webpage)
84 return self.playlist_result(entries, page_id)
86 flashvars = compat_parse_qs(
87 self._html_search_regex(r'<param name="flashvars" value="([^"]+)"', webpage, 'flashvars'))
89 page_id = flashvars['trackerClipId'][0]
90 video_url = flashvars['dslSrc'][0]
91 title = flashvars['trackerClipTitle'][0]
92 thumbnail = flashvars['startPicture'][0] if 'startPicture' in flashvars else None
94 if 'trackerClipAirTime' in flashvars:
95 upload_date = flashvars['trackerClipAirTime'][0]
97 upload_date = self._html_search_meta('DC.Date', webpage, 'upload date')
100 upload_date = unified_strdate(upload_date)
102 if video_url.endswith('.f4m'):
103 video_url += '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18'
106 ext = determine_ext(video_url)
108 description = self._html_search_meta('Description', webpage, 'description')
115 'description': description,
116 'thumbnail': thumbnail,
117 'upload_date': upload_date,
121 class WDRMobileIE(InfoExtractor):
122 _VALID_URL = r'''(?x)
123 https?://mobile-ondemand\.wdr\.de/
124 .*?/fsk(?P<age_limit>[0-9]+)
126 (?P<id>[0-9]+)_(?P<title>[0-9]+)'''
127 IE_NAME = 'wdr:mobile'
129 'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
136 'skip': 'Problems with loading data.'
139 def _real_extract(self, url):
140 mobj = re.match(self._VALID_URL, url)
142 'id': mobj.group('id'),
143 'title': mobj.group('title'),
144 'age_limit': int(mobj.group('age_limit')),
146 'user_agent': 'mobile',
150 class WDRMausIE(InfoExtractor):
151 _VALID_URL = 'http://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)(?:/index\.php5|(?<!index)\.php5|/(?:$|[?#]))'
152 IE_DESC = 'Sendung mit der Maus'
154 'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
156 'id': 'aktuelle-sendung',
158 'thumbnail': 're:^http://.+\.jpg',
159 'upload_date': 're:^[0-9]{8}$',
160 'title': 're:^[0-9.]{10} - Aktuelle Sendung$',
163 'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/40_jahre_maus.php5',
164 'md5': '3b1227ca3ed28d73ec5737c65743b2a3',
166 'id': '40_jahre_maus',
168 'thumbnail': 're:^http://.+\.jpg',
169 'upload_date': '20131007',
170 'title': '12.03.2011 - 40 Jahre Maus',
174 def _real_extract(self, url):
175 mobj = re.match(self._VALID_URL, url)
176 video_id = mobj.group('id')
178 webpage = self._download_webpage(url, video_id)
179 param_code = self._html_search_regex(
180 r'<a href="\?startVideo=1&([^"]+)"', webpage, 'parameters')
182 title_date = self._search_regex(
183 r'<div class="sendedatum"><p>Sendedatum:\s*([0-9\.]+)</p>',
185 title_str = self._html_search_regex(
186 r'<h1>(.*?)</h1>', webpage, 'title')
187 title = '%s - %s' % (title_date, title_str)
188 upload_date = unified_strdate(
189 self._html_search_meta('dc.date', webpage))
191 fields = compat_parse_qs(param_code)
192 video_url = fields['firstVideo'][0]
193 thumbnail = compat_urlparse.urljoin(url, fields['startPicture'][0])
200 jscode = self._download_webpage(
201 'http://www.wdrmaus.de/codebase/js/extended-medien.min.js',
202 video_id, fatal=False,
203 note='Downloading URL translation table',
204 errnote='Could not download URL translation table')
206 for m in re.finditer(
207 r"stream:\s*'dslSrc=(?P<stream>[^']+)',\s*download:\s*'(?P<dl>[^']+)'\s*\}",
209 if video_url.startswith(m.group('stream')):
210 http_url = video_url.replace(
211 m.group('stream'), m.group('dl'))
218 self._sort_formats(formats)
224 'thumbnail': thumbnail,
225 'upload_date': upload_date,