[\S\s]+?
(?P.+?)
',
webpage, u'uploader', fatal=False)
- if uploader: uploader = clean_html(uploader)
info = {
'id': video_id,
@@ -3907,9 +3914,8 @@ class SpiegelIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
- video_title = self._search_regex(r'
(.*?)
',
+ video_title = self._html_search_regex(r'
(.*?)
',
webpage, u'title')
- video_title = unescapeHTML(video_title)
xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml'
xml_code = self._download_webpage(xml_url, video_id,
@@ -3948,15 +3954,13 @@ class LiveLeakIE(InfoExtractor):
video_url = self._search_regex(r'file: "(.*?)",',
webpage, u'video URL')
- video_title = self._search_regex(r'
',
+ video_uploader = self._html_search_regex(r'By:.*?(\w+)',
webpage, u'uploader', fatal=False)
info = {
@@ -4009,6 +4013,64 @@ class ARDIE(InfoExtractor):
info["url"] = stream["video_url"]
return [info]
+class ZDFIE(InfoExtractor):
+ _VALID_URL = r'^http://www\.zdf\.de\/ZDFmediathek\/(.*beitrag\/video\/)(?P
[^/\?]+)(?:\?.*)?'
+ _TITLE = r'(?P.*)</h1>'
+ _MEDIA_STREAM = r'<a href="(?P<video_url>.+(?P<media_type>.streaming).+/zdf/(?P<quality>[^\/]+)/[^"]*)".+class="play".+>'
+ _MMS_STREAM = r'href="(?P<video_url>mms://[^"]*)"'
+ _RTSP_STREAM = r'(?P<video_url>rtsp://[^"]*.mp4)'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+ video_id = mobj.group('video_id')
+
+ html = self._download_webpage(url, video_id)
+ streams = [m.groupdict() for m in re.finditer(self._MEDIA_STREAM, html)]
+ if streams is None:
+ raise ExtractorError(u'No media url found.')
+
+ # s['media_type'] == 'wstreaming' -> use 'Windows Media Player' and mms url
+ # s['media_type'] == 'hstreaming' -> use 'Quicktime' and rtsp url
+ # choose first/default media type and highest quality for now
+ for s in streams: #find 300 - dsl1000mbit
+ if s['quality'] == '300' and s['media_type'] == 'wstreaming':
+ stream_=s
+ break
+ for s in streams: #find veryhigh - dsl2000mbit
+ if s['quality'] == 'veryhigh' and s['media_type'] == 'wstreaming': # 'hstreaming' - rtsp is not working
+ stream_=s
+ break
+ if stream_ is None:
+ raise ExtractorError(u'No stream found.')
+
+ media_link = self._download_webpage(stream_['video_url'], video_id,'Get stream URL')
+
+ self.report_extraction(video_id)
+ mobj = re.search(self._TITLE, html)
+ if mobj is None:
+ raise ExtractorError(u'Cannot extract title')
+ title = unescapeHTML(mobj.group('title'))
+
+ mobj = re.search(self._MMS_STREAM, media_link)
+ if mobj is None:
+ mobj = re.search(self._RTSP_STREAM, media_link)
+ if mobj is None:
+ raise ExtractorError(u'Cannot extract mms:// or rtsp:// URL')
+ mms_url = mobj.group('video_url')
+
+ mobj = re.search('(.*)[.](?P<ext>[^.]+)', mms_url)
+ if mobj is None:
+ raise ExtractorError(u'Cannot extract extention')
+ ext = mobj.group('ext')
+
+ return [{'id': video_id,
+ 'url': mms_url,
+ 'title': title,
+ 'ext': ext
+ }]
+
class TumblrIE(InfoExtractor):
_VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)/(.*?)'
@@ -4033,9 +4095,8 @@ class TumblrIE(InfoExtractor):
# The only place where you can get a title, it's not complete,
# but searching in other places doesn't work for all videos
- video_title = self._search_regex(r'<title>(?P<title>.*?)',
+ video_title = self._html_search_regex(r'(?P<title>.*?)',
webpage, u'title', flags=re.DOTALL)
- video_title = unescapeHTML(video_title)
return [{'id': video_id,
'url': video_url,
@@ -4105,10 +4166,10 @@ class RedTubeIE(InfoExtractor):
self.report_extraction(video_id)
- video_url = self._search_regex(r'',
+ video_url = self._html_search_regex(r'',
webpage, u'video URL')
- video_title = self._search_regex('(.+?)
',
+ video_title = self._html_search_regex('(.+?)
',
webpage, u'title')
return [{
@@ -4132,7 +4193,7 @@ class InaIE(InfoExtractor):
self.report_extraction(video_id)
- video_url = self._search_regex(r'.*?)]]>',
@@ -4161,13 +4222,13 @@ class HowcastIE(InfoExtractor):
video_url = self._search_regex(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)',
webpage, u'video URL')
- video_title = self._search_regex(r'.*?(.+?)
',
+ uploader = self._html_search_regex(r'