fenix
/
ytdl-nightly
mirror of https://github.com/ytdl-org/ytdl-nightly.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[CinemassacreIE] Add support for other embed methods

This commit is contained in:
rzhxeo 2013-10-05 13:36:13 +02:00
parent 400afddaf4
commit 1ece880d7c
1 changed files with 22 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
youtube_dl/extractor/cinemassacre.py
View File

@ -20,6 +20,17 @@ class CinemassacreIE(InfoExtractor):
u'params': { u'params': {
u'skip_download': True, u'skip_download': True,
}, },
},
{
u'url': u'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
u'file': u'521be8ef82b16.mp4',
u'info_dict': {
u'upload_date': u'20131002',
u'title': u'The Mummy’s Hand (1940)',
},
u'params': {
u'skip_download': True,
},
}] }]
def _real_extract(self,url): def _real_extract(self,url):
@ -28,19 +39,24 @@ class CinemassacreIE(InfoExtractor):
webpage_url = u'http://' + mobj.group('url') webpage_url = u'http://' + mobj.group('url')
webpage = self._download_webpage(webpage_url, None) # Don't know video id yet webpage = self._download_webpage(webpage_url, None) # Don't know video id yet
video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d') video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
video_id = self._html_search_regex(r'src="http://player\.screenwavemedia\.com/play/embed\.php\?id=(?P<video_id>.+?)"', mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/(?:embed|player)\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
webpage, u'video_id') if not mobj:
video_title = self._html_search_regex(r'<h1 class="entry-title">(?P<title>.+?)</h1>[^<]*</div>', raise ExtractorError(u'Can\'t extract embed url and video id')
playerdata_url = mobj.group(u'embed_url')
video_id = mobj.group(u'video_id')
video_title = self._html_search_regex(r'<title>(?P<title>.+?)\|',
webpage, u'title') webpage, u'title')
video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>', video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>',
webpage, u'description', flags=re.DOTALL, fatal=False) webpage, u'description', flags=re.DOTALL, fatal=False)
if len(video_description) == 0:
video_description = None
playerdata_url = u'http://player.screenwavemedia.com/play/player.php?id=' + video_id
playerdata = self._download_webpage(playerdata_url, video_id) playerdata = self._download_webpage(playerdata_url, video_id)
base_url = self._html_search_regex(r'\'streamer\': \'(?P<base_url>rtmp://[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3})/vod\'', base_url = self._html_search_regex(r'\'streamer\': \'(?P<base_url>rtmp://[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3})/(?:vod|Cinemassacre)\'',
playerdata, u'base_url') playerdata, u'base_url')
base_url += '/Cinemassacre/' base_url += '/Cinemassacre/'
# The file names in playerdata are wrong for some videos??? # Important: The file names in playerdata are not used by the player and even wrong for some videos
sd_file = 'Cinemassacre-%s_high.mp4' % video_id sd_file = 'Cinemassacre-%s_high.mp4' % video_id
hd_file = 'Cinemassacre-%s.mp4' % video_id hd_file = 'Cinemassacre-%s.mp4' % video_id
video_thumbnail = 'http://image.screenwavemedia.com/Cinemassacre/Cinemassacre-%s_thumb_640x360.jpg' % video_id video_thumbnail = 'http://image.screenwavemedia.com/Cinemassacre/Cinemassacre-%s_thumb_640x360.jpg' % video_id