[CinemassacreIE] Extract all available video/audio formats

This commit is contained in:
rzhxeo 2014-05-22 10:33:30 +02:00
parent eec4d8ef96
commit 7cf4547ab6

View file

@ -14,7 +14,7 @@ class CinemassacreIE(InfoExtractor):
{ {
'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
'file': '19911.mp4', 'file': '19911.mp4',
'md5': '782f8504ca95a0eba8fc9177c373eec7', 'md5': 'fde81fbafaee331785f58cd6c0d46190',
'info_dict': { 'info_dict': {
'upload_date': '20121110', 'upload_date': '20121110',
'title': '“Angry Video Game Nerd: The Movie” Trailer', 'title': '“Angry Video Game Nerd: The Movie” Trailer',
@ -24,7 +24,7 @@ class CinemassacreIE(InfoExtractor):
{ {
'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940', 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
'file': '521be8ef82b16.mp4', 'file': '521be8ef82b16.mp4',
'md5': 'dec39ee5118f8d9cc067f45f9cbe3a35', 'md5': 'd72f10cd39eac4215048f62ab477a511',
'info_dict': { 'info_dict': {
'upload_date': '20131002', 'upload_date': '20131002',
'title': 'The Mummys Hand (1940)', 'title': 'The Mummys Hand (1940)',
@ -51,28 +51,30 @@ class CinemassacreIE(InfoExtractor):
webpage, 'description', flags=re.DOTALL, fatal=False) webpage, 'description', flags=re.DOTALL, fatal=False)
playerdata = self._download_webpage(playerdata_url, video_id) playerdata = self._download_webpage(playerdata_url, video_id)
video_thumbnail = self._search_regex(r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False)
sd_url = self._search_regex(r'file: \'([^\']+)\', label: \'SD\'', playerdata, 'sd_file')
videolist_url = self._search_regex(r'file: \'([^\']+\.smil)\'}', playerdata, 'videolist_url')
sd_url = self._html_search_regex(r'file: \'([^\']+)\', label: \'SD\'', playerdata, 'sd_file') videolist = self._download_webpage(videolist_url, video_id)
hd_url = self._html_search_regex( formats = []
r'file: \'([^\']+)\', label: \'HD\'', playerdata, 'hd_file', baseurl = sd_url[:sd_url.rfind('/')+1]
default=None) for match in re.finditer('<video src="mp4:(?P<file>[^"]+_(?P<format_id>[^"]+)\.[^"]+)" system-bitrate="(?P<br>\d+)"(?: width="(?P<width>\d+)" height="(?P<height>\d+)")?/>', videolist):
video_thumbnail = self._html_search_regex(r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False) format = {
'url': baseurl + match.group('file'),
formats = [{ 'format_id': match.group('format_id')
'url': sd_url, }
'ext': 'mp4', if match.group('width'):
'format': 'sd', format.update({
'format_id': 'sd', 'tbr': int(match.group('br')) // 1000,
'quality': 1, 'width': int(match.group('width')),
}] 'height': int(match.group('height'))
if hd_url:
formats.append({
'url': hd_url,
'ext': 'mp4',
'format': 'hd',
'format_id': 'hd',
'quality': 2,
}) })
else:
format.update({
'abr': int(match.group('br')) // 1000,
'vcodec': 'none'
})
formats.append(format)
self._sort_formats(formats) self._sort_formats(formats)
return { return {