From 7cf4547ab6dbf5952b58b4c112d96ebc48564ae3 Mon Sep 17 00:00:00 2001 From: rzhxeo Date: Thu, 22 May 2014 10:33:30 +0200 Subject: [PATCH 1/2] [CinemassacreIE] Extract all available video/audio formats --- youtube_dl/extractor/cinemassacre.py | 50 +++++++++++++++------------- 1 file changed, 26 insertions(+), 24 deletions(-) diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py index 2301f61b6..8167a2370 100644 --- a/youtube_dl/extractor/cinemassacre.py +++ b/youtube_dl/extractor/cinemassacre.py @@ -14,7 +14,7 @@ class CinemassacreIE(InfoExtractor): { 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', 'file': '19911.mp4', - 'md5': '782f8504ca95a0eba8fc9177c373eec7', + 'md5': 'fde81fbafaee331785f58cd6c0d46190', 'info_dict': { 'upload_date': '20121110', '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', 'file': '521be8ef82b16.mp4', - 'md5': 'dec39ee5118f8d9cc067f45f9cbe3a35', + 'md5': 'd72f10cd39eac4215048f62ab477a511', 'info_dict': { 'upload_date': '20131002', 'title': 'The Mummy’s Hand (1940)', @@ -51,28 +51,30 @@ class CinemassacreIE(InfoExtractor): webpage, 'description', flags=re.DOTALL, fatal=False) playerdata = self._download_webpage(playerdata_url, video_id) - - sd_url = self._html_search_regex(r'file: \'([^\']+)\', label: \'SD\'', playerdata, 'sd_file') - hd_url = self._html_search_regex( - r'file: \'([^\']+)\', label: \'HD\'', playerdata, 'hd_file', - default=None) - video_thumbnail = self._html_search_regex(r'image: \'(?P[^\']+)\'', playerdata, 'thumbnail', fatal=False) - - formats = [{ - 'url': sd_url, - 'ext': 'mp4', - 'format': 'sd', - 'format_id': 'sd', - 'quality': 1, - }] - if hd_url: - formats.append({ - 'url': hd_url, - 'ext': 'mp4', - 'format': 'hd', - 'format_id': 'hd', - 'quality': 2, - }) + video_thumbnail = self._search_regex(r'image: \'(?P[^\']+)\'', 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') + + videolist = self._download_webpage(videolist_url, video_id) + formats = [] + baseurl = sd_url[:sd_url.rfind('/')+1] + for match in re.finditer('