From 0d3641e589288a46903333a6e47ec4e18f6c39d5 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 24 Mar 2014 13:42:20 +0100 Subject: [PATCH] [cinemassacre] Fix #2815 --- youtube_dl/extractor/cinemassacre.py | 46 +++++++++++++++------------- 1 file changed, 25 insertions(+), 21 deletions(-) diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py index bfbffefdc..2301f61b6 100644 --- a/youtube_dl/extractor/cinemassacre.py +++ b/youtube_dl/extractor/cinemassacre.py @@ -9,12 +9,12 @@ class CinemassacreIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P[0-9]{4})/(?P[0-9]{2})/(?P[0-9]{2})/.+?' + _VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P[0-9]{4})/(?P[0-9]{2})/(?P[0-9]{2})/(?P[^?#/]+)' _TESTS = [ { 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', 'file': '19911.mp4', - 'md5': 'fde81fbafaee331785f58cd6c0d46190', + 'md5': '782f8504ca95a0eba8fc9177c373eec7', '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': 'd72f10cd39eac4215048f62ab477a511', + 'md5': 'dec39ee5118f8d9cc067f45f9cbe3a35', 'info_dict': { 'upload_date': '20131002', 'title': 'The Mummy’s Hand (1940)', @@ -34,8 +34,9 @@ class CinemassacreIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') - webpage = self._download_webpage(url, None) # Don't know video id yet + webpage = self._download_webpage(url, display_id) video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d') mobj = re.search(r'src="(?Phttp://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?id=(?:Cinemassacre-)?(?P.+?))"', webpage) if not mobj: @@ -43,33 +44,36 @@ def _real_extract(self, url): playerdata_url = mobj.group('embed_url') video_id = mobj.group('video_id') - video_title = self._html_search_regex(r'(?P<title>.+?)\|', - webpage, 'title') - video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>', + video_title = self._html_search_regex( + r'<title>(?P<title>.+?)\|', webpage, 'title') + video_description = self._html_search_regex( + r'<div class="entry-content">(?P<description>.+?)</div>', webpage, 'description', flags=re.DOTALL, fatal=False) - if len(video_description) == 0: - video_description = None playerdata = self._download_webpage(playerdata_url, video_id) - sd_url = self._html_search_regex(r'file: \'(?P<sd_file>[^\']+)\', label: \'SD\'', playerdata, 'sd_file') - hd_url = self._html_search_regex(r'file: \'(?P<hd_file>[^\']+)\', label: \'HD\'', playerdata, 'hd_file') + 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<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False) - formats = [ - { - 'url': sd_url, - 'ext': 'mp4', - 'format': 'sd', - 'format_id': 'sd', - }, - { + 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, + }) + self._sort_formats(formats) return { 'id': video_id,