[cinemassacre] Fix #2815

This commit is contained in:
Philipp Hagemeister 2014-03-24 13:42:20 +01:00
parent 72546c831e
commit 0d3641e589
1 changed files with 25 additions and 21 deletions

View File

@ -9,12 +9,12 @@ from ..utils import (
class CinemassacreIE(InfoExtractor): class CinemassacreIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/.+?' _VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)'
_TESTS = [ _TESTS = [
{ {
'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': 'fde81fbafaee331785f58cd6c0d46190', 'md5': '782f8504ca95a0eba8fc9177c373eec7',
'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': 'd72f10cd39eac4215048f62ab477a511', 'md5': 'dec39ee5118f8d9cc067f45f9cbe3a35',
'info_dict': { 'info_dict': {
'upload_date': '20131002', 'upload_date': '20131002',
'title': 'The Mummys Hand (1940)', 'title': 'The Mummys Hand (1940)',
@ -34,8 +34,9 @@ class CinemassacreIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, 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') video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage) mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
if not mobj: if not mobj:
@ -43,33 +44,36 @@ class CinemassacreIE(InfoExtractor):
playerdata_url = mobj.group('embed_url') playerdata_url = mobj.group('embed_url')
video_id = mobj.group('video_id') video_id = mobj.group('video_id')
video_title = self._html_search_regex(r'<title>(?P<title>.+?)\|', video_title = self._html_search_regex(
webpage, 'title') r'<title>(?P<title>.+?)\|', webpage, '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, 'description', flags=re.DOTALL, fatal=False) webpage, 'description', flags=re.DOTALL, fatal=False)
if len(video_description) == 0:
video_description = None
playerdata = self._download_webpage(playerdata_url, video_id) playerdata = self._download_webpage(playerdata_url, video_id)
sd_url = self._html_search_regex(r'file: \'(?P<sd_file>[^\']+)\', label: \'SD\'', playerdata, 'sd_file') sd_url = self._html_search_regex(r'file: \'([^\']+)\', label: \'SD\'', playerdata, 'sd_file')
hd_url = self._html_search_regex(r'file: \'(?P<hd_file>[^\']+)\', label: \'HD\'', playerdata, 'hd_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) video_thumbnail = self._html_search_regex(r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False)
formats = [ formats = [{
{
'url': sd_url, 'url': sd_url,
'ext': 'mp4', 'ext': 'mp4',
'format': 'sd', 'format': 'sd',
'format_id': 'sd', 'format_id': 'sd',
}, 'quality': 1,
{ }]
if hd_url:
formats.append({
'url': hd_url, 'url': hd_url,
'ext': 'mp4', 'ext': 'mp4',
'format': 'hd', 'format': 'hd',
'format_id': 'hd', 'format_id': 'hd',
}, 'quality': 2,
] })
self._sort_formats(formats)
return { return {
'id': video_id, 'id': video_id,