From d9dd3584e1051b159a748da32cd7d7a1da0bb787 Mon Sep 17 00:00:00 2001 From: =?utf8?q?Sergey=20M=E2=80=A4?= Date: Wed, 28 May 2014 19:38:44 +0700 Subject: [PATCH] [cinemassacre] Improve formats extraction and modernize --- youtube_dl/extractor/cinemassacre.py | 43 ++++++++++++++++++---------- 1 file changed, 28 insertions(+), 15 deletions(-) diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py index 8167a2370..496271be4 100644 --- a/youtube_dl/extractor/cinemassacre.py +++ b/youtube_dl/extractor/cinemassacre.py @@ -1,10 +1,12 @@ # encoding: utf-8 from __future__ import unicode_literals + import re from .common import InfoExtractor from ..utils import ( ExtractorError, + int_or_none, ) @@ -13,9 +15,10 @@ class CinemassacreIE(InfoExtractor): _TESTS = [ { 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', - 'file': '19911.mp4', 'md5': 'fde81fbafaee331785f58cd6c0d46190', 'info_dict': { + 'id': '19911', + 'ext': 'mp4', 'upload_date': '20121110', 'title': '“Angry Video Game Nerd: The Movie” – Trailer', 'description': 'md5:fb87405fcb42a331742a0dce2708560b', @@ -23,9 +26,10 @@ class CinemassacreIE(InfoExtractor): }, { 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940', - 'file': '521be8ef82b16.mp4', 'md5': 'd72f10cd39eac4215048f62ab477a511', 'info_dict': { + 'id': '521be8ef82b16', + 'ext': 'mp4', 'upload_date': '20131002', 'title': 'The Mummy’s Hand (1940)', }, @@ -50,29 +54,38 @@ class CinemassacreIE(InfoExtractor): r'
(?P.+?)
', webpage, 'description', flags=re.DOTALL, fatal=False) - playerdata = self._download_webpage(playerdata_url, video_id) - video_thumbnail = self._search_regex(r'image: \'(?P[^\']+)\'', playerdata, 'thumbnail', fatal=False) + playerdata = self._download_webpage(playerdata_url, video_id, 'Downloading player webpage') + 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) + + videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML') + formats = [] baseurl = sd_url[:sd_url.rfind('/')+1] - for match in re.finditer('