From 400afddaf49353c9b4c31d17d5efe4045e500fec Mon Sep 17 00:00:00 2001 From: rzhxeo Date: Sat, 5 Oct 2013 09:37:11 +0200 Subject: [PATCH 1/4] Add CinemassacreIE --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/cinemassacre.py | 100 +++++++++++++++++++++++++++ 2 files changed, 101 insertions(+) create mode 100644 youtube_dl/extractor/cinemassacre.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index d1b7e5f99..db30edc27 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -12,6 +12,7 @@ from .brightcove import BrightcoveIE from .c56 import C56IE from .canalplus import CanalplusIE from .canalc2 import Canalc2IE +from .cinemassacre import CinemassacreIE from .cnn import CNNIE from .collegehumor import CollegeHumorIE from .comedycentral import ComedyCentralIE diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py new file mode 100644 index 000000000..16eaff3a1 --- /dev/null +++ b/youtube_dl/extractor/cinemassacre.py @@ -0,0 +1,100 @@ +# encoding: utf-8 +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, +) + +class CinemassacreIE(InfoExtractor): + """Information Extractor for Cinemassacre""" + _VALID_URL = r'(?:http://)?(?:www\.)?(?Pcinemassacre\.com/(?P[0-9]{4})/(?P[0-9]{2})/(?P[0-9]{2})/.+?)(?:[/?].*)?' + _TESTS = [{ + u'url': u'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', + u'file': u'19911.mp4', + u'info_dict': { + u'upload_date': u'20121110', + u'title': u'“Angry Video Game Nerd: The Movie” – Trailer', + #u'description': u'“Angry Video Game Nerd: The Movie” is...', # Description is too long + }, + u'params': { + u'skip_download': True, + }, + }] + + def _real_extract(self,url): + mobj = re.match(self._VALID_URL, url) + + webpage_url = u'http://' + mobj.group('url') + webpage = self._download_webpage(webpage_url, None) # Don't know video id yet + video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d') + video_id = self._html_search_regex(r'src="http://player\.screenwavemedia\.com/play/embed\.php\?id=(?P.+?)"', + webpage, u'video_id') + video_title = self._html_search_regex(r'

(?P.+?)</h1>[^<]*</div>', + webpage, u'title') + video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>', + webpage, u'description', flags=re.DOTALL, fatal=False) + + playerdata_url = u'http://player.screenwavemedia.com/play/player.php?id=' + video_id + playerdata = self._download_webpage(playerdata_url, video_id) + base_url = self._html_search_regex(r'\'streamer\': \'(?P<base_url>rtmp://[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3})/vod\'', + playerdata, u'base_url') + base_url += '/Cinemassacre/' + # The file names in playerdata are wrong for some videos??? + sd_file = 'Cinemassacre-%s_high.mp4' % video_id + hd_file = 'Cinemassacre-%s.mp4' % video_id + video_thumbnail = 'http://image.screenwavemedia.com/Cinemassacre/Cinemassacre-%s_thumb_640x360.jpg' % video_id + + formats = [{ + 'id': video_id, + 'url': base_url + hd_file, + 'format': 'hd', + 'ext': 'mp4', + 'title': video_title, + 'description': video_description, + 'upload_date': video_date, + 'thumbnail': video_thumbnail, + }, + { + 'id': video_id, + 'url': base_url + sd_file, + 'ext': 'mp4', + 'format': 'sd', + 'title': video_title, + 'description': video_description, + 'upload_date': video_date, + 'thumbnail': video_thumbnail, + }] + + if self._downloader.params.get('listformats', None): + self._print_formats(formats) + return + + req_format = self._downloader.params.get('format', 'best') + self.to_screen(u'Format: %s' % req_format) + + if req_format is None or req_format == 'best': + return [formats[0]] + elif req_format == 'worst': + return [formats[-1]] + elif req_format in ('-1', 'all'): + return formats + else: + format = self._specific( req_format, formats ) + if format is None: + raise ExtractorError(u'Requested format not available') + return [format] + + def _print_formats(self, formats): + """Print all available formats""" + print(u'Available formats:') + print(u'ext\t\tformat') + print(u'---------------------------------') + for format in formats: + print(u'%s\t\t%s' % (format['ext'], format['format'])) + + def _specific(self, req_format, formats): + for x in formats: + if x["format"] == req_format: + return x + return None From 1ece880d7c94d9b966f52855949aae6c0f37a140 Mon Sep 17 00:00:00 2001 From: rzhxeo <rzhxeot7z81b4700@mailcatch.com> Date: Sat, 5 Oct 2013 13:36:13 +0200 Subject: [PATCH 2/4] [CinemassacreIE] Add support for other embed methods --- youtube_dl/extractor/cinemassacre.py | 28 ++++++++++++++++++++++------ 1 file changed, 22 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py index 16eaff3a1..f0629ee93 100644 --- a/youtube_dl/extractor/cinemassacre.py +++ b/youtube_dl/extractor/cinemassacre.py @@ -20,6 +20,17 @@ class CinemassacreIE(InfoExtractor): u'params': { u'skip_download': True, }, + }, + { + u'url': u'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940', + u'file': u'521be8ef82b16.mp4', + u'info_dict': { + u'upload_date': u'20131002', + u'title': u'The Mummy’s Hand (1940)', + }, + u'params': { + u'skip_download': True, + }, }] def _real_extract(self,url): @@ -28,19 +39,24 @@ class CinemassacreIE(InfoExtractor): webpage_url = u'http://' + mobj.group('url') webpage = self._download_webpage(webpage_url, None) # Don't know video id yet video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d') - video_id = self._html_search_regex(r'src="http://player\.screenwavemedia\.com/play/embed\.php\?id=(?P<video_id>.+?)"', - webpage, u'video_id') - video_title = self._html_search_regex(r'<h1 class="entry-title">(?P<title>.+?)</h1>[^<]*</div>', + mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/(?:embed|player)\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage) + if not mobj: + raise ExtractorError(u'Can\'t extract embed url and video id') + playerdata_url = mobj.group(u'embed_url') + video_id = mobj.group(u'video_id') + + video_title = self._html_search_regex(r'<title>(?P<title>.+?)\|', webpage, u'title') video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>', webpage, u'description', flags=re.DOTALL, fatal=False) + if len(video_description) == 0: + video_description = None - playerdata_url = u'http://player.screenwavemedia.com/play/player.php?id=' + video_id playerdata = self._download_webpage(playerdata_url, video_id) - base_url = self._html_search_regex(r'\'streamer\': \'(?P<base_url>rtmp://[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3})/vod\'', + base_url = self._html_search_regex(r'\'streamer\': \'(?P<base_url>rtmp://[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3})/(?:vod|Cinemassacre)\'', playerdata, u'base_url') base_url += '/Cinemassacre/' - # The file names in playerdata are wrong for some videos??? + # Important: The file names in playerdata are not used by the player and even wrong for some videos sd_file = 'Cinemassacre-%s_high.mp4' % video_id hd_file = 'Cinemassacre-%s.mp4' % video_id video_thumbnail = 'http://image.screenwavemedia.com/Cinemassacre/Cinemassacre-%s_thumb_640x360.jpg' % video_id From 91a26ca559d225307d1bcaac74a5ca499748adc5 Mon Sep 17 00:00:00 2001 From: rzhxeo <rzhxeot7z81b4700@mailcatch.com> Date: Sat, 5 Oct 2013 13:40:05 +0200 Subject: [PATCH 3/4] [CinemassacreIE] Remove docstring from class --- youtube_dl/extractor/cinemassacre.py | 1 - 1 file changed, 1 deletion(-) diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py index f0629ee93..181f57e76 100644 --- a/youtube_dl/extractor/cinemassacre.py +++ b/youtube_dl/extractor/cinemassacre.py @@ -7,7 +7,6 @@ from ..utils import ( ) class CinemassacreIE(InfoExtractor): - """Information Extractor for Cinemassacre""" _VALID_URL = r'(?:http://)?(?:www\.)?(?P<url>cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/.+?)(?:[/?].*)?' _TESTS = [{ u'url': u'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', From ca215e0a4fdf42cba913f5b21d0e9e0e46814102 Mon Sep 17 00:00:00 2001 From: rzhxeo <rzhxeot7z81b4700@mailcatch.com> Date: Sat, 5 Oct 2013 13:42:17 +0200 Subject: [PATCH 4/4] [CinemassacreIE] Use MD5 to check in TEST description --- youtube_dl/extractor/cinemassacre.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py index 181f57e76..17a7916cb 100644 --- a/youtube_dl/extractor/cinemassacre.py +++ b/youtube_dl/extractor/cinemassacre.py @@ -14,7 +14,7 @@ class CinemassacreIE(InfoExtractor): u'info_dict': { u'upload_date': u'20121110', u'title': u'“Angry Video Game Nerd: The Movie” – Trailer', - #u'description': u'“Angry Video Game Nerd: The Movie” is...', # Description is too long + u'description': u'md5:fb87405fcb42a331742a0dce2708560b', }, u'params': { u'skip_download': True,