diff options
author | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2013-10-11 19:53:27 +0200 |
---|---|---|
committer | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2013-10-11 19:53:27 +0200 |
commit | d2f9cdb2058fe3530ba42ba26fe843fb94021f70 (patch) | |
tree | 39af03ac1572eda0405d43175647f95e33bd3df3 /youtube_dl/extractor | |
parent | 3823342d9d0a2c50327aa3e1f85a7e8e1221b0bc (diff) | |
parent | ca215e0a4fdf42cba913f5b21d0e9e0e46814102 (diff) | |
download | youtube-dl-d2f9cdb2058fe3530ba42ba26fe843fb94021f70.tar.xz |
Merge branch 'cinemassacre' of github.com:rzhxeo/youtube-dl into rzhxeo-cinemassacre
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/cinemassacre.py | 115 |
2 files changed, 116 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 688196869..226c3a762 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..17a7916cb --- /dev/null +++ b/youtube_dl/extractor/cinemassacre.py @@ -0,0 +1,115 @@ +# encoding: utf-8 +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, +) + +class CinemassacreIE(InfoExtractor): + _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/', + 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'md5:fb87405fcb42a331742a0dce2708560b', + }, + 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): + 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') + 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 = 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|Cinemassacre)\'', + playerdata, u'base_url') + base_url += '/Cinemassacre/' + # 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 + + 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 |