From 684712076f1ade9dbe432ad95d5796ec278b73ce Mon Sep 17 00:00:00 2001 From: felix Date: Sun, 7 Dec 2014 11:51:02 +0100 Subject: add direct screenwavemedia.com URL support --- youtube_dl/extractor/screenwavemedia.py | 162 ++++++++++++++++++++++++++++++++ 1 file changed, 162 insertions(+) create mode 100644 youtube_dl/extractor/screenwavemedia.py (limited to 'youtube_dl/extractor/screenwavemedia.py') diff --git a/youtube_dl/extractor/screenwavemedia.py b/youtube_dl/extractor/screenwavemedia.py new file mode 100644 index 000000000..3fb3bfa32 --- /dev/null +++ b/youtube_dl/extractor/screenwavemedia.py @@ -0,0 +1,162 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + int_or_none, +) + +class ScreenwaveMediaIE(InfoExtractor): + _VALID_URL = r'(?:http://)?(?' \ + r':(?Pplayer\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P.+))' \ + r'|(?P(?:www\.)?cinemassacre\.com/(?P[0-9]{4})/(?P[0-9]{2})/(?P[0-9]{2})/(?P[^?#/]+))' \ + r')' + + _TESTS = [ + { + 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', + 'md5': 'fde81fbafaee331785f58cd6c0d46190', + 'info_dict': { + 'id': 'Cinemasssacre-19911', + 'ext': 'mp4', + 'upload_date': '20121110', + 'title': '“Angry Video Game Nerd: The Movie” – Trailer', + 'description': 'md5:fb87405fcb42a331742a0dce2708560b', + }, + }, + { + 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940', + 'md5': 'd72f10cd39eac4215048f62ab477a511', + 'info_dict': { + 'id': 'Cinemasssacre-521be8ef82b16', + 'ext': 'mp4', + 'upload_date': '20131002', + 'title': 'The Mummy’s Hand (1940)', + }, + } + ] + + def _cinemassacre_get_info(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('cm_display_id') + + webpage = self._download_webpage(url, display_id) + video_date = mobj.group('cm_date_Y') + mobj.group('cm_date_m') + mobj.group('cm_date_d') + mobj = re.search(r'src="(?Phttp://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"', webpage) + if not mobj: + raise ExtractorError('Can\'t extract embed url and video id') + playerdata_url = mobj.group('embed_url') + + 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>', + webpage, 'description', flags=re.DOTALL, fatal=False) + video_thumbnail = self._og_search_thumbnail(webpage) + + return { + 'title': video_title, + 'description': video_description, + 'upload_date': video_date, + 'thumbnail': video_thumbnail, + '_embed_url': playerdata_url, + } + + def _screenwavemedia_get_info(self, url): + mobj = re.match(self._VALID_URL, url) + if not mobj: + raise ExtractorError('Can\'t extract embed url and video id') + video_id = mobj.group('video_id') + + playerdata = self._download_webpage(url, video_id, 'Downloading player webpage') + + vidtitle = self._search_regex( + r'\'vidtitle\'\s*:\s*"([^\']+)"', playerdata, 'vidtitle').replace('\\/', '/') + vidurl = self._search_regex( + r'\'vidurl\'\s*:\s*"([^\']+)"', playerdata, 'vidurl').replace('\\/', '/') + pageurl = self._search_regex( + r'\'pageurl\'\s*:\s*"([^\']+)"', playerdata, 'pageurl', fatal=False).replace('\\/', '/') + + videolist_url = None + + mobj = re.search(r"'videoserver'\s*:\s*'(?P<videoserver>[^']+)'", playerdata) + if mobj: + videoserver = mobj.group('videoserver') + mobj = re.search(r'\'vidid\'\s*:\s*"(?P<vidid>[^\']+)"', playerdata) + vidid = mobj.group('vidid') if mobj else video_id + videolist_url = 'http://%s/vod/smil:%s.smil/jwplayer.smil' % (videoserver, vidid) + else: + mobj = re.search(r"file\s*:\s*'(?P<smil>http.+?/jwplayer\.smil)'", playerdata) + if mobj: + videolist_url = mobj.group('smil') + + if videolist_url: + videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML') + formats = [] + baseurl = vidurl[:vidurl.rfind('/') + 1] + for video in videolist.findall('.//video'): + src = video.get('src') + if not src: + continue + file_ = src.partition(':')[-1] + width = int_or_none(video.get('width')) + height = int_or_none(video.get('height')) + bitrate = int_or_none(video.get('system-bitrate')) + format = { + 'url': baseurl + file_, + 'format_id': src.rpartition('.')[0].rpartition('_')[-1], + } + if width or height: + format.update({ + 'tbr': bitrate // 1000 if bitrate else None, + 'width': width, + 'height': height, + }) + else: + format.update({ + 'abr': bitrate // 1000 if bitrate else None, + 'vcodec': 'none', + }) + formats.append(format) + self._sort_formats(formats) + else: + formats = [{ + 'url': vidurl, + }] + + return { + 'id': video_id, + 'title': vidtitle, + 'formats': formats, + '_episode_page': pageurl, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + + swm_info = None + site_info = None + + if mobj.group('generic'): + swm_info = self._screenwavemedia_get_info(url) + url = swm_info['_episode_page'] + mobj = re.match(self._VALID_URL, url) + + if mobj: + if mobj.group('cinemassacre'): + site_info = self._cinemassacre_get_info(url) + + if not swm_info: + if site_info: + swm_info = self._screenwavemedia_get_info(site_info['_embed_url']) + + if not swm_info: + raise ExtractorError("Failed to extract metadata for this URL") + + if site_info: + swm_info.update(site_info) + + return swm_info -- cgit v1.2.3