X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fscreenwavemedia.py;h=d1ab66b3216d5153a5480769fb0723919f3fdb37;hb=d97f5cd795b0bd8b6bd636b899bdbc8b10d5907b;hp=b515b11b45855fb5148b19a6ee5346e7f3b069a5;hpb=0954cd8aa4421b1844a30e99702c364f1fffc15f;p=youtube-dl diff --git a/youtube_dl/extractor/screenwavemedia.py b/youtube_dl/extractor/screenwavemedia.py index b515b11b4..d1ab66b32 100644 --- a/youtube_dl/extractor/screenwavemedia.py +++ b/youtube_dl/extractor/screenwavemedia.py @@ -7,13 +7,11 @@ from .common import InfoExtractor from ..utils import ( int_or_none, unified_strdate, - ExtractorError ) -from .bliptv import BlipTVIE class ScreenwaveMediaIE(InfoExtractor): - _VALID_URL = r'http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P.+)' + _VALID_URL = r'http://player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?[^"]*\bid=(?P.+)' _TESTS = [{ 'url': 'http://player.screenwavemedia.com/play/play.php?playerdiv=videoarea&companiondiv=squareAd&id=Cinemassacre-19911', @@ -22,7 +20,10 @@ class ScreenwaveMediaIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - playerdata = self._download_webpage(url, video_id, 'Downloading player webpage') + + playerdata = self._download_webpage( + 'http://player.screenwavemedia.com/play/player.php?id=%s' % video_id, + video_id, 'Downloading player webpage') vidtitle = self._search_regex( r'\'vidtitle\'\s*:\s*"([^"]+)"', playerdata, 'vidtitle').replace('\\/', '/') @@ -83,79 +84,6 @@ class ScreenwaveMediaIE(InfoExtractor): } -class CinemassacreIE(InfoExtractor): - _VALID_URL = 'https?://(?:www\.)?cinemassacre\.com/(?P[0-9]{4})/(?P[0-9]{2})/(?P[0-9]{2})/(?P[^?#/]+)' - _TESTS = [ - { - 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', - 'md5': 'fde81fbafaee331785f58cd6c0d46190', - 'info_dict': { - 'id': 'Cinemassacre-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': 'Cinemassacre-521be8ef82b16', - 'ext': 'mp4', - 'upload_date': '20131002', - 'title': 'The Mummy’s Hand (1940)', - }, - }, - { - 'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/', - 'md5': 'ca9b3c8dd5a66f9375daeb5135f5a3de', - 'info_dict': { - 'id': '4065369', - 'ext': 'flv', - 'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles', - 'upload_date': '20061207', - 'uploader': 'cinemassacre', - 'uploader_id': '250778', - 'timestamp': 1283233867, - 'description': 'md5:0a108c78d130676b207d0f6d029ecffd', - } - } - ] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('display_id') - video_date = mobj.group('date_y') + mobj.group('date_m') + mobj.group('date_d') - - webpage = self._download_webpage(url, display_id) - - playerdata_url = self._search_regex( - r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"', - webpage, 'player data URL', default=None) - if not playerdata_url: - playerdata_url = BlipTVIE._extract_url(webpage) - if not playerdata_url: - raise ExtractorError('Unable to find player data') - - 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 { - '_type': 'url_transparent', - 'display_id': display_id, - 'title': video_title, - 'description': video_description, - 'upload_date': video_date, - 'thumbnail': video_thumbnail, - 'url': playerdata_url, - } - - class TeamFourIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/video/(?P<id>[a-z0-9\-]+)/?' _TEST = { @@ -174,7 +102,7 @@ class TeamFourIE(InfoExtractor): webpage = self._download_webpage(url, display_id) playerdata_url = self._search_regex( - r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"', + r'src="(http://player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?[^"]*\bid=.+?)"', webpage, 'player data URL') video_title = self._html_search_regex(