diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 9aaa7ca9bd..934419c434 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -1,4 +1,3 @@ - from .archiveorg import ArchiveOrgIE from .ard import ARDIE from .arte import ArteTvIE @@ -12,6 +11,7 @@ from .cspan import CSpanIE from .dailymotion import DailymotionIE from .depositfiles import DepositFilesIE +from .dotsub import DotsubIE from .dreisat import DreiSatIE from .eighttracks import EightTracksIE from .escapist import EscapistIE diff --git a/youtube_dl/extractor/dotsub.py b/youtube_dl/extractor/dotsub.py new file mode 100644 index 0000000000..2afeaba072 --- /dev/null +++ b/youtube_dl/extractor/dotsub.py @@ -0,0 +1,42 @@ +import re +import json +from .common import InfoExtractor + + +class DotsubIE(InfoExtractor): + _VALID_URL = r'(?:http://)?(?:www\.)?dotsub\.com/view/([^/]+)' + _TEST = { + u'url': u'http://dotsub.com/view/aed3b8b2-1889-4df5-ae63-ad85f5572f27', + u'file': u'aed3b8b2-1889-4df5-ae63-ad85f5572f27.flv', + u'md5': u'0914d4d69605090f623b7ac329fea66e', + u'info_dict': { + u"title": u"Pyramids of Waste (2010), AKA The Lightbulb Conspiracy - Planned obsolescence documentary", + u"uploader": u"4v4l0n42", + u'description': u'Pyramids of Waste (2010) also known as "The lightbulb conspiracy" is a documentary about how our economic system based on consumerism and planned obsolescence is breaking our planet down.\r\n\r\nSolutions to this can be found at:\r\nhttp://robotswillstealyourjob.com\r\nhttp://www.federicopistono.org\r\n\r\nhttp://opensourceecology.org\r\nhttp://thezeitgeistmovement.com', + u'thumbnail': u'http://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p' + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group(1) + info_url = "https://dotsub.com/api/media/%s/metadata" %(video_id) + webpage = self._download_webpage(info_url, video_id) + info = json.loads(webpage) + video_url = info['mediaURI'] + uploader = info['user'] + description = info['description'] + view_count = info['numberOfViews'] + title = info['title'] + thumbnail_url = info['screenshotURI'] + ext = 'flv' + return [{ + 'id': video_id, + 'url': video_url, + 'ext': ext, + 'title': title, + 'thumbnail': thumbnail_url, + 'description': description, + 'uploader': uploader, + 'view_count': view_count, + }]