From: Jaime Marquínez Ferrándiz Date: Mon, 27 Jan 2014 11:45:59 +0000 (+0100) Subject: Merge remote-tracking branch 'origin/master' X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=commitdiff_plain;h=e2ba07024f36b683d186a46d6c9542edb4e748b1;hp=b6d3a99678052bb85a187268dbd50e35fbde109c;p=youtube-dl Merge remote-tracking branch 'origin/master' --- diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index b8d635c30..1e8556124 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -48,6 +48,7 @@ from .depositfiles import DepositFilesIE from .dotsub import DotsubIE from .dreisat import DreiSatIE from .defense import DefenseGouvFrIE +from .discovery import DiscoveryIE from .dropbox import DropboxIE from .ebaumsworld import EbaumsWorldIE from .ehow import EHowIE diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py new file mode 100644 index 000000000..885944c5e --- /dev/null +++ b/youtube_dl/extractor/discovery.py @@ -0,0 +1,46 @@ +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor + + +class DiscoveryIE(InfoExtractor): + _VALID_URL = r'http://dsc\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P[a-zA-Z0-9\-]*)(.htm)?' + _TEST = { + 'url': 'http://dsc.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm', + 'file': '614784.mp4', + 'md5': 'e12614f9ee303a6ccef415cb0793eba2', + 'info_dict': { + 'title': 'MythBusters: Mission Impossible Outtakes', + 'description': ('Watch Jamie Hyneman and Adam Savage practice being' + ' each other -- to the point of confusing Jamie\'s dog -- and ' + 'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s' + ' back.'), + 'duration': 156, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + + video_list_json = self._search_regex(r'var videoListJSON = ({.*?});', + webpage, 'video list', flags=re.DOTALL) + video_list = json.loads(video_list_json) + info = video_list['clips'][0] + formats = [] + for f in info['mp4']: + formats.append( + {'url': f['src'], r'ext': r'mp4', 'tbr': int(f['bitrate'][:-1])}) + + return { + 'id': info['contentId'], + 'title': video_list['name'], + 'formats': formats, + 'description': info['videoCaption'], + 'thumbnail': info.get('videoStillURL') or info.get('thumbnailURL'), + 'duration': info['duration'], + }