From 53bfd6b24c48ae052b73e9ab19a9c9906d57fa44 Mon Sep 17 00:00:00 2001 From: sahutd Date: Sun, 26 Jan 2014 14:05:34 +0530 Subject: [PATCH] Added support for Discovery Issue #2227 --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/discovery.py | 40 +++++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+) create mode 100644 youtube_dl/extractor/discovery.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 05c782d58..ba3d4ac0e 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -47,6 +47,7 @@ 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..14fca3cae --- /dev/null +++ b/youtube_dl/extractor/discovery.py @@ -0,0 +1,40 @@ +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': 'mission-impossible-outtakes.mp4', + 'md5': 'e12614f9ee303a6ccef415cb0793eba2', + 'info_dict': { + 'title': 'MythBusters: Mission Impossible Outtakes' + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + title = self._search_regex( + r'(?<=\"name\": ")(?P.*?)(?=\"\,)', webpage, r'Filename') + duration = int(self._search_regex( + r'(?<=\"duration\"\: )(?P<duration>.*?)(?=,)', webpage, r'Duration')) + formats_raw = self._search_regex( + r'(?<=\"mp4\":)(.*?)(}])', webpage, r'formats') + '}]' + formats_json = json.loads(formats_raw) + formats = [] + for f in formats_json: + formats.append( + {'url': f['src'], r'ext': r'mp4', 'tbr': int(f['bitrate'][:-1])}) + + return { + 'id': video_id, + 'duration': duration, + 'title': title, + 'formats': formats + }