From c460bdd56b0420bb5175344c0f6523675fdae415 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Thu, 19 Feb 2015 00:31:01 +0100 Subject: [PATCH] [sandia] Add new extractor (#4974) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/sandia.py | 117 +++++++++++++++++++++++++++++++ youtube_dl/utils.py | 11 ++- 3 files changed, 128 insertions(+), 1 deletion(-) create mode 100644 youtube_dl/extractor/sandia.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 7d0909b5d..c712b907f 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -386,6 +386,7 @@ from .rutube import ( RutubePersonIE, ) from .rutv import RUTVIE +from .sandia import SandiaIE from .sapo import SapoIE from .savefrom import SaveFromIE from .sbs import SBSIE diff --git a/youtube_dl/extractor/sandia.py b/youtube_dl/extractor/sandia.py new file mode 100644 index 000000000..9c88167f0 --- /dev/null +++ b/youtube_dl/extractor/sandia.py @@ -0,0 +1,117 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import itertools +import json +import re + +from .common import InfoExtractor +from ..compat import ( + compat_urllib_request, + compat_urlparse, +) +from ..utils import ( + int_or_none, + js_to_json, + mimetype2ext, + unified_strdate, +) + + +class SandiaIE(InfoExtractor): + IE_DESC = 'Sandia National Laboratories' + _VALID_URL = r'https?://digitalops\.sandia\.gov/Mediasite/Play/(?P[0-9a-f]+)' + _TEST = { + 'url': 'http://digitalops.sandia.gov/Mediasite/Play/24aace4429fc450fb5b38cdbf424a66e1d', + 'md5': '9422edc9b9a60151727e4b6d8bef393d', + 'info_dict': { + 'id': '24aace4429fc450fb5b38cdbf424a66e1d', + 'ext': 'mp4', + 'title': 'Xyce Software Training - Section 1', + 'description': 're:(?s)SAND Number: SAND 2013-7800.{200,}', + 'upload_date': '20120904', + 'duration': 7794, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + req = compat_urllib_request.Request(url) + req.add_header('Cookie', 'MediasitePlayerCaps=ClientPlugins=4') + webpage = self._download_webpage(req, video_id) + + js_path = self._search_regex( + r'