From 2ad4d1ba077893e4020532f748547296801704e3 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Fri, 4 Apr 2014 00:25:35 +0200 Subject: [PATCH] [morningstar] Add new extractor (Fixes #2687) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/morningstar.py | 55 +++++++++++++++++++++++++++++ 2 files changed, 56 insertions(+) create mode 100644 youtube_dl/extractor/morningstar.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 12c10d962..66f71edf6 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -154,6 +154,7 @@ from .mixcloud import MixcloudIE from .mpora import MporaIE from .mofosex import MofosexIE from .mooshare import MooshareIE +from .morningstar import MorningstarIE from .motorsport import MotorsportIE from .mtv import ( MTVIE, diff --git a/youtube_dl/extractor/morningstar.py b/youtube_dl/extractor/morningstar.py new file mode 100644 index 000000000..3d3225699 --- /dev/null +++ b/youtube_dl/extractor/morningstar.py @@ -0,0 +1,55 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import hashlib +import json +import re +import time + +from .common import InfoExtractor +from ..utils import ( + compat_parse_qs, + compat_str, + int_or_none, +) + + +class MorningstarIE(InfoExtractor): + IE_DESC = 'morningstar.com' + _VALID_URL = r'https?://(?:www\.)?morningstar\.com/cover/videocenter\.aspx\?id=(?P[0-9]+)' + _TEST = { + 'url': 'http://www.morningstar.com/cover/videocenter.aspx?id=615869', + 'md5': '6c0acface7a787aadc8391e4bbf7b0f5', + 'info_dict': { + 'id': '615869', + 'ext': 'mp4', + 'title': 'Get Ahead of the Curve on 2013 Taxes', + 'description': "Vanguard's Joel Dickson on managing higher tax rates for high-income earners and fund capital-gain distributions in 2013.", + 'thumbnail': r're:^https?://.*m(?:orning)?star\.com/.+thumb\.jpg$' + } + } + + 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._html_search_regex( + r'

(.*?)

', webpage, 'title') + video_url = self._html_search_regex( + r'(.*?)', + webpage, 'description', fatal=False) + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'thumbnail': thumbnail, + 'description': description, + }