Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-22 16:44:32 +01:00
Code Issues Releases Wiki Activity

[Morningstar] Modernize

Browse Source
This commit is contained in:
Déstin Reed 2016-09-29 15:17:48 +02:00
parent 8f0cf20ab9
commit 2c30087e73
1 changed files with 12 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
youtube_dl/extractor/morningstar.py
View File

@ -1,9 +1,11 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
ExtractorError,
get_element_by_id,
)
class MorningstarIE(InfoExtractor): class MorningstarIE(InfoExtractor):
@ -16,32 +18,30 @@ class MorningstarIE(InfoExtractor):
'id': '615869', 'id': '615869',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Get Ahead of the Curve on 2013 Taxes', '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.", 'description': 'md5:0f71dedfd54bb3dca09e6474e2b624f7',
'thumbnail': r're:^https?://.*m(?:orning)?star\.com/.+thumb\.jpg$' 'thumbnail': r're:^https?://.*m(?:orning)?star\.com/.+thumb\.jpg$'
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
r'<h1 id="titleLink">(.*?)</h1>', webpage, 'title') title = get_element_by_id('titleLink', webpage)
if not title:
raise ExtractorError('Unable to extract title for %s.' % video_id)
video_url = self._html_search_regex( video_url = self._html_search_regex(
r'<input type="hidden" id="hidVideoUrl" value="([^"]+)"', r'<input type="hidden" id="hidVideoUrl" value="([^"]+)"',
webpage, 'video URL') webpage, 'video URL')
thumbnail = self._html_search_regex( thumbnail = self._html_search_regex(
r'<input type="hidden" id="hidSnapshot" value="([^"]+)"', r'<input type="hidden" id="hidSnapshot" value="([^"]+)"',
webpage, 'thumbnail', fatal=False) webpage, 'thumbnail', fatal=False)
description = self._html_search_regex(
r'<div id="mstarDeck".*?>(.*?)</div>',
webpage, 'description', fatal=False)
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'url': video_url, 'url': video_url,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'description': description, 'description': get_element_by_id('mstarDeck', webpage),
} }