X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fellentv.py;h=fc92ff8253734f151fa973ea4979adbe5c6063bf;hb=ecd1936695e73ba850d0618828b4a40d7d16c091;hp=097317842cc63fa4645976197d3c9a9392761d10;hpb=6e46c3f1fddc954596d429d15d7c035d12a625a9;p=youtube-dl diff --git a/youtube_dl/extractor/ellentv.py b/youtube_dl/extractor/ellentv.py index 097317842..fc92ff825 100644 --- a/youtube_dl/extractor/ellentv.py +++ b/youtube_dl/extractor/ellentv.py @@ -1,7 +1,6 @@ # coding: utf-8 from __future__ import unicode_literals -import re import json from .common import InfoExtractor @@ -12,7 +11,7 @@ from ..utils import ( class EllenTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(ellentv|ellentube)\.com/videos/(?P[a-z0-9_-]+)' + _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P[a-z0-9_-]+)' _TESTS = [{ 'url': 'http://www.ellentv.com/videos/0-7jqrsr18/', 'md5': 'e4af06f3bf0d5f471921a18db5764642', @@ -20,38 +19,41 @@ class EllenTVIE(InfoExtractor): 'id': '0-7jqrsr18', 'ext': 'mp4', 'title': 'What\'s Wrong with These Photos? A Whole Lot', + 'description': 'md5:35f152dc66b587cf13e6d2cf4fa467f6', 'timestamp': 1406876400, 'upload_date': '20140801', } - }, - { + }, { 'url': 'http://ellentube.com/videos/0-dvzmabd5/', 'md5': '98238118eaa2bbdf6ad7f708e3e4f4eb', 'info_dict': { 'id': '0-dvzmabd5', 'ext': 'mp4', 'title': '1 year old twin sister makes her brother laugh', + 'description': '1 year old twin sister makes her brother laugh', 'timestamp': 1419542075, 'upload_date': '20141225', } }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + video_url = self._html_search_meta('VideoURL', webpage, 'url') + title = self._og_search_title(webpage, default=None) or self._search_regex( + r'pageName\s*=\s*"([^"]+)"', webpage, 'title') + description = self._html_search_meta( + 'description', webpage, 'description') or self._og_search_description(webpage) timestamp = parse_iso8601(self._search_regex( r'