# coding: utf-8 from __future__ import unicode_literals import re import json from .common import InfoExtractor from ..utils import ( ExtractorError, parse_iso8601, ) class EllenTVIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?(ellentv|ellentube)\.com/videos/(?P[a-z0-9_-]+)' _TESTS = [{ 'url': 'http://www.ellentv.com/videos/0-7jqrsr18/', 'md5': 'e4af06f3bf0d5f471921a18db5764642', 'info_dict': { 'id': '0-7jqrsr18', 'ext': 'mp4', 'title': 'What\'s Wrong with These Photos? A Whole Lot', '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', 'timestamp': 1419542075, 'upload_date': '20141225', } }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) timestamp = parse_iso8601(self._search_regex( r'