from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( int_or_none, unified_strdate, ) class ExpoTVIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?expotv\.com/videos/[^?#]*/(?P[0-9]+)($|[?#])' _TEST = { 'url': 'http://www.expotv.com/videos/reviews/3/40/NYX-Butter-lipstick/667916', 'md5': 'fe1d728c3a813ff78f595bc8b7a707a8', 'info_dict': { 'id': '667916', 'ext': 'mp4', 'title': 'NYX Butter Lipstick Little Susie', 'description': 'Goes on like butter, but looks better!', 'thumbnail': r're:^https?://.*\.jpg$', 'uploader': 'Stephanie S.', 'upload_date': '20150520', 'view_count': int, } } def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) player_key = self._search_regex( r'Plays: ([0-9]+)', webpage, 'view counts')) uploader = self._search_regex( r'
\s*([^Reviewed on ([0-9/.]+)', webpage, 'upload date', fatal=False), day_first=False) return { 'id': video_id, 'formats': formats, 'title': title, 'description': description, 'view_count': view_count, 'thumbnail': thumbnail, 'uploader': uploader, 'upload_date': upload_date, }