from __future__ import unicode_literals import re from .common import InfoExtractor from ..utils import ( ExtractorError, RegexNotFoundError, unescapeHTML, ) class JukeboxIE(InfoExtractor): _VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P[a-z0-9\-]+)\.html' _TEST = { 'url': 'http://www.jukebox.es/kosheen/videoclip,pride,r303r.html', 'info_dict': { 'id': 'r303r', 'ext': 'flv', 'title': 'Kosheen-En Vivo Pride', 'uploader': 'Kosheen', }, } def _real_extract(self, url): video_id = self._match_id(url) html = self._download_webpage(url, video_id) iframe_url = unescapeHTML(self._search_regex(r'