import re import json from .common import InfoExtractor from ..utils import ( ExtractorError, ) class VevoIE(InfoExtractor): """ Accepts urls from vevo.com or in the format 'vevo:{id}' (currently used by MTVIE) """ _VALID_URL = r'((http://www.vevo.com/watch/.*?/.*?/)|(vevo:))(?P.*)$' _TEST = { u'url': u'http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280', u'file': u'GB1101300280.mp4', u'md5': u'06bea460acb744eab74a9d7dcb4bfd61', u'info_dict': { u"upload_date": u"20130624", u"uploader": u"Hurts", u"title": u"Somebody to Die For" } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') json_url = 'http://www.vevo.com/data/video/%s' % video_id base_url = 'http://smil.lvl3.vevo.com' videos_url = '%s/Video/V2/VFILE/%s/%sr.smil' % (base_url, video_id, video_id.lower()) info_json = self._download_webpage(json_url, video_id, u'Downloading json info') links_webpage = self._download_webpage(videos_url, video_id, u'Downloading videos urls') self.report_extraction(video_id) video_info = json.loads(info_json) m_urls = list(re.finditer(r'