from __future__ import unicode_literals import re from .common import InfoExtractor from ..utils import ( ExtractorError, ) class TeamcocoIE(InfoExtractor): _VALID_URL = r'http://teamcoco\.com/video/(?P[0-9]+)?/?(?P.*)' _TESTS = [ { 'url': 'http://teamcoco.com/video/80187/conan-becomes-a-mary-kay-beauty-consultant', 'file': '80187.mp4', 'md5': '3f7746aa0dc86de18df7539903d399ea', 'info_dict': { 'title': 'Conan Becomes A Mary Kay Beauty Consultant', 'description': 'Mary Kay is perhaps the most trusted name in female beauty, so of course Conan is a natural choice to sell their products.' } }, { 'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush', 'file': '19705.mp4', 'md5': 'cde9ba0fa3506f5f017ce11ead928f9a', 'info_dict': { "description": "Louis C.K. got starstruck by George W. Bush, so what? Part one.", "title": "Louis C.K. Interview Pt. 1 11/3/11" } } ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) if mobj is None: raise ExtractorError('Invalid URL: %s' % url) url_title = mobj.group('url_title') webpage = self._download_webpage(url, url_title) video_id = mobj.group("video_id") if video_id == '': video_id = self._html_search_regex( r'