from __future__ import unicode_literals import datetime import re from .common import InfoExtractor from ..utils import ( int_or_none, unified_strdate, ) class MotherlessIE(InfoExtractor): _VALID_URL = r'http://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/)?(?P[A-Z0-9]+)' _TESTS = [ { 'url': 'http://motherless.com/AC3FFE1', 'md5': '310f62e325a9fafe64f68c0bccb6e75f', 'info_dict': { 'id': 'AC3FFE1', 'ext': 'mp4', 'title': 'Fucked in the ass while playing PS3', 'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'], 'upload_date': '20100913', 'uploader_id': 'famouslyfuckedup', 'thumbnail': 're:http://.*\.jpg', 'age_limit': 18, } }, { 'url': 'http://motherless.com/532291B', 'md5': 'bc59a6b47d1f958e61fbd38a4d31b131', 'info_dict': { 'id': '532291B', 'ext': 'mp4', 'title': 'Amazing girl playing the omegle game, PERFECT!', 'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen', 'game', 'hairy'], 'upload_date': '20140622', 'uploader_id': 'Sulivana7x', 'thumbnail': 're:http://.*\.jpg', 'age_limit': 18, } }, { 'url': 'http://motherless.com/g/cosplay/633979F', 'md5': '0b2a43f447a49c3e649c93ad1fafa4a0', 'info_dict': { 'id': '633979F', 'ext': 'mp4', 'title': 'Turtlette', 'categories': ['superheroine heroine superher'], 'upload_date': '20140827', 'uploader_id': 'shade0230', 'thumbnail': 're:http://.*\.jpg', 'age_limit': 18, } } ] def _real_extract(self,url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) title = self._html_search_regex(r'id="view-upload-title">\s+([^<]+)<', webpage, 'title') video_url = self._html_search_regex(r'setup\(\{\s+"file".+: "([^"]+)",', webpage, 'video_url') age_limit = self._rta_search(webpage) view_count = self._html_search_regex(r'Views\s+([^<]+)<', webpage, 'view_count') upload_date = self._html_search_regex(r'Uploaded\s+([^<]+)<', webpage, 'upload_date') if 'Ago' in upload_date: days = int(re.search(r'([0-9]+)', upload_date).group(1)) upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d') else: upload_date = unified_strdate(upload_date) like_count = self._html_search_regex(r'Favorited\s+([^<]+)<', webpage, 'like_count') comment_count = webpage.count('class="media-comment-contents"') uploader_id = self._html_search_regex(r'"thumb-member-username">\s+