from __future__ import unicode_literals import re from .common import InfoExtractor from ..utils import ( parse_duration, ) class NuvidIE(InfoExtractor): _VALID_URL = r'https?://(?:www|m)\.nuvid\.com/video/(?P[0-9]+)' _TEST = { 'url': 'http://m.nuvid.com/video/1310741/', 'md5': 'eab207b7ac4fccfb4e23c86201f11277', 'info_dict': { 'id': '1310741', 'ext': 'mp4', 'title': 'Horny babes show their awesome bodeis and', 'duration': 129, 'age_limit': 18, } } def _real_extract(self, url): video_id = self._match_id(url) page_url = 'https://m.nuvid.com/video/%s' % video_id webpage = self._download_webpage( page_url, video_id, 'Downloading video page') video_hash_re = r'(?s)<(?:video|audio).+data-video_hash="(?P[^"]+)[^>]*(?:>)', hash_time_re = r'(?s)<(?:video|audio).+data-hash_time="(?P[^"]+)[^>]*(?:>)', video_hash = self._html_search_regex(video_hash_re, webpage, 'video_hash') hash_time = self._html_search_regex(hash_time_re, webpage, 'hash_time') query = {'video_hash': video_hash, 'hash_time': hash_time, 'video_id': video_id} player_source = self._download_json('https://m.nuvid.com/player_config', video_id, query=query) mp4_video_url = player_source['source'] formats = [{ 'url': mp4_video_url }] title = self._html_search_regex( [r'
', r'
\s*]*>([^<]+)', r']+class="title_thumb">([^<]+)'], webpage, 'title').strip() thumbnails = [ { 'url': thumb_url, } for thumb_url in re.findall(r'', webpage) ] thumbnail = thumbnails[0]['url'] if thumbnails else None duration = parse_duration(self._html_search_regex( [r'\s*(\d{2}:\d{2})', r']+class="view_time">([^<]+)'], webpage, 'duration', fatal=False)) return { 'id': video_id, 'title': title, 'thumbnails': thumbnails, 'thumbnail': thumbnail, 'duration': duration, 'age_limit': 18, 'formats': formats, }