# encoding: utf-8 from __future__ import unicode_literals import re from .common import InfoExtractor from ..utils import ( unified_strdate, ) class NormalbootsIE(InfoExtractor): _VALID_URL = r'http://(?:www\.)?normalboots\.com/video/(?P[0-9a-z-]*)/?$' _TEST = { 'url': 'http://normalboots.com/video/home-alone-games-jontron/', 'md5': '8bf6de238915dd501105b44ef5f1e0f6', 'info_dict': { 'id': 'home-alone-games-jontron', 'ext': 'mp4', 'title': 'Home Alone Games - JonTron - NormalBoots', 'description': 'Jon is late for Christmas. Typical. Thanks to: Paul Ritchey for Co-Writing/Filming: http://www.youtube.com/user/ContinueShow Michael Azzi for Christmas Intro Animation: http://michafrar.tumblr.com/ Jerrod Waters for Christmas Intro Music: http://www.youtube.com/user/xXJerryTerryXx Casey Ormond for ‘Tense Battle Theme’:\xa0http://www.youtube.com/Kiamet/', 'uploader': 'JonTron', 'upload_date': '20140125', }, 'params': { # rtmp download 'skip_download': True, }, } def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) video_uploader = self._html_search_regex( r'Posted\sby\s(?P[A-Za-z]*)\s', webpage, 'uploader', fatal=False) video_upload_date = unified_strdate(self._html_search_regex( r'[A-Za-z]+, (?P.*)', webpage, 'date', fatal=False)) player_url = self._html_search_regex( r'[\S]+)"', webpage, 'player url') player_page = self._download_webpage(player_url, video_id) video_url = self._html_search_regex( r"file:\s'(?P[^']+\.mp4)'", player_page, 'file') return { 'id': video_id, 'url': video_url, 'title': self._og_search_title(webpage), 'description': self._og_search_description(webpage), 'thumbnail': self._og_search_thumbnail(webpage), 'uploader': video_uploader, 'upload_date': video_upload_date, }