youtube_dl/extractor/normalboots.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8 from ..utils import (
   9     unified_strdate,
  10 )
  11
  12
  13 class NormalbootsIE(InfoExtractor):
  14     _VALID_URL = r'http://(?:www\.)?normalboots\.com/video/(?P<videoid>[0-9a-z-]*)/?$'
  15     _TEST = {
  16         'url': 'http://normalboots.com/video/home-alone-games-jontron/',
  17         'md5': '8bf6de238915dd501105b44ef5f1e0f6',
  18         'info_dict': {
  19             'id': 'home-alone-games-jontron',
  20             'ext': 'mp4',
  21             'title': 'Home Alone Games - JonTron - NormalBoots',
  22             '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/',
  23             'uploader': 'JonTron',
  24             'upload_date': '20140125',
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id = mobj.group('videoid')
  31
  32         webpage = self._download_webpage(url, video_id)
  33         video_uploader = self._html_search_regex(r'Posted\sby\s<a\shref="[A-Za-z0-9/]*">(?P<uploader>[A-Za-z]*)\s</a>',
  34             webpage, 'uploader')
  35         raw_upload_date = self._html_search_regex('<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>',
  36             webpage, 'date')
  37         video_upload_date = unified_strdate(raw_upload_date)
  38
  39         player_url = self._html_search_regex(r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"', webpage, 'url')
  40         player_page = self._download_webpage(player_url, video_id)
  41         video_url = self._html_search_regex(r"file:\s'(?P<file>[^']+\.mp4)'", player_page, 'file')
  42
  43         return {
  44             'id': video_id,
  45             'url': video_url,
  46             'title': self._og_search_title(webpage),
  47             'description': self._og_search_description(webpage),
  48             'thumbnail': self._og_search_thumbnail(webpage),
  49             'uploader': video_uploader,
  50             'upload_date': video_upload_date,
  51         }