Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/normalboots.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6 from ..utils import (
   7     unified_strdate,
   8 )
   9
  10
  11 class NormalbootsIE(InfoExtractor):
  12     _VALID_URL = r'http://(?:www\.)?normalboots\.com/video/(?P<id>[0-9a-z-]*)/?$'
  13     _TEST = {
  14         'url': 'http://normalboots.com/video/home-alone-games-jontron/',
  15         'md5': '8bf6de238915dd501105b44ef5f1e0f6',
  16         'info_dict': {
  17             'id': 'home-alone-games-jontron',
  18             'ext': 'mp4',
  19             'title': 'Home Alone Games - JonTron - NormalBoots',
  20             '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/',
  21             'uploader': 'JonTron',
  22             'upload_date': '20140125',
  23         },
  24         'params': {
  25             # rtmp download
  26             'skip_download': True,
  27         },
  28     }
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32         webpage = self._download_webpage(url, video_id)
  33
  34         video_uploader = self._html_search_regex(
  35             r'Posted\sby\s<a\shref="[A-Za-z0-9/]*">(?P<uploader>[A-Za-z]*)\s</a>',
  36             webpage, 'uploader', fatal=False)
  37         video_upload_date = unified_strdate(self._html_search_regex(
  38             r'<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>',
  39             webpage, 'date', fatal=False))
  40
  41         player_url = self._html_search_regex(
  42             r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"',
  43             webpage, 'player url')
  44         player_page = self._download_webpage(player_url, video_id)
  45         video_url = self._html_search_regex(
  46             r"file:\s'(?P<file>[^']+\.mp4)'", player_page, 'file')
  47
  48         return {
  49             'id': video_id,
  50             'url': video_url,
  51             'title': self._og_search_title(webpage),
  52             'description': self._og_search_description(webpage),
  53             'thumbnail': self._og_search_thumbnail(webpage),
  54             'uploader': video_uploader,
  55             'upload_date': video_upload_date,
  56         }