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

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5 from ..utils import (
   6     ExtractorError,
   7     unified_strdate,
   8 )
   9
  10 class NormalbootsIE(InfoExtractor):
  11     _VALID_URL = r'(?:http://)?(?:www\.)?normalboots\.com/video/(?P<videoid>[0-9a-z-]*)/?$'
  12     _TEST = {
  13         u'url': u'http://normalboots.com/video/home-alone-games-jontron/',
  14         u'file': u'home-alone-games-jontron.mp4',
  15         u'md5': u'8bf6de238915dd501105b44ef5f1e0f6',
  16         u'info_dict': {
  17             u'title': u'Home Alone Games - JonTron - NormalBoots',
  18             u'description': u'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 \u2018Tense Battle Theme\u2019:\xa0http://www.youtube.com/Kiamet/',
  19             u'uploader': u'JonTron',
  20             u'upload_date': u'20140125',
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         mobj = re.match(self._VALID_URL, url)
  26         if mobj is None:
  27             raise ExtractorError(u'Invalid URL: %s' % url)
  28         video_id = mobj.group('videoid')
  29
  30         info = {
  31             'id': video_id,
  32             'uploader': None,
  33             'upload_date': None,
  34         }
  35
  36         if url[:4] != 'http':
  37             url = 'http://' + url
  38
  39         webpage = self._download_webpage(url, video_id)
  40         video_title = self._og_search_title(webpage)
  41         video_description = self._og_search_description(webpage)
  42         video_thumbnail = self._og_search_thumbnail(webpage)
  43         video_uploader = self._html_search_regex(r'Posted\sby\s<a\shref="[A-Za-z0-9/]*">(?P<uploader>[A-Za-z]*)\s</a>',
  44             webpage, 'uploader')
  45         raw_upload_date = self._html_search_regex('<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>',
  46             webpage, 'date')
  47         video_upload_date = unified_strdate(raw_upload_date)
  48         video_upload_date = unified_strdate(raw_upload_date)
  49
  50         player_url = self._html_search_regex(r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"', webpage, 'url')
  51         player_page = self._download_webpage(player_url, video_id)
  52         video_url = u'http://player.screenwavemedia.com/' + self._html_search_regex(r"'file':\s'(?P<file>[0-9A-Za-z-_\.]+)'", player_page, 'file')
  53
  54         info['url'] = video_url
  55         info['title'] = video_title
  56         info['description'] = video_description
  57         info['thumbnail'] = video_thumbnail
  58         info['uploader'] = video_uploader
  59         info['upload_date'] = video_upload_date
  60
  61         return info