_ Git - youtube-dl/blob - youtube_dl/extractor/teachertube.py

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class TeacherTubeIE(InfoExtractor):
  10     IE_NAME = 'teachertube'
  11     IE_DESC = 'teachertube.com videos'
  12
  13     _VALID_URL = r'https?://(?:www\.)?teachertube\.com/viewVideo\.php\?video_id=(?P<id>\d+)'
  14
  15     _TESTS = [{
  16         'url': 'http://www.teachertube.com/viewVideo.php?video_id=339997',
  17         'md5': 'f9434ef992fd65936d72999951ee254c',
  18         'info_dict': {
  19             'id': '339997',
  20             'ext': 'mp4',
  21             'title': 'Measures of dispersion from a frequency table_x264',
  22             'description': 'md5:a3e9853487185e9fcd7181a07164650b',
  23             'thumbnail': 're:http://.*\.jpg',
  24         },
  25     }, {
  26         'url': 'http://www.teachertube.com/viewVideo.php?video_id=340064',
  27         'md5': '0d625ec6bc9bf50f70170942ad580676',
  28         'info_dict': {
  29             'id': '340064',
  30             'ext': 'mp4',
  31             'title': 'How to Make Paper Dolls _ Paper Art Projects',
  32             'description': 'md5:2ca52b20cd727773d1dc418b3d6bd07b',
  33             'thumbnail': 're:http://.*\.jpg',
  34         },
  35     }]
  36
  37     def _real_extract(self, url):
  38         mobj = re.match(self._VALID_URL, url)
  39         video_id = mobj.group('id')
  40
  41         webpage = self._download_webpage(url, video_id)
  42
  43         url = self._html_search_meta('twitter:player:stream', webpage, 'twitter player')
  44
  45         formats = [{
  46             'format_id': 'flv',
  47             'url': url.replace('mp4v', 'flv').replace('.mp4', '.flv'),
  48             'quality': 0,
  49             'ext': 'flv',
  50         }, {
  51             'format_id': 'mp4',
  52             'url': url,
  53             'quality': 1,
  54             'ext': 'mp4',
  55         }]
  56
  57         self._sort_formats(formats)
  58
  59         return {
  60             'id': video_id,
  61             'title': self._og_search_title(webpage),
  62             'thumbnail': self._og_search_thumbnail(webpage),
  63             'formats': formats,
  64             'description': self._og_search_description(webpage),
  65         }
  66
  67
  68 class TeacherTubeClassroomIE(InfoExtractor):
  69     IE_NAME = 'teachertube:classroom'
  70     IE_DESC = 'teachertube.com online classrooms'
  71
  72     _VALID_URL = r'https?://(?:www\.)?teachertube\.com/view_classroom\.php\?user=(?P<user>[0-9a-zA-Z]+)'
  73
  74     def _real_extract(self, url):
  75         mobj = re.match(self._VALID_URL, url)
  76         user_id = mobj.group('user')
  77
  78         rss = self._download_xml('http://www.teachertube.com/rssclassroom.php?mode=user&username=%s' % user_id,
  79                                       user_id, 'Downloading classroom RSS')
  80
  81         entries = []
  82         for url in rss.findall('.//{http://search.yahoo.com/mrss/}player'):
  83             entries.append(self.url_result(url.attrib['url'], 'TeacherTube'))
  84
  85         return self.playlist_result(entries, user_id)