Raphaël G. Git Repositories - youtubedl/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 from ..utils import (
   8     qualities,
   9     determine_ext,
  10 )
  11
  12
  13 class TeacherTubeIE(InfoExtractor):
  14     IE_NAME = 'teachertube'
  15     IE_DESC = 'teachertube.com videos'
  16
  17     _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(viewVideo\.php\?video_id=|music\.php\?music_id=)(?P<id>\d+)'
  18
  19     _TESTS = [{
  20         'url': 'http://www.teachertube.com/viewVideo.php?video_id=339997',
  21         'md5': 'f9434ef992fd65936d72999951ee254c',
  22         'info_dict': {
  23             'id': '339997',
  24             'ext': 'mp4',
  25             'title': 'Measures of dispersion from a frequency table_x264',
  26             'description': 'md5:a3e9853487185e9fcd7181a07164650b',
  27             'thumbnail': 're:http://.*\.jpg',
  28         },
  29     }, {
  30         'url': 'http://www.teachertube.com/viewVideo.php?video_id=340064',
  31         'md5': '0d625ec6bc9bf50f70170942ad580676',
  32         'info_dict': {
  33             'id': '340064',
  34             'ext': 'mp4',
  35             'title': 'How to Make Paper Dolls _ Paper Art Projects',
  36             'description': 'md5:2ca52b20cd727773d1dc418b3d6bd07b',
  37             'thumbnail': 're:http://.*\.jpg',
  38         },
  39     }, {
  40         'url': 'http://www.teachertube.com/music.php?music_id=8805',
  41         'md5': '01e8352006c65757caf7b961f6050e21',
  42         'info_dict': {
  43             'id': '8805',
  44             'ext': 'mp3',
  45             'title': 'PER ASPERA AD ASTRA',
  46             'description': 'RADIJSKA EMISIJA ZRAKOPLOVNE TEHNIČKE ŠKOLE PER ASPERA AD ASTRA',
  47         },
  48     }]
  49
  50     def _real_extract(self, url):
  51         mobj = re.match(self._VALID_URL, url)
  52         video_id = mobj.group('id')
  53
  54         webpage = self._download_webpage(url, video_id)
  55
  56         quality = qualities(['mp3', 'flv', 'mp4'])
  57
  58         formats = [
  59             {
  60                 'url': media_url,
  61                 'quality': quality(determine_ext(media_url))
  62             } for media_url in set(zip(*re.findall(r'([\'"])file\1\s*:\s*"([^"]+)"', webpage))[1])
  63         ]
  64
  65         self._sort_formats(formats)
  66
  67         return {
  68             'id': video_id,
  69             'title': self._og_search_title(webpage),
  70             'thumbnail': self._og_search_thumbnail(webpage),
  71             'formats': formats,
  72             'description': self._og_search_description(webpage),
  73         }
  74
  75
  76 class TeacherTubeClassroomIE(InfoExtractor):
  77     IE_NAME = 'teachertube:classroom'
  78     IE_DESC = 'teachertube.com online classrooms'
  79
  80     _VALID_URL = r'https?://(?:www\.)?teachertube\.com/view_classroom\.php\?user=(?P<user>[0-9a-zA-Z]+)'
  81
  82     def _real_extract(self, url):
  83         mobj = re.match(self._VALID_URL, url)
  84         user_id = mobj.group('user')
  85
  86         rss = self._download_xml('http://www.teachertube.com/rssclassroom.php?mode=user&username=%s' % user_id,
  87                                       user_id, 'Downloading classroom RSS')
  88
  89         entries = []
  90         for url in rss.findall('.//{http://search.yahoo.com/mrss/}player'):
  91             entries.append(self.url_result(url.attrib['url'], 'TeacherTube'))
  92
  93         return self.playlist_result(entries, user_id)