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=|video/(?:[\da-z-]+-)?|audio/)(?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',
  26             'description': 'Measures of dispersion from a frequency table',
  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': 'Learn how to make paper dolls in this simple',
  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 TEHNI?KE ?KOLE P',
  47         },
  48     }, {
  49         'url': 'http://www.teachertube.com/video/intro-video-schleicher-297790',
  50         'md5': '9c79fbb2dd7154823996fc28d4a26998',
  51         'info_dict': {
  52             'id': '297790',
  53             'ext': 'mp4',
  54             'title': 'Intro Video - Schleicher',
  55             'description': 'Intro Video - Why to flip, how flipping will',
  56         },
  57     }]
  58
  59     def _real_extract(self, url):
  60         mobj = re.match(self._VALID_URL, url)
  61         video_id = mobj.group('id')
  62
  63         webpage = self._download_webpage(url, video_id)
  64
  65         title = self._html_search_meta('title', webpage, 'title', fatal=True)
  66         TITLE_SUFFIX = ' - TeacherTube'
  67         if title.endswith(TITLE_SUFFIX):
  68             title = title[:-len(TITLE_SUFFIX)].strip()
  69
  70         description = self._html_search_meta('description', webpage, 'description')
  71         if description:
  72             description = description.strip()
  73
  74         quality = qualities(['mp3', 'flv', 'mp4'])
  75
  76         media_urls = re.findall(r'data-contenturl="([^"]+)"', webpage)
  77         media_urls.extend(re.findall(r'var\s+filePath\s*=\s*"([^"]+)"', webpage))
  78         media_urls.extend(re.findall(r'\'file\'\s*:\s*["\']([^"\']+)["\'],', webpage))
  79
  80         formats = [
  81             {
  82                 'url': media_url,
  83                 'quality': quality(determine_ext(media_url))
  84             } for media_url in set(media_urls)
  85         ]
  86
  87         self._sort_formats(formats)
  88
  89         return {
  90             'id': video_id,
  91             'title': title,
  92             'thumbnail': self._html_search_regex(r'\'image\'\s*:\s*["\']([^"\']+)["\']', webpage, 'thumbnail'),
  93             'formats': formats,
  94             'description': description,
  95         }
  96
  97
  98 class TeacherTubeUserIE(InfoExtractor):
  99     IE_NAME = 'teachertube:user:collection'
 100     IE_DESC = 'teachertube.com user and collection videos'
 101
 102     _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(user/profile|collection)/(?P<user>[0-9a-zA-Z]+)/?'
 103
 104     _MEDIA_RE = r'''(?sx)
 105         class="?sidebar_thumb_time"?>[0-9:]+</div>
 106         \s*
 107         <a\s+href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)"
 108     '''
 109
 110     def _real_extract(self, url):
 111         mobj = re.match(self._VALID_URL, url)
 112         user_id = mobj.group('user')
 113
 114         urls = []
 115         webpage = self._download_webpage(url, user_id)
 116         urls.extend(re.findall(self._MEDIA_RE, webpage))
 117
 118         pages = re.findall(r'/ajax-user/user-videos/%s\?page=([0-9]+)' % user_id, webpage)[:-1]
 119         for p in pages:
 120             more = 'http://www.teachertube.com/ajax-user/user-videos/%s?page=%s' % (user_id, p)
 121             webpage = self._download_webpage(more, user_id, 'Downloading page %s/%s' % (p, len(pages)))
 122             video_urls = re.findall(self._MEDIA_RE, webpage)
 123             urls.extend(video_urls)
 124
 125         entries = [self.url_result(vurl, 'TeacherTube') for vurl in urls]
 126         return self.playlist_result(entries, user_id)