yt_dlp/extractor/teachertube.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     determine_ext,
   6     ExtractorError,
   7     qualities,
   8 )
   9
  10
  11 class TeacherTubeIE(InfoExtractor):
  12     IE_NAME = 'teachertube'
  13     IE_DESC = 'teachertube.com videos'
  14
  15     _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(viewVideo\.php\?video_id=|music\.php\?music_id=|video/(?:[\da-z-]+-)?|audio/)(?P<id>\d+)'
  16
  17     _TESTS = [{
  18         # flowplayer
  19         'url': 'http://www.teachertube.com/viewVideo.php?video_id=339997',
  20         'md5': 'f9434ef992fd65936d72999951ee254c',
  21         'info_dict': {
  22             'id': '339997',
  23             'ext': 'mp4',
  24             'title': 'Measures of dispersion from a frequency table',
  25             'description': 'Measures of dispersion from a frequency table',
  26             'thumbnail': r're:https?://.*\.(?:jpg|png)',
  27         },
  28     }, {
  29         # jwplayer
  30         'url': 'http://www.teachertube.com/music.php?music_id=8805',
  31         'md5': '01e8352006c65757caf7b961f6050e21',
  32         'info_dict': {
  33             'id': '8805',
  34             'ext': 'mp3',
  35             'title': 'PER ASPERA AD ASTRA',
  36             'description': 'RADIJSKA EMISIJA ZRAKOPLOVNE TEHNI?KE ?KOLE P',
  37         },
  38     }, {
  39         # unavailable video
  40         'url': 'http://www.teachertube.com/video/intro-video-schleicher-297790',
  41         'only_matching': True,
  42     }]
  43
  44     def _real_extract(self, url):
  45         video_id = self._match_id(url)
  46         webpage = self._download_webpage(url, video_id)
  47
  48         error = self._search_regex(
  49             r'<div\b[^>]+\bclass=["\']msgBox error[^>]+>([^<]+)', webpage,
  50             'error', default=None)
  51         if error:
  52             raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
  53
  54         title = self._html_search_meta('title', webpage, 'title', fatal=True)
  55         TITLE_SUFFIX = ' - TeacherTube'
  56         if title.endswith(TITLE_SUFFIX):
  57             title = title[:-len(TITLE_SUFFIX)].strip()
  58
  59         description = self._html_search_meta('description', webpage, 'description')
  60         if description:
  61             description = description.strip()
  62
  63         quality = qualities(['mp3', 'flv', 'mp4'])
  64
  65         media_urls = re.findall(r'data-contenturl="([^"]+)"', webpage)
  66         media_urls.extend(re.findall(r'var\s+filePath\s*=\s*"([^"]+)"', webpage))
  67         media_urls.extend(re.findall(r'\'file\'\s*:\s*["\']([^"\']+)["\'],', webpage))
  68
  69         formats = [
  70             {
  71                 'url': media_url,
  72                 'quality': quality(determine_ext(media_url))
  73             } for media_url in set(media_urls)
  74         ]
  75
  76         thumbnail = self._og_search_thumbnail(
  77             webpage, default=None) or self._html_search_meta(
  78             'thumbnail', webpage)
  79
  80         return {
  81             'id': video_id,
  82             'title': title,
  83             'description': description,
  84             'thumbnail': thumbnail,
  85             'formats': formats,
  86         }
  87
  88
  89 class TeacherTubeUserIE(InfoExtractor):
  90     IE_NAME = 'teachertube:user:collection'
  91     IE_DESC = 'teachertube.com user and collection videos'
  92
  93     _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(user/profile|collection)/(?P<user>[0-9a-zA-Z]+)/?'
  94
  95     _MEDIA_RE = r'''(?sx)
  96         class="?sidebar_thumb_time"?>[0-9:]+</div>
  97         \s*
  98         <a\s+href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)"
  99     '''
 100     _TEST = {
 101         'url': 'http://www.teachertube.com/user/profile/rbhagwati2',
 102         'info_dict': {
 103             'id': 'rbhagwati2'
 104         },
 105         'playlist_mincount': 179,
 106     }
 107
 108     def _real_extract(self, url):
 109         mobj = self._match_valid_url(url)
 110         user_id = mobj.group('user')
 111
 112         urls = []
 113         webpage = self._download_webpage(url, user_id)
 114         urls.extend(re.findall(self._MEDIA_RE, webpage))
 115
 116         pages = re.findall(r'/ajax-user/user-videos/%s\?page=([0-9]+)' % user_id, webpage)[:-1]
 117         for p in pages:
 118             more = 'http://www.teachertube.com/ajax-user/user-videos/%s?page=%s' % (user_id, p)
 119             webpage = self._download_webpage(more, user_id, 'Downloading page %s/%s' % (p, len(pages)))
 120             video_urls = re.findall(self._MEDIA_RE, webpage)
 121             urls.extend(video_urls)
 122
 123         entries = [self.url_result(vurl, 'TeacherTube') for vurl in urls]
 124         return self.playlist_result(entries, user_id)