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     determine_ext,
   9     ExtractorError,
  10     qualities,
  11 )
  12
  13
  14 class TeacherTubeIE(InfoExtractor):
  15     IE_NAME = 'teachertube'
  16     IE_DESC = 'teachertube.com videos'
  17
  18     _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(viewVideo\.php\?video_id=|music\.php\?music_id=|video/(?:[\da-z-]+-)?|audio/)(?P<id>\d+)'
  19
  20     _TESTS = [{
  21         # flowplayer
  22         'url': 'http://www.teachertube.com/viewVideo.php?video_id=339997',
  23         'md5': 'f9434ef992fd65936d72999951ee254c',
  24         'info_dict': {
  25             'id': '339997',
  26             'ext': 'mp4',
  27             'title': 'Measures of dispersion from a frequency table',
  28             'description': 'Measures of dispersion from a frequency table',
  29             'thumbnail': r're:https?://.*\.(?:jpg|png)',
  30         },
  31     }, {
  32         # jwplayer
  33         'url': 'http://www.teachertube.com/music.php?music_id=8805',
  34         'md5': '01e8352006c65757caf7b961f6050e21',
  35         'info_dict': {
  36             'id': '8805',
  37             'ext': 'mp3',
  38             'title': 'PER ASPERA AD ASTRA',
  39             'description': 'RADIJSKA EMISIJA ZRAKOPLOVNE TEHNI?KE ?KOLE P',
  40         },
  41     }, {
  42         # unavailable video
  43         'url': 'http://www.teachertube.com/video/intro-video-schleicher-297790',
  44         'only_matching': True,
  45     }]
  46
  47     def _real_extract(self, url):
  48         video_id = self._match_id(url)
  49         webpage = self._download_webpage(url, video_id)
  50
  51         error = self._search_regex(
  52             r'<div\b[^>]+\bclass=["\']msgBox error[^>]+>([^<]+)', webpage,
  53             'error', default=None)
  54         if error:
  55             raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
  56
  57         title = self._html_search_meta('title', webpage, 'title', fatal=True)
  58         TITLE_SUFFIX = ' - TeacherTube'
  59         if title.endswith(TITLE_SUFFIX):
  60             title = title[:-len(TITLE_SUFFIX)].strip()
  61
  62         description = self._html_search_meta('description', webpage, 'description')
  63         if description:
  64             description = description.strip()
  65
  66         quality = qualities(['mp3', 'flv', 'mp4'])
  67
  68         media_urls = re.findall(r'data-contenturl="([^"]+)"', webpage)
  69         media_urls.extend(re.findall(r'var\s+filePath\s*=\s*"([^"]+)"', webpage))
  70         media_urls.extend(re.findall(r'\'file\'\s*:\s*["\']([^"\']+)["\'],', webpage))
  71
  72         formats = [
  73             {
  74                 'url': media_url,
  75                 'quality': quality(determine_ext(media_url))
  76             } for media_url in set(media_urls)
  77         ]
  78
  79         self._sort_formats(formats)
  80
  81         thumbnail = self._og_search_thumbnail(
  82             webpage, default=None) or self._html_search_meta(
  83             'thumbnail', webpage)
  84
  85         return {
  86             'id': video_id,
  87             'title': title,
  88             'description': description,
  89             'thumbnail': thumbnail,
  90             'formats': formats,
  91         }
  92
  93
  94 class TeacherTubeUserIE(InfoExtractor):
  95     IE_NAME = 'teachertube:user:collection'
  96     IE_DESC = 'teachertube.com user and collection videos'
  97
  98     _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(user/profile|collection)/(?P<user>[0-9a-zA-Z]+)/?'
  99
 100     _MEDIA_RE = r'''(?sx)
 101         class="?sidebar_thumb_time"?>[0-9:]+</div>
 102         \s*
 103         <a\s+href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)"
 104     '''
 105     _TEST = {
 106         'url': 'http://www.teachertube.com/user/profile/rbhagwati2',
 107         'info_dict': {
 108             'id': 'rbhagwati2'
 109         },
 110         'playlist_mincount': 179,
 111     }
 112
 113     def _real_extract(self, url):
 114         mobj = re.match(self._VALID_URL, url)
 115         user_id = mobj.group('user')
 116
 117         urls = []
 118         webpage = self._download_webpage(url, user_id)
 119         urls.extend(re.findall(self._MEDIA_RE, webpage))
 120
 121         pages = re.findall(r'/ajax-user/user-videos/%s\?page=([0-9]+)' % user_id, webpage)[:-1]
 122         for p in pages:
 123             more = 'http://www.teachertube.com/ajax-user/user-videos/%s?page=%s' % (user_id, p)
 124             webpage = self._download_webpage(more, user_id, 'Downloading page %s/%s' % (p, len(pages)))
 125             video_urls = re.findall(self._MEDIA_RE, webpage)
 126             urls.extend(video_urls)
 127
 128         entries = [self.url_result(vurl, 'TeacherTube') for vurl in urls]
 129         return self.playlist_result(entries, user_id)