_ 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 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/|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
  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         title = self._html_search_meta('title', webpage, 'title')
  57         TITLE_SUFFIX = ' - TeacherTube'
  58         if title.endswith(TITLE_SUFFIX):
  59             title = title[:-len(TITLE_SUFFIX)].strip()
  60
  61         description = self._html_search_meta('description', webpage, 'description')
  62         if description:
  63             description = description.strip()
  64
  65         quality = qualities(['mp3', 'flv', 'mp4'])
  66
  67         media_urls = re.findall(r'data-contenturl="([^"]+)"', webpage)
  68         media_urls.extend(re.findall(r'var\s+filePath\s*=\s*"([^"]+)"', webpage))
  69         media_urls.extend(re.findall(r'\'file\'\s*:\s*["\']([^"\']+)["\'],', webpage))
  70
  71         formats = [
  72             {
  73                 'url': media_url,
  74                 'quality': quality(determine_ext(media_url))
  75             } for media_url in set(media_urls)
  76         ]
  77
  78         self._sort_formats(formats)
  79
  80         return {
  81             'id': video_id,
  82             'title': title,
  83             'thumbnail': self._html_search_regex(r'\'image\'\s*:\s*["\']([^"\']+)["\']', webpage, 'thumbnail'),
  84             'formats': formats,
  85             'description': description,
  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'(?s)"sidebar_thumb_time">[0-9:]+</div>.+?<a href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)">'
  96
  97     def _real_extract(self, url):
  98         mobj = re.match(self._VALID_URL, url)
  99         user_id = mobj.group('user')
 100
 101         urls = []
 102         webpage = self._download_webpage(url, user_id)
 103         urls.extend(re.findall(self._MEDIA_RE, webpage))
 104
 105         pages = re.findall(r'/ajax-user/user-videos/%s\?page=([0-9]+)' % user_id, webpage)[1:-1]
 106         for p in pages:
 107             more = 'http://www.teachertube.com/ajax-user/user-videos/%s?page=%s' % (user_id, p)
 108             webpage = self._download_webpage(more, user_id, 'Downloading page %s/%s' % (p, len(pages) + 1))
 109             urls.extend(re.findall(self._MEDIA_RE, webpage))
 110
 111         entries = []
 112         for url in urls:
 113             entries.append(self.url_result(url, 'TeacherTube'))
 114
 115         return self.playlist_result(entries, user_id)