]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/teachertube.py
1 # -*- coding: utf-8 -*-
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
13 class TeacherTubeIE(InfoExtractor
):
14 IE_NAME
= 'teachertube'
15 IE_DESC
= 'teachertube.com videos'
17 _VALID_URL
= r
'https?://(?:www\.)?teachertube\.com/(viewVideo\.php\?video_id=|music\.php\?music_id=|video/(?:[\da-z-]+-)?|audio/)(?P<id>\d+)'
20 'url': 'http://www.teachertube.com/viewVideo.php?video_id=339997',
21 'md5': 'f9434ef992fd65936d72999951ee254c',
25 'title': 'Measures of dispersion from a frequency table',
26 'description': 'Measures of dispersion from a frequency table',
27 'thumbnail': 're:http://.*\.jpg',
30 'url': 'http://www.teachertube.com/viewVideo.php?video_id=340064',
31 'md5': '0d625ec6bc9bf50f70170942ad580676',
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',
40 'url': 'http://www.teachertube.com/music.php?music_id=8805',
41 'md5': '01e8352006c65757caf7b961f6050e21',
45 'title': 'PER ASPERA AD ASTRA',
46 'description': 'RADIJSKA EMISIJA ZRAKOPLOVNE TEHNI?KE ?KOLE P',
49 'url': 'http://www.teachertube.com/video/intro-video-schleicher-297790',
50 'md5': '9c79fbb2dd7154823996fc28d4a26998',
54 'title': 'Intro Video - Schleicher',
55 'description': 'Intro Video - Why to flip, how flipping will',
59 def _real_extract(self
, url
):
60 mobj
= re
.match(self
._VALID
_URL
, url
)
61 video_id
= mobj
.group('id')
63 webpage
= self
._download
_webpage
(url
, video_id
)
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()
70 description
= self
._html
_search
_meta
('description', webpage
, 'description')
72 description
= description
.strip()
74 quality
= qualities(['mp3', 'flv', 'mp4'])
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))
83 'quality': quality(determine_ext(media_url))
84 } for media_url in set(media_urls)
87 self._sort_formats(formats)
92 'thumbnail': self._html_search_regex(r'\'image\'\s*:\s*["\']([^
"\']+)["\']', webpage, 'thumbnail
'),
94 'description
': description,
98 class TeacherTubeUserIE(InfoExtractor):
99 IE_NAME = 'teachertube
:user
:collection
'
100 IE_DESC = 'teachertube
.com user
and collection videos
'
102 _VALID_URL = r'https?
://(?
:www\
.)?teachertube\
.com
/(user
/profile|collection
)/(?P
<user
>[0-9a
-zA
-Z
]+)/?
'
104 _MEDIA_RE = r'''(?sx)
105 class="?sidebar_thumb_time"?>[0-9:]+</div>
107 <a\s+href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)"
110 'url
': 'http
://www
.teachertube
.com
/user
/profile
/rbhagwati2
',
114 'playlist_mincount
': 179,
117 def _real_extract(self, url):
118 mobj = re.match(self._VALID_URL, url)
119 user_id = mobj.group('user
')
122 webpage = self._download_webpage(url, user_id)
123 urls.extend(re.findall(self._MEDIA_RE, webpage))
125 pages = re.findall(r'/ajax
-user
/user
-videos
/%s\?page
=([0-9]+)' % user_id, webpage)[:-1]
127 more = 'http
://www
.teachertube
.com
/ajax
-user
/user
-videos
/%s?page
=%s' % (user_id, p)
128 webpage = self._download_webpage(more, user_id, 'Downloading page
%s/%s' % (p, len(pages)))
129 video_urls = re.findall(self._MEDIA_RE, webpage)
130 urls.extend(video_urls)
132 entries = [self.url_result(vurl, 'TeacherTube
') for vurl in urls]
133 return self.playlist_result(entries, user_id)