]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/teachertube.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
14 class TeacherTubeIE(InfoExtractor
):
15 IE_NAME
= 'teachertube'
16 IE_DESC
= 'teachertube.com videos'
18 _VALID_URL
= r
'https?://(?:www\.)?teachertube\.com/(viewVideo\.php\?video_id=|music\.php\?music_id=|video/(?:[\da-z-]+-)?|audio/)(?P<id>\d+)'
22 'url': 'http://www.teachertube.com/viewVideo.php?video_id=339997',
23 'md5': 'f9434ef992fd65936d72999951ee254c',
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)',
33 'url': 'http://www.teachertube.com/music.php?music_id=8805',
34 'md5': '01e8352006c65757caf7b961f6050e21',
38 'title': 'PER ASPERA AD ASTRA',
39 'description': 'RADIJSKA EMISIJA ZRAKOPLOVNE TEHNI?KE ?KOLE P',
43 'url': 'http://www.teachertube.com/video/intro-video-schleicher-297790',
44 'only_matching': True,
47 def _real_extract(self
, url
):
48 video_id
= self
._match
_id
(url
)
49 webpage
= self
._download
_webpage
(url
, video_id
)
51 error
= self
._search
_regex
(
52 r
'<div\b[^>]+\bclass=["\']msgBox error
[^
>]+>([^
<]+)', webpage,
53 'error
', default=None)
55 raise ExtractorError('%s said
: %s' % (self.IE_NAME, error), expected=True)
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()
62 description = self._html_search_meta('description
', webpage, 'description
')
64 description = description.strip()
66 quality = qualities(['mp3
', 'flv
', 'mp4
'])
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))
75 'quality': quality(determine_ext(media_url))
76 } for media_url in set(media_urls)
79 self._sort_formats(formats)
81 thumbnail = self._og_search_thumbnail(
82 webpage, default=None) or self._html_search_meta(
88 'description': description,
89 'thumbnail': thumbnail,
94 class TeacherTubeUserIE(InfoExtractor):
95 IE_NAME = 'teachertube:user:collection'
96 IE_DESC = 'teachertube.com user and collection videos'
98 _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(user/profile|collection)/(?P<user>[0-9a-zA-Z]+)/?'
100 _MEDIA_RE = r'''(?sx)
101 class="?sidebar_thumb_time
"?>[0-9:]+</div>
103 <a\s+href="(https?
://(?
:www\
.)?teachertube\
.com
/(?
:video|audio
)/[^
"]+)"
106 'url': 'http://www.teachertube.com/user/profile/rbhagwati2',
110 'playlist_mincount': 179,
113 def _real_extract(self, url):
114 mobj = re.match(self._VALID_URL, url)
115 user_id = mobj.group('user')
118 webpage = self._download_webpage(url, user_id)
119 urls.extend(re.findall(self._MEDIA_RE, webpage))
121 pages = re.findall(r'/ajax-user/user-videos/%s\?page=([0-9]+)' % user_id, webpage)[:-1]
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)
128 entries = [self.url_result(vurl, 'TeacherTube') for vurl in urls]
129 return self.playlist_result(entries, user_id)