diff options
Diffstat (limited to 'youtube_dl/extractor/teachertube.py')
| -rw-r--r-- | youtube_dl/extractor/teachertube.py | 40 |
1 files changed, 29 insertions, 11 deletions
diff --git a/youtube_dl/extractor/teachertube.py b/youtube_dl/extractor/teachertube.py index b3cb6bd76..2c2113b14 100644 --- a/youtube_dl/extractor/teachertube.py +++ b/youtube_dl/extractor/teachertube.py @@ -14,7 +14,7 @@ class TeacherTubeIE(InfoExtractor): IE_NAME = 'teachertube' IE_DESC = 'teachertube.com videos' - _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(viewVideo\.php\?video_id=|music\.php\?music_id=)(?P<id>\d+)' + _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(viewVideo\.php\?video_id=|music\.php\?music_id=|video/(?:[\da-z-]+-)?|audio/)(?P<id>\d+)' _TESTS = [{ 'url': 'http://www.teachertube.com/viewVideo.php?video_id=339997', @@ -45,6 +45,15 @@ class TeacherTubeIE(InfoExtractor): 'title': 'PER ASPERA AD ASTRA', 'description': 'RADIJSKA EMISIJA ZRAKOPLOVNE TEHNI?KE ?KOLE P', }, + }, { + 'url': 'http://www.teachertube.com/video/intro-video-schleicher-297790', + 'md5': '9c79fbb2dd7154823996fc28d4a26998', + 'info_dict': { + 'id': '297790', + 'ext': 'mp4', + 'title': 'Intro Video - Schleicher', + 'description': 'Intro Video - Why to flip, how flipping will', + }, }] def _real_extract(self, url): @@ -66,6 +75,7 @@ class TeacherTubeIE(InfoExtractor): media_urls = re.findall(r'data-contenturl="([^"]+)"', webpage) media_urls.extend(re.findall(r'var\s+filePath\s*=\s*"([^"]+)"', webpage)) + media_urls.extend(re.findall(r'\'file\'\s*:\s*["\']([^"\']+)["\'],', webpage)) formats = [ { @@ -79,28 +89,36 @@ class TeacherTubeIE(InfoExtractor): return { 'id': video_id, 'title': title, - 'thumbnail': self._html_search_regex(r'var\s+thumbUrl\s*=\s*"([^"]+)"', webpage, 'thumbnail'), + 'thumbnail': self._html_search_regex(r'\'image\'\s*:\s*["\']([^"\']+)["\']', webpage, 'thumbnail'), 'formats': formats, 'description': description, } -class TeacherTubeClassroomIE(InfoExtractor): - IE_NAME = 'teachertube:classroom' - IE_DESC = 'teachertube.com online classrooms' +class TeacherTubeUserIE(InfoExtractor): + IE_NAME = 'teachertube:user:collection' + IE_DESC = 'teachertube.com user and collection videos' + + _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(user/profile|collection)/(?P<user>[0-9a-zA-Z]+)/?' - _VALID_URL = r'https?://(?:www\.)?teachertube\.com/view_classroom\.php\?user=(?P<user>[0-9a-zA-Z]+)' + _MEDIA_RE = r'(?s)"sidebar_thumb_time">[0-9:]+</div>.+?<a href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)">' def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) user_id = mobj.group('user') - rss = self._download_xml( - 'http://www.teachertube.com/rssclassroom.php?mode=user&username=%s' % user_id, - user_id, 'Downloading classroom RSS') + urls = [] + webpage = self._download_webpage(url, user_id) + urls.extend(re.findall(self._MEDIA_RE, webpage)) + + pages = re.findall(r'/ajax-user/user-videos/%s\?page=([0-9]+)' % user_id, webpage)[1:-1] + for p in pages: + more = 'http://www.teachertube.com/ajax-user/user-videos/%s?page=%s' % (user_id, p) + webpage = self._download_webpage(more, user_id, 'Downloading page %s/%s' % (p, len(pages) + 1)) + urls.extend(re.findall(self._MEDIA_RE, webpage)) entries = [] - for url in rss.findall('.//{http://search.yahoo.com/mrss/}player'): - entries.append(self.url_result(url.attrib['url'], 'TeacherTube')) + for url in urls: + entries.append(self.url_result(url, 'TeacherTube')) return self.playlist_result(entries, user_id) |