X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fteachertube.py;h=f14713a78904c0e879571d6642061f3baa7a617a;hb=ec85ded83cbfa652ba94cb080aab52d8b270212a;hp=b3cb6bd76db9b691135a9a32e2d9ab5cda1f8655;hpb=9a2dc4f7ac308725afd651b1f0f92291d1906496;p=youtube-dl

diff --git a/youtube_dl/extractor/teachertube.py b/youtube_dl/extractor/teachertube.py
index b3cb6bd76..f14713a78 100644
--- a/youtube_dl/extractor/teachertube.py
+++ b/youtube_dl/extractor/teachertube.py
@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -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',
@@ -24,7 +24,7 @@ class TeacherTubeIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Measures of dispersion from a frequency table',
             'description': 'Measures of dispersion from a frequency table',
-            'thumbnail': 're:http://.*\.jpg',
+            'thumbnail': r're:http://.*\.jpg',
         },
     }, {
         'url': 'http://www.teachertube.com/viewVideo.php?video_id=340064',
@@ -34,7 +34,7 @@ class TeacherTubeIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'How to Make Paper Dolls _ Paper Art Projects',
             'description': 'Learn how to make paper dolls in this simple',
-            'thumbnail': 're:http://.*\.jpg',
+            'thumbnail': r're:http://.*\.jpg',
         },
     }, {
         'url': 'http://www.teachertube.com/music.php?music_id=8805',
@@ -45,15 +45,22 @@ 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):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        title = self._html_search_meta('title', webpage, 'title')
+        title = self._html_search_meta('title', webpage, 'title', fatal=True)
         TITLE_SUFFIX = ' - TeacherTube'
         if title.endswith(TITLE_SUFFIX):
             title = title[:-len(TITLE_SUFFIX)].strip()
@@ -66,6 +73,7 @@ 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 +87,45 @@ 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'''(?sx)
+        class="?sidebar_thumb_time"?>[0-9:]+</div>
+        \s*
+        <a\s+href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)"
+    '''
+    _TEST = {
+        'url': 'http://www.teachertube.com/user/profile/rbhagwati2',
+        'info_dict': {
+            'id': 'rbhagwati2'
+        },
+        'playlist_mincount': 179,
+    }
 
     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))
 
-        entries = []
-        for url in rss.findall('.//{http://search.yahoo.com/mrss/}player'):
-            entries.append(self.url_result(url.attrib['url'], 'TeacherTube'))
+        pages = re.findall(r'/ajax-user/user-videos/%s\?page=([0-9]+)' % user_id, webpage)[:-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)))
+            video_urls = re.findall(self._MEDIA_RE, webpage)
+            urls.extend(video_urls)
 
+        entries = [self.url_result(vurl, 'TeacherTube') for vurl in urls]
         return self.playlist_result(entries, user_id)