[youtube] Fix extraction.

[youtube-dl] / youtube_dl / extractor / teachertube.py

diff --git a/youtube_dl/extractor/teachertube.py b/youtube_dl/extractor/teachertube.py
index 7167a036e7a5649e1e886af80185a2bb2973e60c..1272078c50b8703aa906e055fc57842078542e95 100644 (file)
--- a/youtube_dl/extractor/teachertube.py
+++ b/youtube_dl/extractor/teachertube.py
@@ -1,12 +1,13 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
 from ..utils import (
-    qualities,
     determine_ext,
+    ExtractorError,
+    qualities,
 )
 
 
@@ -14,9 +15,10 @@ 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=|video/|audio/)(?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 = [{
+        # flowplayer
         'url': 'http://www.teachertube.com/viewVideo.php?video_id=339997',
         'md5': 'f9434ef992fd65936d72999951ee254c',
         'info_dict': {
@@ -24,19 +26,10 @@ 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',
-        },
-    }, {
-        'url': 'http://www.teachertube.com/viewVideo.php?video_id=340064',
-        'md5': '0d625ec6bc9bf50f70170942ad580676',
-        'info_dict': {
-            'id': '340064',
-            '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:https?://.*\.(?:jpg|png)',
         },
     }, {
+        # jwplayer
         'url': 'http://www.teachertube.com/music.php?music_id=8805',
         'md5': '01e8352006c65757caf7b961f6050e21',
         'info_dict': {
@@ -45,15 +38,23 @@ class TeacherTubeIE(InfoExtractor):
             'title': 'PER ASPERA AD ASTRA',
             'description': 'RADIJSKA EMISIJA ZRAKOPLOVNE TEHNI?KE ?KOLE P',
         },
+    }, {
+        # unavailable video
+        'url': 'http://www.teachertube.com/video/intro-video-schleicher-297790',
+        'only_matching': True,
     }]
 
     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')
+        error = self._search_regex(
+            r'<div\b[^>]+\bclass=["\']msgBox error[^>]+>([^<]+)', webpage,
+            'error', default=None)
+        if error:
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
+
+        title = self._html_search_meta('title', webpage, 'title', fatal=True)
         TITLE_SUFFIX = ' - TeacherTube'
         if title.endswith(TITLE_SUFFIX):
             title = title[:-len(TITLE_SUFFIX)].strip()
@@ -77,12 +78,16 @@ class TeacherTubeIE(InfoExtractor):
 
         self._sort_formats(formats)
 
+        thumbnail = self._og_search_thumbnail(
+            webpage, default=None) or self._html_search_meta(
+            'thumbnail', webpage)
+
         return {
             'id': video_id,
             'title': title,
-            'thumbnail': self._html_search_regex(r'\'image\'\s*:\s*["\']([^"\']+)["\']', webpage, 'thumbnail'),
-            'formats': formats,
             'description': description,
+            'thumbnail': thumbnail,
+            'formats': formats,
         }
 
 
@@ -92,7 +97,18 @@ class TeacherTubeUserIE(InfoExtractor):
 
     _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(user/profile|collection)/(?P<user>[0-9a-zA-Z]+)/?'
 
-    _MEDIA_RE = r'(?s)"sidebar_thumb_time">[0-9:]+</div>.+?<a href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)">'
+    _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)
@@ -101,15 +117,13 @@ class TeacherTubeUserIE(InfoExtractor):
         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]
+
+        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) + 1))
-            urls.extend(re.findall(self._MEDIA_RE, webpage))
-
-        entries = []
-        for url in urls:
-            entries.append(self.url_result(url, 'TeacherTube'))
+            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)