Add support for https for all extractors as preventive and future-proof measure

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

diff --git a/youtube_dl/extractor/redtube.py b/youtube_dl/extractor/redtube.py
index 6d56f16f1d484b2769642305447a17d485c9442a..7ba41ba593295cdc7d2e28e6b64702321ed1ef08 100644 (file)
--- a/youtube_dl/extractor/redtube.py
+++ b/youtube_dl/extractor/redtube.py
@@ -1,34 +1,45 @@
-import re
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-)
+from ..utils import ExtractorError
 
 
 class RedTubeIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
-
-    def _real_extract(self,url):
-        mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
-
-        video_id = mobj.group('id')
-        video_extension = 'mp4'        
+    _VALID_URL = r'https?://(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.redtube.com/66418',
+        'md5': '7b8c22b5e7098a3e1c09709df1126d2d',
+        'info_dict': {
+            'id': '66418',
+            'ext': 'mp4',
+            'title': 'Sucked on a toilet',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        self.report_extraction(video_id)
-
-        video_url = self._html_search_regex(r'<source src="(.+?)" type="video/mp4">',
-            webpage, u'video URL')
-
-        video_title = self._html_search_regex('<h1 class="videoTitle slidePanelMovable">(.+?)</h1>',
-            webpage, u'title')
-
-        return [{
-            'id':       video_id,
-            'url':      video_url,
-            'ext':      video_extension,
-            'title':    video_title,
-        }]
+        if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']):
+            raise ExtractorError('Video %s has been removed' % video_id, expected=True)
+
+        video_url = self._html_search_regex(
+            r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
+        video_title = self._html_search_regex(
+            r'<h1 class="videoTitle[^"]*">(.+?)</h1>',
+            webpage, 'title')
+        video_thumbnail = self._og_search_thumbnail(webpage)
+
+        # No self-labeling, but they describe themselves as
+        # "Home of Videos Porno"
+        age_limit = 18
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': video_title,
+            'thumbnail': video_thumbnail,
+            'age_limit': age_limit,
+        }