New upstream version 2017.12.31

[youtubedl] / youtube_dl / extractor / youtube.py

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index 4e8db240d3f9d141cfa457c1d941d1b5399f0c67..0919bef0e06ae1b839a7debc38bdf457dafae192 100644 (file)
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -1391,7 +1391,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             )
             (["\'])
                 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
             )
             (["\'])
                 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/

-                (?:embed|v|p)/.+?)
+                (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)

             \1''', webpage)]
 
         # lazyYT YouTube embed
             \1''', webpage)]
 
         # lazyYT YouTube embed


@@ -1622,6 +1622,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         # description
         description_original = video_description = get_element_by_id("eow-description", video_webpage)
         if video_description:
         # description
         description_original = video_description = get_element_by_id("eow-description", video_webpage)
         if video_description:

+
+            def replace_url(m):
+                redir_url = compat_urlparse.urljoin(url, m.group(1))
+                parsed_redir_url = compat_urllib_parse_urlparse(redir_url)
+                if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect':
+                    qs = compat_parse_qs(parsed_redir_url.query)
+                    q = qs.get('q')
+                    if q and q[0]:
+                        return q[0]
+                return redir_url
+

             description_original = video_description = re.sub(r'''(?x)
                 <a\s+
                     (?:[a-zA-Z-]+="[^"]*"\s+)*?
             description_original = video_description = re.sub(r'''(?x)
                 <a\s+
                     (?:[a-zA-Z-]+="[^"]*"\s+)*?


@@ -1630,7 +1641,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     class="[^"]*"[^>]*>
                 [^<]+\.{3}\s*
                 </a>
                     class="[^"]*"[^>]*>
                 [^<]+\.{3}\s*
                 </a>

-            ''', lambda m: compat_urlparse.urljoin(url, m.group(1)), video_description)
+            ''', replace_url, video_description)

             video_description = clean_html(video_description)
         else:
             fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
             video_description = clean_html(video_description)
         else:
             fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)


@@ -2259,6 +2270,19 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
             r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
             page, 'title', default=None)
 
             r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
             page, 'title', default=None)
 

+        _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
+        uploader = self._search_regex(
+            r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE,
+            page, 'uploader', default=None)
+        mobj = re.search(
+            r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE,
+            page)
+        if mobj:
+            uploader_id = mobj.group('uploader_id')
+            uploader_url = compat_urlparse.urljoin(url, mobj.group('path'))
+        else:
+            uploader_id = uploader_url = None
+

         has_videos = True
 
         if not playlist_title:
         has_videos = True
 
         if not playlist_title:


@@ -2269,8 +2293,15 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
             except StopIteration:
                 has_videos = False
 
             except StopIteration:
                 has_videos = False
 

-        return has_videos, self.playlist_result(
+        playlist = self.playlist_result(

             self._entries(page, playlist_id), playlist_id, playlist_title)
             self._entries(page, playlist_id), playlist_id, playlist_title)

+        playlist.update({
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'uploader_url': uploader_url,
+        })
+
+        return has_videos, playlist

 
     def _check_download_just_video(self, url, playlist_id):
         # Check if it's a video-specific URL
 
     def _check_download_just_video(self, url, playlist_id):
         # Check if it's a video-specific URL