Update upstream source from tag 'upstream/2018.03.14'

[youtubedl] / youtube_dl / extractor / common.py

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index deafb48508fc7a0def88e5bd23fab558d37d8213..fcdd0fd14a85a12690031b409058d932a3d4e4db 100644 (file)
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -174,6 +174,8 @@ class InfoExtractor(object):
                                  width : height ratio as float.
                     * no_resume  The server does not support resuming the
                                  (HTTP or RTMP) download. Boolean.
                                  width : height ratio as float.
                     * no_resume  The server does not support resuming the
                                  (HTTP or RTMP) download. Boolean.

+                    * downloader_options  A dictionary of downloader options as
+                                 described in FileDownloader

 
     url:            Final video URL.
     ext:            Video filename extension.
 
     url:            Final video URL.
     ext:            Video filename extension.


@@ -2248,9 +2250,10 @@ class InfoExtractor(object):
     def _extract_wowza_formats(self, url, video_id, m3u8_entry_protocol='m3u8_native', skip_protocols=[]):
         query = compat_urlparse.urlparse(url).query
         url = re.sub(r'/(?:manifest|playlist|jwplayer)\.(?:m3u8|f4m|mpd|smil)', '', url)
     def _extract_wowza_formats(self, url, video_id, m3u8_entry_protocol='m3u8_native', skip_protocols=[]):
         query = compat_urlparse.urlparse(url).query
         url = re.sub(r'/(?:manifest|playlist|jwplayer)\.(?:m3u8|f4m|mpd|smil)', '', url)

-        url_base = self._search_regex(
-            r'(?:(?:https?|rtmp|rtsp):)?(//[^?]+)', url, 'format url')
-        http_base_url = '%s:%s' % ('http', url_base)
+        mobj = re.search(
+            r'(?:(?:http|rtmp|rtsp)(?P<s>s)?:)?(?P<url>//[^?]+)', url)
+        url_base = mobj.group('url')
+        http_base_url = '%s%s:%s' % ('http', mobj.group('s') or '', url_base)

         formats = []
 
         def manifest_url(manifest):
         formats = []
 
         def manifest_url(manifest):


@@ -2350,7 +2353,10 @@ class InfoExtractor(object):
                 for track in tracks:
                     if not isinstance(track, dict):
                         continue
                 for track in tracks:
                     if not isinstance(track, dict):
                         continue

-                    if track.get('kind') != 'captions':
+                    track_kind = track.get('kind')
+                    if not track_kind or not isinstance(track_kind, compat_str):
+                        continue
+                    if track_kind.lower() not in ('captions', 'subtitles'):

                         continue
                     track_url = urljoin(base_url, track.get('file'))
                     if not track_url:
                         continue
                     track_url = urljoin(base_url, track.get('file'))
                     if not track_url: