From: Sergey M․ <dstftw@gmail.com>
Date: Thu, 3 Aug 2017 16:19:59 +0000 (+0700)
Subject: [pbs] Add support for new URL schema (closes #13801)
X-Git-Url: https://git.cielonegro.org/gitweb.cgi?a=commitdiff_plain;h=183062a4ab2f698f5096e69602fb2b5c861c01a0;p=youtube-dl.git

[pbs] Add support for new URL schema (closes #13801)
---

diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py
index 16cc667d0..8889e4a1a 100644
--- a/youtube_dl/extractor/pbs.py
+++ b/youtube_dl/extractor/pbs.py
@@ -189,7 +189,7 @@ class PBSIE(InfoExtractor):
            # Direct video URL
            (?:%s)/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
            # Article with embedded player (or direct video)
-           (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
+           (?:www\.)?pbs\.org/(?:[^/]+/){1,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
            # Player
            (?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
         )
@@ -345,6 +345,21 @@ class PBSIE(InfoExtractor):
                 'formats': 'mincount:8',
             },
         },
+        {
+            # https://github.com/rg3/youtube-dl/issues/13801
+            'url': 'https://www.pbs.org/video/pbs-newshour-full-episode-july-31-2017-1501539057/',
+            'info_dict': {
+                'id': '3003333873',
+                'ext': 'mp4',
+                'title': 'PBS NewsHour - full episode July 31, 2017',
+                'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+                'duration': 3265,
+                'thumbnail': r're:^https?://.*\.jpg$',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
         {
             'url': 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true',
             'only_matching': True,
@@ -433,6 +448,9 @@ class PBSIE(InfoExtractor):
                 if url:
                     break
 
+            if not url:
+                url = self._og_search_url(webpage)
+
             mobj = re.match(self._VALID_URL, url)
 
         player_id = mobj.group('player_id')