X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fpbs.py;h=a28ee17caa5ec19b245bf39cf43e3fa448bc936a;hb=f7560859a3e25ccaa74123428d42f821299a2bed;hp=8889e4a1aaa3e41f49a63b53c010cf69d0842b1b;hpb=7b67b60773b70ac74edd3993eeea6fe9b790c664;p=youtube-dl

diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py
index 8889e4a1a..a28ee17ca 100644
--- a/youtube_dl/extractor/pbs.py
+++ b/youtube_dl/extractor/pbs.py
@@ -187,7 +187,7 @@ class PBSIE(InfoExtractor):
     _VALID_URL = r'''(?x)https?://
         (?:
            # Direct video URL
-           (?:%s)/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
+           (?:%s)/(?:(?:vir|port)alplayer|video)/(?P<id>[0-9]+)(?:[?/]|$) |
            # Article with embedded player (or direct video)
            (?:www\.)?pbs\.org/(?:[^/]+/){1,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
            # Player
@@ -367,6 +367,10 @@ class PBSIE(InfoExtractor):
         {
             'url': 'http://watch.knpb.org/video/2365616055/',
             'only_matching': True,
+        },
+        {
+            'url': 'https://player.pbs.org/portalplayer/3004638221/?uid=',
+            'only_matching': True,
         }
     ]
     _ERRORS = {
@@ -417,6 +421,7 @@ class PBSIE(InfoExtractor):
                 r'class="coveplayerid">([^<]+)<',                       # coveplayer
                 r'<section[^>]+data-coveid="(\d+)"',                    # coveplayer from http://www.pbs.org/wgbh/frontline/film/real-csi/
                 r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>',  # jwplayer
+                r"(?s)window\.PBS\.playerConfig\s*=\s*{.*?id\s*:\s*'([0-9]+)',",
             ]
 
             media_id = self._search_regex(
@@ -500,7 +505,7 @@ class PBSIE(InfoExtractor):
             if player:
                 video_info = self._parse_json(
                     self._search_regex(
-                        r'(?s)PBS\.videoData\s*=\s*({.+?});\n',
+                        [r'(?s)PBS\.videoData\s*=\s*({.+?});\n', r'window\.videoBridge\s*=\s*({.+?});'],
                         player, '%s video data' % page, default='{}'),
                     display_id, transform_source=js_to_json, fatal=False)
                 if video_info:
@@ -508,10 +513,14 @@ class PBSIE(InfoExtractor):
                     if not info:
                         info = video_info
                 if not chapters:
-                    for chapter_data in re.findall(r'(?s)chapters\.push\(({.*?})\)', player):
-                        chapter = self._parse_json(chapter_data, video_id, js_to_json, fatal=False)
-                        if not chapter:
-                            continue
+                    raw_chapters = video_info.get('chapters') or []
+                    if not raw_chapters:
+                        for chapter_data in re.findall(r'(?s)chapters\.push\(({.*?})\)', player):
+                            chapter = self._parse_json(chapter_data, video_id, js_to_json, fatal=False)
+                            if not chapter:
+                                continue
+                            raw_chapters.append(chapter)
+                    for chapter in raw_chapters:
                         start_time = float_or_none(chapter.get('start_time'), 1000)
                         duration = float_or_none(chapter.get('duration'), 1000)
                         if start_time is None or duration is None: