[youtube] Move metadata extraction after video availability check

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

diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py
index b51dcbe10dd14136220516c76e6cada7f70a9b0c..a28ee17caa5ec19b245bf39cf43e3fa448bc936a 100644 (file)
--- a/youtube_dl/extractor/pbs.py
+++ b/youtube_dl/extractor/pbs.py
@@ -421,6 +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(
@@ -504,7 +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:
@@ -512,10 +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: