From f20f636596aa4ec949360e7b05f6b9499e28c2a2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com>
Date: Sat, 2 Jun 2018 00:35:07 +0700
Subject: [PATCH] [cbc] Improve extraction (closes #16583, closes #16593)

---
 youtube_dl/extractor/cbc.py | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/youtube_dl/extractor/cbc.py b/youtube_dl/extractor/cbc.py
index ce8e3d346..43f95c739 100644
--- a/youtube_dl/extractor/cbc.py
+++ b/youtube_dl/extractor/cbc.py
@@ -17,6 +17,7 @@
     xpath_element,
     xpath_with_ns,
     find_xpath_attr,
+    orderedSet,
     parse_duration,
     parse_iso8601,
     parse_age_limit,
@@ -136,9 +137,15 @@ def _real_extract(self, url):
         entries = [
             self._extract_player_init(player_init, display_id)
             for player_init in re.findall(r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage)]
+        media_ids = []
+        for media_id_re in (
+                r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"',
+                r'<div[^>]+\bid=["\']player-(\d+)',
+                r'guid["\']\s*:\s*["\'](\d+)'):
+            media_ids.extend(re.findall(media_id_re, webpage))
         entries.extend([
             self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
-            for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)])
+            for media_id in orderedSet(media_ids)])
         return self.playlist_result(
             entries, display_id, strip_or_none(title),
             self._og_search_description(webpage))