From 6c6b8bd5ccef10aad73ee5a556830f9b00b93661 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?=
<jaime.marquinez.ferrandiz@gmail.com>
Date: Mon, 28 Dec 2015 13:48:10 +0100
Subject: [PATCH] [cspan] Fix extraction (fixes #8032)
---
youtube_dl/extractor/cspan.py | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py
index 154bddb43..b3ee67018 100644
--- a/youtube_dl/extractor/cspan.py
+++ b/youtube_dl/extractor/cspan.py
@@ -60,11 +60,13 @@ class CSpanIE(InfoExtractor):
video_id = self._match_id(url)
video_type = None
webpage = self._download_webpage(url, video_id)
- matches = re.search(r'data-(prog|clip)id=\'([0-9]+)\'', webpage)
- if matches:
+ # We first look for clipid, because clipprog always appears before
+ patterns = [r'id=\'clip(%s)\'\s*value=\'([0-9]+)\'' % t for t in ('id', 'prog')]
+ results = list(filter(None, (re.search(p, webpage) for p in patterns)))
+ if results:
+ matches = results[0]
video_type, video_id = matches.groups()
- if video_type == 'prog':
- video_type = 'program'
+ video_type = 'clip' if video_type == 'id' else 'program'
else:
senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
if senate_isvp_url: