From 407ae733ab24dbe4fdbd5b996aef6438f16834a2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?=
<jaime.marquinez.ferrandiz@gmail.com>
Date: Wed, 22 Jan 2014 11:06:03 +0100
Subject: [PATCH] =?UTF-8?q?[cspan]=20Make=20=E2=80=98www=E2=80=99=20option?=
=?UTF-8?q?al=20and=20improve=20the=20regex=20for=20extracting=20the=20id?=
=?UTF-8?q?=20(fixes=20#2194)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
---
youtube_dl/extractor/cspan.py | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py
index a2cbd4d8d5..521bbdee08 100644
--- a/youtube_dl/extractor/cspan.py
+++ b/youtube_dl/extractor/cspan.py
@@ -10,7 +10,7 @@ from ..utils import (
class CSpanIE(InfoExtractor):
- _VALID_URL = r'http://www\.c-spanvideo\.org/program/(.*)'
+ _VALID_URL = r'http://(?:www\.)?c-spanvideo\.org/program/(?P<name>.*)'
IE_DESC = 'C-SPAN'
_TEST = {
'url': 'http://www.c-spanvideo.org/program/HolderonV',
@@ -24,9 +24,9 @@ class CSpanIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- prog_name = mobj.group(1)
+ prog_name = mobj.group('name')
webpage = self._download_webpage(url, prog_name)
- video_id = self._search_regex(r'programid=(.*?)&', webpage, 'video id')
+ video_id = self._search_regex(r'prog(?:ram)?id=(.*?)&', webpage, 'video id')
title = self._html_search_regex(
r'<!-- title -->\n\s*<h1[^>]*>(.*?)</h1>', webpage, 'title')