From 62a9e35ed0cc0aebb9ef13edb76394c9efd543e6 Mon Sep 17 00:00:00 2001
From: David Zhuang <david.zhuang@mail.utoronto.ca>
Date: Thu, 30 Jun 2016 02:36:07 -0400
Subject: [PATCH] [CNTV] Fix CCAV domain, Add pattern, fix #1193 ,#909 ,
 replace #1031

---
 src/you_get/common.py          | 1 +
 src/you_get/extractors/cntv.py | 8 +++++++-
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/src/you_get/common.py b/src/you_get/common.py
index 119640d5..d30397c7 100755
--- a/src/you_get/common.py
+++ b/src/you_get/common.py
@@ -9,6 +9,7 @@ SITES = {
     'bandcamp'         : 'bandcamp',
     'baomihua'         : 'baomihua',
     'bilibili'         : 'bilibili',
+    'cctv'             : 'cntv',
     'cntv'             : 'cntv',
     'cbs'              : 'cbs',
     'dailymotion'      : 'dailymotion',
diff --git a/src/you_get/extractors/cntv.py b/src/you_get/extractors/cntv.py
index cfd96e59..a32808cb 100644
--- a/src/you_get/extractors/cntv.py
+++ b/src/you_get/extractors/cntv.py
@@ -7,6 +7,7 @@ from ..common import *
 import json
 import re
 
+
 def cntv_download_by_id(id, title = None, output_dir = '.', merge = True, info_only = False):
     assert id
     info = json.loads(get_html('http://vdn.apps.cntv.cn/api/getHttpVideoInfo.do?pid=' + id))
@@ -31,7 +32,12 @@ def cntv_download_by_id(id, title = None, output_dir = '.', merge = True, info_o
 def cntv_download(url, output_dir = '.', merge = True, info_only = False, **kwargs):
     if re.match(r'http://tv\.cntv\.cn/video/(\w+)/(\w+)', url):
         id = match1(url, r'http://tv\.cntv\.cn/video/\w+/(\w+)')
-    elif re.match(r'http://\w+\.cntv\.cn/(\w+/\w+/(classpage/video/)?)?\d+/\d+\.shtml', url) or re.match(r'http://\w+.cntv.cn/(\w+/)*VIDE\d+.shtml', url):
+    elif re.match(r'http://\w+.cctv.com/\d+/\d+/\d+/\w+.shtml', url) or re.match(r'http://\w+.cntv.cn/\d+/\d+/\d+/\w+.shtml', url):
+        html = get_content(url)
+        id = match1(html, r'guid = \"(.+)\"')
+    elif re.match(r'http://\w+\.cntv\.cn/(\w+/\w+/(classpage/video/)?)?\d+/\d+\.shtml', url) or \
+         re.match(r'http://\w+.cntv.cn/(\w+/)*VIDE\d+.shtml', url) or \
+         re.match(r'http://(\w+).cntv.cn/(\w+)/classpage/video/(\d+)/(\d+).shtml', url): 
         id = r1(r'videoCenterId","(\w+)"', get_html(url))
     elif re.match(r'http://xiyou.cntv.cn/v-[\w-]+\.html', url):
         id = r1(r'http://xiyou.cntv.cn/v-([\w-]+)\.html', url)