2014-07-18 04:14:34 +04:00
|
|
|
#!/usr/bin/env python
|
|
|
|
|
|
|
|
|
|
__all__ = ['catfun_download']
|
2014-07-18 18:28:30 +04:00
|
|
|
from .tudou import tudou_download_by_id
|
|
|
|
|
from .sina import sina_download_by_vid
|
2014-07-18 04:14:34 +04:00
|
|
|
|
|
|
|
|
from ..common import *
|
2014-07-18 18:28:30 +04:00
|
|
|
from xml.dom.minidom import *
|
2014-07-18 04:14:34 +04:00
|
|
|
|
|
|
|
|
def parse_item(item):
|
|
|
|
|
if item["type"]=="youku":
|
|
|
|
|
page=get_content("http://www.catfun.tv/index.php?m=catfun&c=catfun_video&a=get_youku_video_info&youku_id="+item["vid"])
|
2014-07-18 18:28:30 +04:00
|
|
|
dom=parseString(page)
|
|
|
|
|
ext=dom.getElementsByTagName("format")[0].firstChild.nodeValue;
|
|
|
|
|
size=0
|
|
|
|
|
urls=[]
|
|
|
|
|
for i in dom.getElementsByTagName("durl"):
|
|
|
|
|
urls.append(i.getElementsByTagName("url")[0].firstChild.nodeValue)
|
|
|
|
|
size+=int(i.getElementsByTagName("size")[0].firstChild.nodeValue);
|
|
|
|
|
return urls,ext,size
|
2014-07-18 04:14:34 +04:00
|
|
|
pass
|
|
|
|
|
|
|
|
|
|
elif item["type"]=="qq":
|
|
|
|
|
page=get_content("http://www.catfun.tv/index.php?m=catfun&c=catfun_video&a=get_qq_video_info&qq_id="+item["vid"])
|
2014-07-18 18:28:30 +04:00
|
|
|
dom=parseString(page)
|
|
|
|
|
size=0
|
|
|
|
|
urls=[]
|
|
|
|
|
for i in dom.getElementsByTagName("durl"):
|
|
|
|
|
url=i.getElementsByTagName("url")[0].firstChild.nodeValue
|
|
|
|
|
urls.append(url)
|
|
|
|
|
vtype,ext,_size=url_info(url)
|
|
|
|
|
size+=_size
|
|
|
|
|
return urls,ext,size
|
2014-07-18 04:14:34 +04:00
|
|
|
pass
|
|
|
|
|
|
|
|
|
|
elif item["type"]=="sina":
|
|
|
|
|
page=get_content("http://www.catfun.tv/index.php?m=catfun&c=catfun_video&a=get_sina_video_info&sina_id=" + item["vid"])
|
2014-07-18 18:28:30 +04:00
|
|
|
try:
|
|
|
|
|
dom=parseString(page)
|
|
|
|
|
except:
|
|
|
|
|
#refresh page encountered
|
|
|
|
|
page=get_content(match1(page,r'url=(.+?)"'))
|
|
|
|
|
dom=parseString(page)
|
|
|
|
|
size=0
|
|
|
|
|
urls=[]
|
|
|
|
|
for i in dom.getElementsByTagName("durl"):
|
|
|
|
|
url=i.getElementsByTagName("url")[0].firstChild.nodeValue
|
|
|
|
|
urls.append(url)
|
|
|
|
|
vtype,ext,_size=url_info(url)
|
|
|
|
|
if not ext:
|
|
|
|
|
ext=match1(url,r'\.(\w+?)\?')
|
|
|
|
|
size+=_size
|
|
|
|
|
#sina's result does not contains content-type
|
|
|
|
|
return urls,ext,size
|
2014-07-18 04:14:34 +04:00
|
|
|
pass
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def catfun_download(url, output_dir = '.', merge = True, info_only = False):
|
|
|
|
|
# html=get_content(url)
|
|
|
|
|
title=match1(get_content(url),r'<h1 class="title">(.+?)</h1>')
|
|
|
|
|
vid=match1(url,r"v\d+/cat(\d+)")
|
|
|
|
|
j=json.loads(get_content("http://www.catfun.tv/index.php?m=catfun&c=catfun_video&a=get_video&modelid=11&id={}".format(vid)))
|
|
|
|
|
for item in j:
|
2014-07-18 18:28:30 +04:00
|
|
|
if item["name"]!="\u672a\u547d\u540d1":
|
|
|
|
|
t=title+"-"+item["name"]
|
|
|
|
|
else:
|
|
|
|
|
t=title
|
|
|
|
|
if item["type"]=="tudou":
|
|
|
|
|
tudou_download_by_id(item["vid"], title, output_dir, merge, info_only)
|
|
|
|
|
|
|
|
|
|
else:
|
|
|
|
|
urls,ext,size=parse_item(item)
|
|
|
|
|
|
|
|
|
|
download_urls(urls,t,ext,size,output_dir)
|
2014-07-18 04:14:34 +04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
site_info = "catfun.com"
|
|
|
|
|
download = catfun_download
|
|
|
|
|
download_playlist = playlist_not_supported('catfun')
|
