Created
May 17, 2011 03:39
-
-
Save scturtle/975898 to your computer and use it in GitHub Desktop.
get song urls from baidu
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# coding: utf-8 | |
import sys,os,urllib2,xml | |
from xml.dom import minidom | |
lc = sys.getfilesystemencoding() | |
baseurl0="http://box.zhangmen.baidu.com/x?op=7&mode=1&count=1&listid=&title=%s" | |
baseurl1="http://box.zhangmen.baidu.com/x?op=12&count=1&mtype=4&title=%s" | |
song=raw_input('Song name:').decode(lc).encode('gbk') | |
data=urllib2.urlopen(baseurl0 % urllib2.quote(song)) | |
data=data.read().replace('gb2312','utf-8').decode('gbk').encode('utf8') | |
doc=minidom.parseString(data) # 丫真挑剔 | |
names=doc.getElementsByTagName('name') | |
count=0 | |
for i in names: | |
print count,i.firstChild.nodeValue.replace('$',' ').encode(lc) | |
count+=1 | |
choice=int(raw_input('\nyour choice:')) | |
data=urllib2.urlopen(baseurl1 % urllib2.quote(names[choice].firstChild.nodeValue.encode('gbk'))) | |
data=data.read().replace('gb2312','utf-8').decode('gbk').encode('utf8') | |
doc=minidom.parseString(data) | |
urls=doc.getElementsByTagName('url') | |
print '\n song urls:' | |
for i in urls: | |
t=i.childNodes | |
pos=t[0].firstChild.nodeValue.rfind('/') | |
prefix=t[0].firstChild.nodeValue[0:pos+1] | |
suffix=t[1].firstChild.nodeValue#.split('?')[0] | |
print prefix+suffix | |
raw_input('\nenter to exit ...') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment