Source code is as follows: Save into Utf-8 bd.py file
Copy Code code as follows:
#!/usr/bin/env python
#-*-Coding:utf-8-*-
Import Sys
Import Urllib, Urllib2
Import re
def Baidu (W):
Url= "http://www.baidu.com/s?"
Values = {
"W": W.encode (' gbk ', ' ignore ')
}
data = Urllib.urlencode (values)
Newurl = URL + data
Response = Urllib2.urlopen (Newurl)
The_page = Response.read (). Decode (' GBK ', ' ignore ')
Return The_page
def ana (data,mysite):
o = Re.compile ("Href=\" (. +?) \"")
f = o.findall (data)
line = 1
For FF in F:
If not Re.search ("Baidu", FF) and not Re.search ("^s\?", FF) and Re.search ("^http:\/\/", FF):
If Re.search (MYSITE,FF):
Print "*", line, FF
Else
Print line, FF
Line + + 1
if __name__ = = "__main__":
MySite = sys.argv[2]
data = Baidu (Sys.argv[1].decode (' Utf-8 '))
Ana (Data,mysite)
Usage python bd.py "keywords" my Domain name section:
Cases:
Copy Code code as follows:
Python bd.py "vbs" "Jb51.net"