代碼如下：

import sys, urllib

import datetime,time

def getDate():

strday=datetime.datetime.now().__str__()

strday=strday.split()[0]

return strday

#url = "http://www.kingnic.com/list/2009-06-16.txt"

def getUrl(dateStr=None):

baseUrl ="http://www.kingnic.com/list/"

if dateStr:

return baseUrl+dateStr+".txt"

thisDate = getDate();

if not thisDate:

print "Error Date!"

return None;

url = baseUrl+thisDate+".txt"

return url

def getSource(url):

source = urllib.urlopen(url).read()

return source

def save(source,filename="domains.txt"):

fp = open(filename,"w")

fp.write(source)

fp.close()

return True;

def loadList(fileName="domains.txt"):

fp = open("domains.txt","r")

source = fp.readlines()

fp.close()

return source;

def getPrefix(domain):

return domain.split('.')[0]

def getPostfix(domain):

return domain.split('.')[1]

def hasMidLine(domain):

if '-' in domain:

return True

else:

return False

def parser(domains):

max =4

min =0

keyword =('sky','see','job')

result=[]

len_num =0;

mid_line_num =0;

for domain in domains:

prefix = getPrefix(domain)

postfix = getPostfix(domain)

domainlen = len(prefix)

if (domainlen < min) or (domainlen > max):

len_num +=1

continue

if hasMidLine(prefix):

mid_line_num +=1

continue

result.append(domain)

print " log : \n"

print "all: \t",len(domains)

print "len not in [%s,%s] \t: %s"%(max,min,len_num)

print "contain '-' :\t",mid_line_num

print "remain:\t",len(result)

return result;

if __name__ == "__main__":

url = getUrl()

source = getSource(url)

save(source)

domains =loadList()

result = parser(domains)

save("".join(result),"result.txt")

print("\n\n\nfinished!!")

輸出文件：

domains.txt ： kingnic.com 據(jù)當(dāng)天釋放的 域名；

result.txt ： 符合過濾條件的域名；

log輸出：

all: 55500

len not in [4,0] : 55019

contain '-' : 32

remain: 449

finished!!

對 后綴、長度和有無“-”過濾，過濾條件有點少，其它以后如有需要再加。

總結(jié)

以上是生活随笔為你收集整理的python源码分析工具_python 域名分析工具实现代码的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。