复制代码 代码如下:
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!!")
输出文件：
domains.txt ： kingnic.com 据当天释放的 域名；
result.txt ： 符合过滤条件的域名；
log输出：
复制代码 代码如下:
all: 55500
len not in [4,0] : 55019
contain '-' : 32
remain: 449
finished!!
对 后缀、长度和有无“-”过滤，过滤条件有点少，其它以后如有需要再加。