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 :
"
print "all: ",len(domains)
print "len not in [%s,%s] : %s"%(max,min,len_num)
print "contain '-' : ",mid_line_num
print "remain: ",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("
finished!!")
