1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
|
'''
IP段匹配
'''
import ipaddress as ipaddr
import pandas as pd
def makecidr(DATAframe):
cidr=pd.DataFrame()
for i in range(DATAframe.shape[0]):
if ":" in DATAframe.loc[i,"start_ip"]:
start_ip=ipaddr.ip_address(DATAframe.loc[i,"start_ip"])
end_ip=ipaddr.ip_address(DATAframe.loc[i,"end_ip"])
ipcidr=ipaddr.summarize_address_range(start_ip,end_ip)
for ips in ipcidr:
cidr = cidr.append([[ips]])
return cidr
def matchIP(ip,cidrs):
for c in cidrs.keys():
for j in range(cidrs[c].shape[0]):
if (ipaddr.IPv6Address(ip) in ipaddr.IPv6Network(cidrs[c].iloc[j, 0])):
return str(c)
if __name__=="__main__":
# 读取原始数据
cidrs=[]
dx = pd.read_excel("./res_data/IPrange/山东电信.xlsx", names=["time", "start_ip", "end_ip", "organization", "company"])
yd = pd.read_excel("./res_data/IPrange/山东移动.xlsx", names=["time", "start_ip", "end_ip", "organization", "company"])
lt = pd.read_excel("./res_data/IPrange/山东联通.xlsx", names=["time", "start_ip", "end_ip", "organization", "company"])
ips=pd.read_csv("./result/v6/allv6dns.csv",header=0)
# dx_cidr=makecidr(dx)
# yd_cidr=makecidr(yd)
# lt_cidr=makecidr(lt)
cidrs={"dx":makecidr(dx),"yd":makecidr(yd),"lt":makecidr(lt)}
ips["company"]=ips["IPv6"].map(lambda x:matchIP(x,cidrs))
ips_n=pd.pivot_table(ips,values=["Count"],index=["IPv6"],aggfunc=sum)
ips_c=ips.drop_duplicates(subset=["IPv6"],keep="first")
ips_L=ips_n.merge(ips_c.loc[:,["IPv6","company"]],how="left",on="IPv6")
ips_L.to_csv("./result/v6/v6DNSs.csv",index=False)
# for i in range(ips.shape[0]):
|
