NAME

Simple::IPInfo - Get IP/IPList Info (location, as number, etc)

给定IP列表，查对应的区域信息，或AS号

SYNOPSIS

use Simple::IPInfo;
use Data::Dumper;
use utf8;

my $rr_loc = get_ip_loc([ [ '202.38.64.10'], ['202.96.196.33'] ]);
my $inet_rr_loc = get_ip_loc([ ['3395339297'], ['3391504394'] ]);
print Dumper($rr_loc, $inet_rr_loc);

my $rr_asn = get_ip_as([ [ '202.38.64.10'], ['202.96.196.33'] ], reserve_inet=>1);
print Dumper($rr_asn);

my $arr = [ [qw/202.38.64.10 xxx/], [qw/8.8.8.8 yyy/], ];
my $r = get_ipinfo(
    $arr, 
    i => 0,
    write_file => '02.ip_loc.csv', 
    sep => ',', 
    charset         => 'utf8',
    return_arrayref => 1,
    ipinfo_names    => [qw/country area isp country_code area_code isp_code/],
    write_head => [qw/ip some country area isp country_code area_code isp_code/ ], 
);
print Dumper($r);

DESCRIPTION

default ip as data: ftp://routeviews.org/dnszones/originas.bz2

default ip location data: http://ip.taobao.com

use iso 3166 country_code, subdivision_1 code, isp shortcut name

METHOD

get_ip_loc

get ip location, with country, area, isp, country_code, area_code, isp_code

返回IP区域信息，包括国家、省份、运营商，及其英文iso3166编号

get_ip_as

get ip as number

返回IP的AS号

get_ipinfo

get ip info, with specified ipinfo_file

iterate_ipinfo

add ipinfo to inet-sorted arrayref, for large file

Note that, lines are inet-sorted

use Simple::IPInfo;
use Data::Dumper;

my $arr = [ [qw/8.8.8.8 yyy/], [qw/202.38.64.10 xxx/], ];

my $r = iterate_ipinfo(
    $arr,  # or some big inet-sorted file : $big_inet_sorted_csv, 
    i => 0,
    write_file => '02.ip_loc.csv', 
    sep => ',', 
    charset         => 'utf8',
    return_arrayref => 1,
    ipinfo_names    => [qw/country area isp country_code area_code isp_code/],
    write_head => [qw/ip some country area isp country_code area_code isp_code/ ], 
);
print Dumper($r);

my $inet_arr = [['3391504394' , 'ceshi'], [ '3395339297', 'test'], ];
my $r = iterate_ipinfo(
    $inet_arr, 
    i=>0,
    write_file => '02.inet_loc.csv', 
    sep => ',', 
    charset         => 'utf8',
    return_arrayref => 1,
    ipinfo_names    => [qw/country area isp country_code area_code isp_code/],
    write_head => [qw/inet some country area isp country_code area_code isp_code/ ], 
);
print Dumper($r);

ATTR

DEBUG

set $Simple::IPInfo::DEBUG = 1 for more details

BIN

csv is in xt/ directory

add_inet.pl

$ add_inet.pl -f 02.ip_raw.csv -i 0 -d 02.ip_inet.csv
$ sort -t, -k3 -n 02.ip_inet.csv > 02.ip_inet.sort.csv

add_ip_info.pl

$ add_ip_info.pl -f 02.ip_inet.sort.csv -d 02.add_ip_info.csv -i 0 -t loc

-f : source file 源文件, inet-sorted
-d : dest file 目标文件
-i : ip is in cloumn x, ip在第x列
-H : skip head or not，default is 0 (not skip) 默认不跳过首行
-t : loc or as, default is loc；添加信息类型，默认是加loc信息，也可指定为as
-s : sep character, default is ',' 默认分隔符为逗号

make_inet_from_cidr.pl

make_inet_from_cidr.pl [src_file] [dst_file]

$ pip install csvkit
$ cd xt/data/

$ csvcut -c network,isp,autonomous_system_number isp_cidr.csv > isp_cidr.csv.cut
$ make_inet_from_cidr.pl isp_cidr.csv.cut isp_inet.csv

$ csvcut -c network,geoname_id city_blocks_ipv4.csv > city_blocks_ipv4.csv.cut
$ csvcut -c geoname_id,country_iso_code,subdivision_1_iso_code,country_name,subdivision_1_name city_locations_zh-CN.csv > city_locations_zh-CN.csv.cut
$ csvjoin -c geoname_id city_blocks_ipv4.csv.cut city_locations_zh-CN.csv.cut |csvcut -C geoname_id > city_cidr.csv
$ make_inet_from_cidr.pl city_cidr.csv city_inet.csv

refine_inet.pl

refine_inet.pl [src_file] [dst_file]

src_file's inet is sorted by csvsort

$ csvsort isp_inet.csv > isp_inet.csv.sort
$ refine_inet.pl isp_inet.csv.sort isp_inet.csv.sort.refine

$ csvsort city_inet.csv > city_inet.csv.sort
$ refine_inet.pl city_inet.csv.sort city_inet.csv.sort.refine

merge_inet.pl

merge_inet.pl [src_inet_file1] [src_inet_file2] [dst_merge_file]

$ merge_inet.pl city_inet.csv.sort.refine isp_inet.csv.sort.refine merge_city_isp_inet.csv

get_ipinfo.pl

get_ipinfo.pl [ip]

$ get_ipinfo.pl 202.38.64.10
202.38.64.10,3391504394,中国,安徽,教育,CN,34,EDU,4538

XBIN

install: curl bunzip2 tar

get ip as data from routeviews.org

$ perl gen_inet_as.pl inet_as.csv

get ip loc from taobao

1) init data dir, and send ip query to taobao

ask_ip_loc_init.pl
ask_ip_loc.pl

2) merge data/*.csv to ip_loc_taobao.csv , tidy it, update old ip_loc.csv

$ perl ip_loc_taobao.pl
$ perl ip_loc_tidy.pl ip_loc_taobao.csv ip_loc_taobao.tidy.csv
$ perl ip_loc_update.pl ip_loc.csv ip_loc_taobao.tidy.csv ip_loc_update.csv

3) guess loc from as, update , write new ip_loc.csv

$ perl ip_loc_from_as.pl ip_loc_update.csv ip_loc_from_as.csv
$ perl ip_loc_update.pl ip_loc_update.csv ip_loc_from_as.csv ip_loc.csv

4) map into inet file, and refine inet_loc_src.csv

$ make_inet_from_cidr.pl ip_loc.csv inet_loc_raw.csv 'ip,country,area,isp'
$ refine_inet.pl inet_loc_raw.csv inet_loc_src.csv

5) add iso_3166 code for inet_loc_src.csv, use merge_file.pl from SimpleR::Reshape

inet_loc_src.csv : s, e , country, area, isp

inet_loc.csv : s, e , country, area, isp , country_code, area_code, isp_code

$ merge_file.pl -f country.csv -k 1 -v 0 -F inet_loc_src.csv -K 2 -o inet_loc.csv.c
$ merge_file.pl -f country_area.csv -k 0,3 -v 1 -F inet_loc.csv.c -K 5,3 -o inet_loc.csv.p
$ merge_file.pl -f country_isp.csv -k 0,3 -v 1 -F inet_loc.csv.p -K 5,4 -o inet_loc.csv

AUTHOR

Abby Pan <abbypan@gmail.com>

Thanks to Gabor Szabo <szabgab@gmail.com>, Neil Bowers <neil@bowers.com>