-
Notifications
You must be signed in to change notification settings - Fork 94
/
gfwlist2dnsmasq_noipset.py
103 lines (88 loc) · 2.55 KB
/
gfwlist2dnsmasq_noipset.py
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
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
#!/usr/bin/env python
#coding=utf-8
#
# Generate a list of dnsmasq rules with ipset for gfwlist
#
# Copyright (C) 2014 http://www.shuyz.com
# Ref https://code.google.com/p/autoproxy-gfwlist/wiki/Rules
import urllib2
import re
import os
import datetime
import base64
import shutil
import ssl
mydnsip = '127.0.0.1'
mydnsport = '5300'
# Extra Domain;
EX_DOMAIN=[ \
'google.com', \
'google.com.hk', \
'google.com.tw', \
'google.com.sg', \
'google.co.jp', \
'google.co.kr', \
'blogspot.com', \
'blogspot.sg', \
'blogspot.hk', \
'blogspot.jp', \
'blogspot.kr', \
'gvt1.com', \
'gvt2.com', \
'gvt3.com', \
'1e100.net', \
'blogspot.tw' \
]
# the url of gfwlist
baseurl = 'https://raw.githubusercontent.com/gfwlist/gfwlist/master/gfwlist.txt'
# match comments/title/whitelist/ip address
comment_pattern = '^\!|\[|^@@|^\d+\.\d+\.\d+\.\d+'
domain_pattern = '(?:[\w\-]*\*[\w\-]*\.)?([\w\-]+\.[\w\.\-]+)[\/\*]*'
ip_pattern = re.compile(r'\b\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}\b')
tmpfile = '/tmp/gfwlisttmp'
# do not write to router internal flash directly
outfile = '/tmp/dnsmasq_list.conf'
rulesfile = './dnsmasq_list.conf'
fs = file(outfile, 'w')
fs.write('# gfw list ipset rules for dnsmasq\n')
fs.write('# updated on ' + datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S") + '\n')
fs.write('#\n')
print 'fetching list...'
if hasattr(ssl, '_create_unverified_context'):
ssl._create_default_https_context = ssl._create_unverified_context
content = urllib2.urlopen(baseurl, timeout=15).read().decode('base64')
# write the decoded content to file then read line by line
tfs = open(tmpfile, 'w')
tfs.write(content)
tfs.close()
tfs = open(tmpfile, 'r')
print 'page content fetched, analysis...'
# remember all blocked domains, in case of duplicate records
domainlist = []
for line in tfs.readlines():
if re.findall(comment_pattern, line):
print 'this is a comment line: ' + line
#fs.write('#' + line)
else:
domain = re.findall(domain_pattern, line)
if domain:
try:
found = domainlist.index(domain[0])
print domain[0] + ' exists.'
except ValueError:
if ip_pattern.match(domain[0]):
print 'skipping ip: ' + domain[0]
continue
print 'saving ' + domain[0]
domainlist.append(domain[0])
fs.write('server=/%s/%s#%s\n'%(domain[0],mydnsip,mydnsport))
else:
print 'no valid domain in this line: ' + line
tfs.close()
for each in EX_DOMAIN:
fs.write('server=/%s/%s#%s\n'%(each,mydnsip,mydnsport))
print 'write extra domain done'
fs.close();
print 'moving generated file to dnsmasq directory'
shutil.move(outfile, rulesfile)
print 'done!'