forked from EFForg/https-everywhere
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathchromium-preloads.py
More file actions
95 lines (73 loc) · 3.18 KB
/
Copy pathchromium-preloads.py
File metadata and controls
95 lines (73 loc) · 3.18 KB
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
#!/usr/bin/env python2.7
# autogenerate sample versions of rules from Chromium browser's HSTS
# preload list (in the from-preloads/ directory)
import urllib.request, urllib.error, urllib.parse, re, glob, os
from lxml import etree
preloads = urllib.request.urlopen("https://src.chromium.org/viewvc/chrome/trunk/src/net/http/transport_security_state_static.h?content-type=text%2Fplain").read()
preloads = preloads.decode('utf-8')
def escape(s):
return re.sub("\.", "\\.", s)
def get_targets():
"""extract unique targets from the set of https-e rulesets"""
ruledir = "src/chrome/content/rules/"
rules = [ruledir+fi for fi in os.listdir(ruledir) if fi.endswith(".xml")]
targets = set()
for fi in rules:
tree = etree.parse(fi)
targets.update(tree.xpath("/ruleset/target/@host"))
return targets
def is_dup(rule, targets):
"""find if a rule is duplicated in the existing https-e rulesets"""
if rule.lower() in map(lambda x: x.lower(), targets):
return True
else:
wildcards = filter(lambda x: '*' in x, targets)
for url in wildcards:
url = re.escape(url)
url = re.sub(r'\\\*', '.*', url) # handle wildcards
url = '^'+url+'$'
if re.compile(url, re.I).search(rule):
return True
else:
continue
return False
def make_rule(name, hosts):
output = """<!-- This rule was automatically generated based on an HSTS
preload rule in the Chromium browser. See
https://src.chromium.org/viewvc/chrome/trunk/src/net/http/transport_security_state_static.h
for the list of preloads. Sites are added to the Chromium HSTS
preload list on request from their administrators, so HTTPS should
work properly everywhere on this site.
Because Chromium and derived browsers automatically force HTTPS for
every access to this site, this rule applies only to Firefox. -->\n"""
output += '<ruleset name="%s" platform="firefox">\n' % name.capitalize()
for h in hosts:
output += '<target host="%s" />\n' % h
output += "\n"
for h in hosts:
output += '<securecookie host="^%s$" name=".+" />\n' % escape(h)
output += "\n"
for h in hosts:
output += '<rule from="^http://%s/" to="https://%s/" />\n' % (escape(h), h)
output += "</ruleset>\n"
open("from-preloads/%s.xml" % name.capitalize(), "w").write(output)
t = re.compile('", true')
preloads = list(filter(t.search,preloads.split("\n")))
preloads = [x.split('"')[1] for x in preloads]
preloads = [re.sub('\\\\[0-9]*', '.', x) for x in preloads]
preloads = [re.sub('^\.', '', x) for x in preloads]
print("Found %d targets total in HSTS preloads list" % len(preloads))
#rules = [open(x).read() for x in glob.glob("src/chrome/content/rules/*.xml")]
targets = get_targets()
d = {}
for x in preloads:
if is_dup(x, targets):
print("Ignored existing domain", x)
continue
domain = ".".join(x.split(".")[-2:])
d.setdefault(domain, []).append(x)
if not os.access("from-preloads", 0):
os.mkdir("from-preloads")
for k in d:
make_rule(k, d[k])
print("Please examine %d new rules in from-preloads/ directory." % len(d))