# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\b(^(http|https|wss|ws|ftp|ftps):\/\/127[.](?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)[.](?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)[.](?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)|^(http|https|wss|ws|ftp|ftps):\/\/0.0.0.0|^(http|https|wss|ws|ftp|ftps):\/\/(10)([.](25[0-5]|2[0-4][0-9]|1[0-9]{1,2}|[0-9]{1,2})){3}|^(http|https|wss|ws|ftp|ftps):\/\/localhost|^(http|https|wss|ws|ftp|ftps):\/\/172[.](0?16|0?17|0?18|0?19|0?20|0?21|0?22|0?23|0?24|0?25|0?26|0?27|0?28|0?29|0?30|0?31)[.](?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)[.](?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)|^(http|https|wss|ws|ftp|ftps):\/\/192[.]168[.](?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)[.](?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)|^(http|https|wss|ws|ftp|ftps):\/\/169[.]254[.](?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)[.](?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?))(?:\/([789]|1?[0-9]{2}))?\b"
test_str = ("# loopback\n"
"http://127.0.0.0:80\n"
"https://127.0.0.0000 # only three digits supported here\n\n"
"# 0.0.0.0 Day\n"
"http://0.0.0.0\n"
"ws://0.0.0.0\n\n"
"# Localhost\n"
"http://localhost:25\n"
"https://localhost:8080\n"
"HTTP://LoCALhosT:99 # Case insensitive\n"
"ws://localhost:7777\n"
"wss://LOCALHOST:9200\n"
"https://google.com/blah/localhost/ # This should not alert\n\n"
"# Web Sockets\n"
"ws://localhost:2121/sockjs-node\n"
"wss://localhost:5882/\n\n"
"# FTP\n"
"ftp://192.168.0.1\n"
"ftps://127.0.0.1\n"
"ftps://localhost\n\n"
"# A (/8 CIDR)\n"
"wss://10.0.0.1/10\n"
"ws://10.255.22.33\n\n"
"# B (/12 CIDR)\n"
"http://172.17.100.155/32 # 172.16.0.0 to 172.31.255.255\n"
"http://172.15.1.1 # This should not fire\n"
"http://172.32.1.1 # This should not fire\n\n"
"# C (/16 CIDR)\n"
"https://192.168.1.1/random/path\n"
"wss://192.168.1.255\n"
"http://192.168.9.9 \n\n"
"# IPv6\n"
"http://fc00:833e:d648:f196:5c6c:1d9a:a14b:0d59 # Private IPv6\n"
"wss://fc01:67e5::6a66:34a7\n"
"ftp://FC02:5fcf:e093:bb10:ce77:b5c9::/112\n"
"http://fc03:49bd:b7c1:5685:fa0a:87e9::2/128\n"
"ws://fc04:::2 hmpf\n"
"http://0de9:b022:883f:2c3c:7dba:a184:7576:4531 # public IP addresses\n"
"https://04e4:e53b:0c2f:2990:27ad:0464:6dd3:b6b3\n"
"wss://0319:3b4a:546e:d480:4814:f885:3396:bba2\n"
"ws://5394:03f5:606f:273e:e343:d94a:610a:3f2e\n"
"ftp://63cd:ad1f:7ffb:62c7:cc17:6e20:9b59:2f7d\n\n"
"# IPV6 with brackets\n"
"http://[::1] # Private IPv6\n"
"http://[fc00:833e:d648:f196:5c6c:1d9a:a14b:0d59]\n"
"wss://[fc01:67e5::6a66:34a7]\n"
"ftp://[FC02:5fcf:e093:bb10:ce77:b5c9::]/112\n"
"http://[fc03:49bd:b7c1:5685:fa0a:87e9::2]/128\n"
"ws://[fc04:::2] hmpf\n"
"http://[0de9:b022:883f:2c3c:7dba:a184:7576:4531] # public IP addresses None of these should fire\n"
"https://[04e4:e53b:0c2f:2990:27ad:0464:6dd3:b6b3]\n"
"wss://[0319:3b4a:546e:d480:4814:f885:3396:bba2]\n"
"ws://[5394:03f5:606f:273e:e343:d94a:610a:3f2e]\n"
"ftp://[63cd:ad1f:7ffb:62c7:cc17:6e20:9b59:2f7d]\n\n"
"# More \"crap\" should not fire\n"
"ws://30.168.1.255.1\n"
"wss://127.1\n"
"https://192.168.1.256\n"
"http://-1.2.3.4\n"
"wss://1.1.1.1.\n"
"ftp://3...3\n"
"wss://255.255.255.255\n"
"ftps://0.0.0.0\n"
"wss://1.1.1.01\n"
"https://10207287.fls.doubleclick.net/\n\n"
"# decimal vs. octal mix\n"
"http://172.031.33.33\n"
"http://172.021.133.01\n\n"
"# octal - not supported here\n"
"http://0254.0021.0062.0041 # Should not fire\n\n"
"# link-local addresses IPv4\n"
"http://169.254.1.0\n"
"http://169.254.254.255\n\n"
"# link-local addresses IPv6\n"
"http://fe90:1234::/64\n"
"http://feaf:ffff::/128\n"
"http://febf:ffff:ffff:ffff:ffff:ffff:ffff:ffff\n")
matches = re.finditer(regex, test_str, re.IGNORECASE | re.MULTILINE)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html