import re
regex = re.compile(r"(?i)(%(25){0,}20|\s)*(%(25){0,}24|\$)(%(25){0,}20|\s)*(%(25){0,}7B|{)(%(25){0,}20|\s)*(%(25){0,}(6A|4A)|J)(%(25){0,}(6E|4E)|N)(%(25){0,}(64|44)|D)(%(25){0,}(69|49)|I)(%(25){0,}20|\s)*(%(25){0,}3A|:)[\w\%]+(%(25){1,}3A|:)(%(25){1,}2F|\/)[^\n]+", flags=re.MULTILINE)
test_str = ("Sample Log4j strings:\n"
"${JNDI:LDAP://\n"
"${JNDI:LDAPS://\n"
"${JNDI:RMI://\n"
"${JNDI:DNS://\n"
"${JNDI:NIS://\n"
"${JNDI:IIOP://\n"
"${JNDI:CORBA://\n"
"${JNDI:NDS://\n"
"${JNDI:HTTPS://\n"
"${JNDI:HTTP://\n"
" $ { JNDI :LDAPS://\n"
" $ { JNDI :LDAPS://\n"
"${jNDi:l%252564ap://\n\n"
"JNDI = %6A%6E%64%69\n"
"jndi = %4A%4E%44%49\n\n"
"Multi-encoding log4j strings (without spaces):\n"
"%24%7B%6A%6E%64%69%3A%2F\n"
"%2524%257B%256A%256E%2564%2569%253A\n"
"%2524%257B%256A%256E%2564%2569%253A%252F\n"
"%252524%25257B%25256A%25256E%252564%252569%25253A%25252F\n\n"
"Multi-URL Encoded string characters:\n"
"(?i)\n"
"(%(25){0,}20|\\s)*\n"
"(%(25){0,}24|$)\n"
"(%(25){0,}20|\\s)*\n"
"(%(25){0,}7B|{)\n"
"(%(25){0,}20|\\s)*\n"
"(%(25){0,}(6A|4A)|J)\n"
"(%(25){0,}(6E|4E)|N)\n"
"(%(25){0,}(64|44)|D)\n"
"(%(25){0,}(69|49)|I)\n"
"(%(25){0,}20|\\s)*\n"
"(%(25){0,}3A|:)\n"
"(%(25){0,}2F|\\/)\n"
"[\\w\\%]+\n"
"(%(25){0,}3A|:)\n"
"(%(25){0,}2F|\\/)\n")
matches = regex.finditer(test_str)
for match_num, match in enumerate(matches, start=1):
print(f"Match {match_num} was found at {match.start()}-{match.end()}: {match.group()}")
for group_num, group in enumerate(match.groups(), start=1):
print(f"Group {group_num} found at {match.start(group_num)}-{match.end(group_num)}: {group}")
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