Scrape OpnSense DHCP Leases Status Page and Export Results as List

scrape_opnsense_dhcp_leases.py

#!/usr/bin/env python3

#
# This python script provides a function to query the opnSense (v21.3 - v23.1.x) dhcp leases status page and 
# return a list of tuples including ip, hostname, and mac address. This script will not work with version 23.7.x+ 
# due to changes in the DHCP lease page.
# See comment from dheldt on modified version that works using api searchLeases page. 
# To use the original script, ensure LXML is installed via package manager or via pip. 
#
# 27-Mar-2021 - Original release
# 17-Jul-2022 - Fix url in scrape function. Add error trapping for case where user/pass are not set up correctly.
# 24-Sep-2023 - Add note about 23.7.x incompatibility.
#


import sys
import requests
from lxml import html
import re

url  = "http://192.168.1.1/status_dhcp_leases.php" #change url to match your opnSense machine address. Note http or https!
user = 'your_username'  #Username for opnSense login (default is 'root')
password = 'your_password' #Password for opnSense login

def scrape_opnsense_dhcp(url, user, password):
   ip = []
   mac = []
   hostname = []

   s = requests.session()
   r = s.get(url,verify = False)

   matchme = '"X-CSRFToken", "(.*)" \);'
   csrf = re.search(matchme,str(r.text))

   payload = {
'login' : 'Login',
'usernamefld' : user,
'passwordfld' : password
}

   r = s.post(url,data=payload,verify = False,headers={"X-CSRFToken":csrf.group(1)})
   r = s.get(url,verify = False)
   tree = html.fromstring(r.content)
   tr_elements = tree.xpath('//tr')
   try:
      headers = [header.text for header in tr_elements[0]]
   except IndexError:
      print("Error retrieving lease list. Are you sure username and password were set up in script?")
      quit()

   ip.extend(tree.xpath('//table[@class="table table-striped"]//tbody//tr//td[' + str(headers.index('IP address') + 1) +']//text()'))

   for node in tree.xpath('//table[@class="table table-striped"]//tbody//tr//td['+ str(headers.index('MAC address') + 1) +']'):
      if bool(re.search(r'([0-9a-f]{2}(?::[0-9a-f]{2}){5})', node.text)):
         mac.append(node.text)

   for node in tree.xpath('//table[@class="table table-striped"]//tbody//tr//td['+ str(headers.index('Hostname') + 1) +']'):
      if node.text is None:
         hostname.append('no_hostname')
      else:
         hostname.append(node.text)

   for i in range(len(mac)):
      mac[i] = mac[i].strip()

   return(list(zip(ip, mac, hostname)))

if __name__ == "__main__":     
    dhcp_list = scrape_opnsense_dhcp(url, user, password)

    for entry in dhcp_list:
            print(entry)

Thank you for working through this!

It turns out it is simpler to set up an api access key as described here:
https://docs.opnsense.org/development/how-tos/api.html.

The code to retrieve the leases can then simply be reduced to a single GET request.

import json
import requests

# define endpoint and credentials
api_key = '---------'   #use your unique key
api_secret = '-----------------'  #use your unique secret
url = 'http://opnsense.home/api/dhcpv4/leases/searchlease'
r = requests.get(url,
                 verify='OPNsense.pem',
                 auth=(api_key, api_secret))

if r.status_code == 200:
    return r.json()
else:
    print ('Connection / Authentication issue, response received:')