#! /usr/bin/python
# Kirk Hammond / 20130318 / kirkdhammond@gmail.com
# This script performs a non case-sensitive string match for content on a web page.  It's designed to detect when httpd is up, but website content is not displayed properly.
# v1.0

# Imports
import sys, re, urllib2

############################
## Start Global Variables ##

# Nagios Return Codes
UNKNOWN = -1
OK = 0
WARNING = 1
CRITICAL = 2
usage = 'usage: ./check_http_content.py <url> <string>'

# ensure there is a value for url and string, if there is not print usage and exit.  No data validity check is done, we only check that there is a value for each sys.argv needed by the script.
if len(sys.argv) >= 2:
  url = sys.argv[1] 
if len(sys.argv) == 3: 
 string = sys.argv[2]
else: 
 print usage
 sys.exit(1)

## End Global Variables ##
##########################

# Read the website into a variable
def get_content(url):
  sitetext = urllib2.urlopen(url)
  return sitetext

# Process sitetext for string match
def string_match(sitetext):
  # set status to not found, each time a match is found status is changed to 'match found'.
  status = 'match not found'
  for line in sitetext.readlines():
    if re.search(string, line, re.IGNORECASE):
      status = 'match found'
  return status

# Determine state to pass to Nagios
def nag_state(status):
  if status == 'match found':
    print 'String','"',string,'"','found on page: OK'
    sys.exit(OK)
  elif status == 'match not found':
    print 'String', string, 'not found on page: CRITICAL'
    sys.exit(CRITICAL)
  

# Main function controls the flow and order of other functions.
def main():
  sitetext = get_content(url)
  status = string_match(sitetext)
  nag_state(status)

# call main function
if __name__ == '__main__':
  main()