ATG Dynamo console web scraper

getSched.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

__author__ = 'Jason V. Orona'
__version__ = 'prototype'

'''
Example:

./getSched.py --server=myserver --port=8080

==== Scheduled services for myserver@8080 ====

|job_id|last_time|next_time|times_run|description|thread_method|repeating|schedule_type|schedule|
|28|Wed Mar 05 12:30:34 CST 2014|Wed Mar 05 12:31:34 CST 2014|356|Updates index of all documents in the Nucleus docroot|reused|true|atg.service.scheduler.PeriodicSchedule|every 1 minute in 1 minute without catch up|
|31|Wed Mar 05 12:30:36 CST 2014|Wed Mar 05 12:31:36 CST 2014|357|Monitors Request Threads|reused|true|atg.service.scheduler.PeriodicSchedule|every 1 minute without catch up|

'''

# Built-in modules
import urllib2
import base64
import re

# Third-party modules
import argparse
from BeautifulSoup import BeautifulSoup

# Global variables
username = 'supersecretuser'
password = 'supersecretpass'

# Functions specific to this program

def get_args():
    '''
    This function parses and return arguments passed in 
    '''
    # Assign description to the help doc
    parser = argparse.ArgumentParser(
        description='Script retrieves schedules from dynamo console')
    # Add arguments
    parser.add_argument(
        '-s', '--server', type=str, help='Server name', required=True)
    parser.add_argument(
        '-p', '--port', type=str, help='Port number', required=True, nargs='+')
    parser.add_argument(
        '-k', '--keyword', type=str, help='Keyword search', required=False,
        default=None)
    # Array for all arguments passed to script
    args = parser.parse_args()
    # Assign args to variables
    server = args.server
    port = args.port[0].split(",")
    keyword = args.keyword 
    # Return all variable values
    return server, port, keyword

def get_http(username, password, url):
    ''' 
    Capture web page request and format
    '''
    try:
        request = urllib2.Request(url)
        base64string = base64.encodestring(
            '%s:%s' % (username, password)).replace('\n', '')
        request.add_header("Authorization", "Basic %s" % base64string)
        soup = BeautifulSoup(urllib2.urlopen(request))
        #sched = soup('table')[0].prettify()
        table = soup.find('table')
        # Format html table into a pipe delimited table
        for row in table.findAll('tr')[1:]:
            col = row.findAll('td')
            job_id = col[1].string
            name = col[2].string
            last_time = col[3].string
            next_time = col[4].string
            times_run = col[5].string
            #source = col[6]    
            #destination = col[7].string
            description = col[8].string
            thread_method = col[9].string
            repeating = col[10].string
            schedule_type = col[11].string
            schedule = col[12].string
            record = (
            job_id, last_time, next_time, times_run, description, 
            thread_method, repeating, schedule_type, schedule)
            line = ("|".join(record))
            print "|%s|" % line
    except urllib2.HTTPError, e:
        print e.headers
        print e.headers.in_key('WWW-Authenticate')

#def search(keyword):
 #   for line in resp.readlines():
  #      if re.search(keyword, line, re.I):
   #         print line

def main():
    '''
    Main program 
    '''
    # Get arguments
    server, port, keyword = get_args()
    # Loop through ports list and output scheduled services
    for p in port:
        url = 'http://%s:%s/dyn/admin/nucleus/atg/dynamo/service/Scheduler/' % ( 
        server, p)
        print "\n==== Scheduled services for port %s@%s ====\n" % (server, p) 
        print 'job_id|last_time|next_time|times_run|description|thread_method|repeating|schedule_type|schedule|'
        get_http(username, password, url) 
        print ""

#       if keyword is not None:
        #       return search(keyword)

if __name__ == '__main__':
    main()