#!/bin/python

###--# Imports #--###
import re, httplib

from sys import argv,exit


###--# Constants #--###
MODE_FILE   = 0 # Read data from file
MODE_URL    = 1 # Read data from a website
MODE_GROUP  = 2 # Read data from Furc's site form specific groupname

PHASE_LINKS = 0 # Group link acquirement phase
PHASE_NAMES = 1 # Group memeber acquirement phase

GRP_ASSOC   = 0 # Associate in charge
GRP_HEAD    = 1 # Group head
GRP_ELDER   = 2 # Group elder
GRP_MEMBER  = 3 # Group member


###--# Checking Syntax #--###
if len(argv) < 2:
    print 'Syntax: %s [f|u|g] <file/url/groupname>'
    exit(1)
elif len(argv) < 3:
    mode = MODE_GROUP
    data = argv[1]
else:
    if argv[1][0] == 'f':
	mode = MODE_FILE
    elif argv[1][0] == 'u':
	mode = MODE_URL
    else:
	mode = MODE_GROUP

    data = argv[2]


###--# Regular Expressions #--###
matchGroupURL = re.compile( '<A HREF=\'(.+)\'>([^<]*)</A>' )
matchName     = re.compile( '<TD[^>]*>([^<]+)</TD>' )


###--# Variable Initialization #--###
useragent   = 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)'
rooturl     = 'http://furcadia.com/services/beekins/listbeekins.php4'
groups      = []            # Group names and links
names       = [[],[],[],[]] # Name list for each group, divided into access level
nNames      = 0             # Total amount of names
defTitle    = 'Furcadia: Beekin Volunteer Listing'
group       = 0
phase       = PHASE_LINKS


###--# Buffer Storage #--###
print '---++ Beekin List Parser ++---\n'
print '[+] Acquiring beekin list...'

if mode == MODE_FILE:
    buffer = file( data, 'r' ).read()
elif mode == MODE_URL:
    url = data
elif mode == MODE_GROUP:
    url = rooturl + '?group=' + data.lower()
else:
    print '[E] Unknown acquisition mode - ' + str(mode)
    exit(2)

if mode == MODE_URL or mode == MODE_GROUP:
    # Figure out whether we start from beginning or after http://
    if url[:7] == 'http://':
	idx = 7
    else:
	idx = 0

    # Set the address we're connecting to
    try:
	addr = url[idx:url[7:].index( '/' )+7]
    except:
	addr = url[idx:]

    print '[+] Connecting to %s...' % addr

    conn = httplib.HTTPConnection( addr )
    conn.connect    ()
    conn.putrequest ( 'GET', url )
    conn.putheader  ( 'User-Agent', useragent )
    conn.endheaders ()

    print '[+] Getting data...'

    ret = conn.getresponse()
    
    if ret.status != 200:
	print '[E] Bad status:', str(ret.status), ret.reason
	exit(3)

    buffer = ret.read()
    ret.close()
    del(ret)
    del(conn)


###--# Getting Site Title #--###
title = re.findall( '<title>(.*)</title>', buffer )[0]

if title != defTitle:
    print '[!] WARNING: Title does not match the common one. Current: ' + title

print '[+] Title: ' + title


###--# Parsing Buffer #--###
for line in buffer.split('\n'):

    if phase == PHASE_LINKS:
	# Did we leave the phase yet? #
	if line[:7] == '<P><BR>':
	    phase = PHASE_NAMES
	    continue
	# Is it a group link? #
	else:
	    ret = re.findall( matchGroupURL, line )
	    if ret != []:
#		print '[D] New Group: %s (%s)' % ( ret[0][0],ret[0][1] )
		groups.append( ret[0] )
    
    elif phase == PHASE_NAMES:
	# Is it a name? #
	ret = re.findall( matchName, line )
	if ret != [] and ret[0] != '&nbsp;':
#	    print '[D] New Name: ' + ret[0]
	    names[group].append( ret[0] )
	    nNames += 1
	    continue
	# Is it a new group marker? #
	elif line[:7] == '<P><BR>':
#	    print '[D] Switching groups!'
	    group += 1


###--# Finalization #--###
def grpPrint( groupno ):
    for name in names[groupno]:
	print '    > ' + name.replace( '|',' ' )

print '\n---++ Summary ++---\n'
print '[#] Groups Found (%d):' % len( groups )

for url,name in groups:
    print '    > ' + name

print '[#] Group Associates (%d):' % len( names[GRP_ASSOC] )
grpPrint( GRP_ASSOC )

print '[#] Group Heads (%d):' % len( names[GRP_HEAD] )
grpPrint( GRP_HEAD )

print '[#] Group Elders (%d):' % len( names[GRP_ELDER] )
grpPrint( GRP_ELDER )

print '[#] Group Members (%d):' % len( names[GRP_MEMBER] )
grpPrint( GRP_MEMBER )

print '[#] Total Personnel: ' + str( nNames )

###--# END OF SCRIPT #--###