#!/usr/bin/env python
#
#    UsernameGen
#    Copyright (C) 2009  Jason Wood (JW Network Consulting)
#
#    This program is free software; you can redistribute it and/or modify
#    it under the terms of the GNU General Public License as published by
#    the Free Software Foundation; either version 2 of the License, or
#    (at your option) any later version.
#
#    This program is distributed in the hope that it will be useful,
#    but WITHOUT ANY WARRANTY; without even the implied warranty of
#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#    GNU General Public License for more details.
#
#    You should have received a copy of the GNU General Public License
#    along with this program; if not, write to the Free Software
#    Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA

__version__ = '2.1.1'
__author__ = 'Jason Wood - aka Tadaka'

__doc__ = """
Originally google.py 
Google (GNUCITIZEN) http://www.gnucitizen.org

 by Petko D. Petkov; pdp (arhictect)
for Python 2.5

Name changed to usernameGen.py and modified
by Jason Wood
http://www.jwnetworkconsulting.com

Changes:
6/28/2009
  - Added "paddbottom" tag fix by Robin Wood for a new tag to match on
  - Added fix for the regex by Robin Wood
  - Added scheme for lastname + first initial usernames 

6/16/2009
  - Added handling for when there are middle names.  creates usernames in the format of 
    first initial, middle initial, last name

6/12/2009
  - URL was changed to use mobile search
  - Regex was tweaked so it would work again
  - Limited the response to only the title
    of each result.
  - Added a new class and method which:
   -  takes the results of the title for the result and extracts the persons first and last name
   -  then makes usernames with the first initial & last name and first name & last initial

"""

import re
import urllib
import urllib2
import logging

class Get(object):
	"""
	Get

	The power of python in a single object
	"""

	def __init__(self):

		self.user_agent = 'User-Agent: Mozilla/5.0 ' \
			+ '(Macintosh; U; Intel Mac OS X 10.5; en-US; rv:1.9.0.11) ' \
			+ 'Gecko/2009060214 Firefox/3.0.11'

	def get(self, url):
		"""
		get(url) -> Response

		Open given url and return response.
		"""

		try:
			request = urllib2.Request(url)
			request.add_header('User-Agent', self.user_agent)

			logging.debug('Get.get - getting url ' + url)

			result = urllib2.urlopen(request)

		except: raise RuntimeError('unable to open url')

		return result


class Search(Get):
	"""
	Search

	The power of Google in a single object
	"""

	def search(self, q, start = 0, num = 10):
		"""
		search(q, start = 0, num = 10) -> generator

		Do google web search.
		"""

		url = 'http://www.google.com/m/search?'
		query = urllib.urlencode({'q':q, 'start':start, 'num':num})

		result = self.get(url + query)
		content = result.read()

		# print content

		tokens = re.findall(
			# '<div\s+class="[a|b]">\s*<a href="(.*?)"\s*>(.*?)</a>', content)
			'<div\s+class="(a|b|padbottom)">\s*<a href="(.*?)"\s*>(.*?)</a>', content)

		results = []

		for token in tokens:
			# print token
		 	title = token[2]

			logging.debug('Search.search - found url ' + url)

			results.append((title))

		return results

class Crawl(Search):
	"""
	Crawl

	The power of Google in a single object
	"""

	def crawl(self, q, depth = 0):
		"""
		crawl(q, depth = 0) -> generator

		Do google web crawl.
		"""

		index = 1
		last_results = None

		while True:
			if index == 1:
				start = 0

			else:
				start = (index - 1) * 10

			try:
				results = self.search(q, start, 10)

			except: continue

			if not results:
				break

			if last_results == results:
				break

			last_results = results

			yield results

			if index == depth:
				break

			index = index + 1


class MungeUsernames(Crawl):
        """
        Create usernames out of the search results
        """

        def mungeusers(self, searchterms):
                """
                set everything to lower case to start
                """

                names_raw = searchterms.lower()
		
		# print names_raw

		"""
		remove " - linkedin" from each row that has it
		then remove ": directory" from every row that has it
		assign the leftover values to the name variable
		"""

		matcher = re.match( r'(.*) - linkedin', names_raw, re.M|re.I)

		name = ""

		if matcher:
			match_directory = re.match( r'(.*): directory', matcher.group(1), re.M|re.I)
			if  match_directory:
				name = match_directory.group(1)
			else:
				name = matcher.group(1)

		"""
		Break the name up into first and last names.
		create the username variations with the first initial, last name
		and first name, last initial
		"""

		if name != "":
			full_name = name.split(" ")

			if len(full_name) == 2:
				fname = full_name[0]
				lname = full_name[1]
				uname = fname[0] + lname
				print uname
				uname = fname + lname[0]
				print uname
				uname = lname + fname[0]
				print uname
			elif len(full_name) == 3:
				fname = full_name[0]
				mname = full_name[1]
				lname = full_name[2]
				uname = fname[0] + lname
				print uname
				uname = fname + lname[0]
				print uname
				uname = lname + fname[0]
				print uname
				uname = fname[0] + mname[0] + lname
				print uname
			

if __name__ == '__main__':
	import os
	import sys
	import time

	import signal
	signal.signal(signal.SIGINT, lambda signum, frame: sys.exit())

	if len(sys.argv) < 3:
		print 'usage:', os.path.basename(sys.argv[0]), 'query #-of-results-pages'

		sys.exit()

	logging.basicConfig()

	g = Crawl()

	u = MungeUsernames()

	search_term = "site:linkedin.com "

	search_term += ' '.join(sys.argv[1:])

	for result in g.crawl(search_term, int(sys.argv[2])):
# 	for result in g.crawl(search_term, 20):
		for entry in result:
			u.mungeusers(entry)

		time.sleep(1)