import urllib

source = urllib.urlopen("http://cse.kut.ac.kr/").read()

len_source = len(source)
print "Initial length of source:", len_source

source_new = None
i = 0
while (i < len_source):
	found = False
	if (found != True and source[i] == "<" and source[i+1 : i+7].lower() == "script"):
		found = True;
		j = i + 7;
		while (True):
			if (source[j] == "<" and source[j+1] == "/" and source[j+2 : j+8].lower() == "script"):
				#print "found - script"
				source = source[:i] + ' ' + source[j+9:]
				break
			j = j + 1
			if (j > len_source):
				break
		len_source = len(source)
	i = i + 1

len_source = len(source)
#print len_source

i = 0
while (i < len_source):
	found = False
	if (found != True and source[i] == "<" and source[i+1 : i+6].lower() == "style"):
		found = True;
		j = i + 6;
		while (True):
			if (source[j] == "<" and source[j+1] == "/" and source[j+2 : j+7].lower() == "style"):
				#print "found - style"
				source = source[:i] + ' ' + source[j+8:]
				break
			j = j + 1
			if (j > len_source):
				break
		len_source = len(source)
	i = i + 1

len_source = len(source)
#print len_source

i = 0
while (i < len_source):
	found = False
	if (found != True and source[i] == "<"):
		found = True;
		j = i + 1;
		while (True):
			if (source[j] == ">"):
				#print "found - HTML tag"
				source = source[:i] + ' ' + source[j+1:]
				break
			j = j + 1
			if (j > len_source):
				break
		len_source = len(source)
	i = i + 1

len_source = len(source)
print "Last length of source:", len_source

words = source.split()

#for word in words:
#	print word

print "Total num of plain words:", len(words)

for word in words:
    print '"' + word + '" ',