Strip out all tags from HTML and return content

striptags.py

def strip_out_tags(html):
	out_of_tags = []
	inside_tags = []
	words = []
	beginning_pos = 0
	end_pos = 0
	if html[beginning_pos] == '<':
		in_tags = True
	else:
		in_tags = False
	while end_pos < len(html):
		if in_tags == False:
			if html[end_pos] != '<':	
				end_pos += 1
			else:				
				if html[beginning_pos:end_pos].rstrip() != '':				
					out_of_tags.append(html[beginning_pos:end_pos].rstrip())
				print beginning_pos, end_pos, in_tags
				in_tags = True
				beginning_pos = end_pos
		else:
			if html[end_pos] != '>':
				end_pos += 1
			else:
				inside_tags.append(html[beginning_pos:end_pos])
				print beginning_pos, end_pos, in_tags				
				in_tags = False
				beginning_pos = end_pos+1
	if beginning_pos != end_pos:
		out_of_tags.append(html[beginning_pos:end_pos].rstrip())
	
	for item in out_of_tags:
		if ' ' in item:
			for word in item.split(' '):
				if word != '':
					words.append(word)
		else:
			words.append(item)
	return words