View difference between Paste ID: hwWszcQU and 5j0R321Y

 #!/usr/bin/python
 
 from bz2 import BZ2File
 from glob import glob
 from contextlib import closing
 from pprint import pprint
 import re
 import codecs
 import sys
 import operator
 
 file = glob('*.bz2')[0]
 
 blackchars = ['{','<','|','}']
-spacestrip = re.compile(r'^\s+')
+spacestrip = re.compile(r'(?:^\s+|\s+\n?$|\n$)')
 strip = re.compile(ur'(?:&.*?;|<.*?>|[^\w\s]|\d)',re.UNICODE)
-tagstrip =re.compile(r'<.*?>')
+
-puncstrip = re.compile(ur'[^\w\s]',re.UNICODE)
+
-digstrip = re.compile(ur'\d',re.UNICODE)
+
 		line = re.sub(spacestrip,'',line.decode('utf-8'))
 		if line.strip() == '' or line[0] in blackchars:
 			continue
-		line = line.strip().decode('utf-8')
+
 			line = re.sub(strip,'',line)
 			for word in line.split(' '):
 				if word not in data:
 					data[word] = 0
 				data[word] += 1
-				if word.strip():
+
-					if word not in data:
+
-						data[word] = 0
+
-					data[word] += 1
+
 data = sorted(data.iteritems(), key=operator.itemgetter(1))
 for i in range(1,100):
 	print str(i)+": "+unicode(data[-i][0])+" - "+str(data[-i][1])