diff --git a/wikiextractor/WikiExtractor.py b/wikiextractor/WikiExtractor.py
index 152cd78..27056e2 100755
--- a/wikiextractor/WikiExtractor.py
+++ b/wikiextractor/WikiExtractor.py
@@ -58,12 +58,12 @@ from io import StringIO
 from multiprocessing import Queue, Process, cpu_count
 from timeit import default_timer
 
-from .extract import Extractor, ignoreTag, define_template
+from .extract import Extractor, ignoreTag, define_template, acceptedNamespaces
 
 # ===========================================================================
 
 # Program version
-__version__ = '3.0.2'
+__version__ = '3.0.3'
 
 ##
 # Defined in <siteinfo>
@@ -136,7 +136,7 @@ class NextFile(object):
 
     def _dirname(self):
         char1 = self.dir_index % 26
-        char2 = self.dir_index / 26 % 26
+        char2 = int(self.dir_index / 26) % 26
         return os.path.join(self.path_name, '%c%c' % (ord('A') + char2, ord('A') + char1))
 
     def _filepath(self):
@@ -201,7 +201,7 @@ def load_templates(file, output_file=None):
     page = []
     inText = False
     if output_file:
-        output = open(output_file, 'wb')
+        output = open(output_file, 'w')
     for line in file:
         line = line.decode('utf-8')
         if '<' not in line:  # faster than doing re.search()
@@ -352,7 +352,7 @@ def process_dump(input_file, template_file, out_file, file_size, file_compress,
     # start worker processes
     logging.info("Using %d extract processes.", process_count)
     workers = []
-    for _ in xrange(max(1, process_count)):
+    for _ in range(max(1, process_count)):
         extractor = Process(target=extract_process,
                             args=(jobs_queue, output_queue))
         extractor.daemon = True  # only live while parent process lives
diff --git a/wikiextractor/extract.py b/wikiextractor/extract.py
index dcfcd83..c0d9d75 100644
--- a/wikiextractor/extract.py
+++ b/wikiextractor/extract.py
@@ -19,7 +19,7 @@
 # =============================================================================
 
 import re
-import cgi
+import html
 from itertools import zip_longest
 import urllib
 from html.entities import name2codepoint
@@ -63,7 +63,7 @@ acceptedNamespaces = ['w', 'wiktionary', 'wikt']
 
 
 def get_url(uid):
-    return "%s?curid=%s" % (options.urlbase, uid)
+    return "%s?curid=%s" % (urlbase, uid)
 
 
 # ======================================================================
@@ -170,7 +170,7 @@ def clean(extractor, text, expand_templates=False, escape_doc=True):
     text = re.sub(r'\n\W+?\n', '\n', text, flags=re.U)  # lines with only punctuations
     text = text.replace(',,', ',').replace(',.', '.')
     if escape_doc:
-        text = cgi.escape(text)
+        text = html.escape(text)
     return text
 
 
@@ -212,9 +212,7 @@ def compact(text, mark_headers=False):
 
             headers[lev] = title
             # drop previous headers
-            for i in headers.keys():
-                if i > lev:
-                    del headers[i]
+            headers = { k:v for k,v in headers.items() if k > lev }
             emptySection = True
             continue
         # Handle page title
@@ -268,8 +266,7 @@ def compact(text, mark_headers=False):
             continue
         elif len(headers):
             if Extractor.keepSections:
-                items = headers.items()
-                items.sort()
+                items = sorted(headers.items())
                 for (i, v) in items:
                     page.append(v)
             headers.clear()
@@ -497,7 +494,7 @@ def makeInternalLink(title, label):
         if colon2 > 1 and title[colon + 1:colon2] not in acceptedNamespaces:
             return ''
     if Extractor.keepLinks:
-        return '<a href="%s">%s</a>' % (urllib.quote(title.encode('utf-8')), label)
+        return '<a href="%s">%s</a>' % (urllib.quote(title), label)
     else:
         return label
 
@@ -860,14 +857,13 @@ class Extractor(object):
         header = '<doc id="%s" url="%s" title="%s">\n' % (self.id, url, self.title)
         # Separate header from text with a newline.
         header += self.title + '\n\n'
-        header = header.encode('utf-8')
         footer = "\n</doc>\n"
         out.write(header)
 
         text = self.clean_text(text)
 
         for line in text:
-            out.write(line.encode('utf-8'))
+            out.write(line)
             out.write('\n')
         out.write(footer)
         errs = (self.template_title_errs,