drop six and python2 support

ox/api.py

@@ -10,10 +10,10 @@ import shutil
 import sys
 import time
 
-from six.moves import http_cookiejar as cookielib
+from http import cookiejar as cookielib
-from six import BytesIO, PY2
+from io import BytesIO
-from six.moves import urllib
+import urllib
-from six.moves.urllib.parse import urlparse
+from urllib.parse import urlparse
 import requests
 
 from . import __version__
@@ -56,10 +56,7 @@ class API(object):
     def _add_method(self, method, name):
         if name is None:
             name = method.func_name
-        if PY2:
+        setattr(self, name, MethodType(method, self))
-            setattr(self, name, MethodType(method, self, type(self)))
-        else:
-            setattr(self, name, MethodType(method, self))
 
     def _add_action(self, action):
         def method(self, *args, **kw):
@@ -73,10 +70,7 @@ class API(object):
             return self._request(action, kw)
         if 'doc' in self._properties[action]:
             method.__doc__ = self._properties[action]['doc']
-        if PY2:
+        method.func_name = action
-            method.func_name = str(action)
-        else:
-            method.func_name = action
         self._add_method(method, action)
 
     def _json_request(self, url, data, files=None):

ox/cache.py

@@ -10,9 +10,8 @@ import sqlite3
 import time
 import zlib
 
-from six import BytesIO
+from io import BytesIO
-from six.moves import urllib
+import urllib
-from six import PY2
 try:
     import requests
     USE_REQUESTS = True
@@ -242,8 +241,6 @@ class SQLiteCache(Cache):
             elif value == 'data':
                 if row[1] == 1:
                     r = zlib.decompress(r)
-                elif PY2:
-                    r = str(r)
             break
 
         c.close()

ox/fixunicode.py

@@ -6,7 +6,6 @@ from __future__ import print_function
 
 import unicodedata
 
-from six import unichr, text_type
 
 __all__ = ['fix_bad_unicode']
 
@@ -151,7 +150,7 @@ def text_badness(text):
     - Improbable single-byte characters, such as ƒ or ¬
     - Letters in somewhat rare scripts
     '''
-    assert isinstance(text, text_type)
+    assert isinstance(text, str)
     errors = 0
     very_weird_things = 0
     weird_things = 0
@@ -289,7 +288,7 @@ SINGLE_BYTE_WEIRDNESS = (
 # Pre-cache the Unicode data saying which of these first 256 characters are
 # letters. We'll need it often.
 SINGLE_BYTE_LETTERS = [
-    unicodedata.category(unichr(i)).startswith('L')
+    unicodedata.category(chr(i)).startswith('L')
     for i in range(256)
 ]
 

ox/form.py

@@ -9,8 +9,6 @@ import os
 import hashlib
 import sys
 
-from six import PY2
-
 
 __all__ = ['MultiPartForm']
 
@@ -63,8 +61,6 @@ class MultiPartForm(object):
 
     def __str__(self):
         body = self.body()
-        if not PY2:
-            body = body.decode('utf-8')
         return body
 
     def body(self):

ox/format.py

@@ -4,8 +4,6 @@ import math
 import re
 import string
 
-from six import text_type
-
 def toAZ(num):
     """
     Converts an integer to bijective base 26 string using A-Z
@@ -238,7 +236,7 @@ def int_value(strValue, default=u''):
     u''
     """
     try:
-        val = re.compile('(\d+)').findall(text_type(strValue).strip())[0]
+        val = re.compile('(\d+)').findall(str(strValue).strip())[0]
     except:
         val = default
     return val
@@ -255,7 +253,7 @@ def float_value(strValue, default=u''):
     u''
     """
     try:
-        val = re.compile('([\d.]+)').findall(text_type(strValue).strip())[0]
+        val = re.compile('([\d.]+)').findall(str(strValue).strip())[0]
     except:
         val = default
     return val

ox/html.py

@@ -3,8 +3,7 @@
 # GPL 2008
 import re
 import string
-from six.moves.html_entities import name2codepoint
+from html.entities import name2codepoint
-from six import unichr, PY2, string_types
 
 letters = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz'
 
@@ -26,8 +25,7 @@ link_target_attribute_re = re.compile(r'(<a [^>]*?)target=[^\s>]+')
 html_gunk_re = re.compile(r'(?:<br clear="all">|<i><\/i>|<b><\/b>|<em><\/em>|<strong><\/strong>|<\/?smallcaps>|<\/?uppercase>)', re.IGNORECASE)
 hard_coded_bullets_re = re.compile(r'((?:<p>(?:%s).*?[a-zA-Z].*?</p>\s*)+)' % '|'.join([re.escape(x) for x in DOTS]), re.DOTALL)
 trailing_empty_content_re = re.compile(r'(?:<p>(?:&nbsp;|\s|<br \/>)*?</p>\s*)+\Z')
-if PY2:
+
-    del x  # Temporary variable
 
 def escape(html):
     '''
@@ -36,7 +34,7 @@ def escape(html):
     >>> escape('html "test" & <brothers>')
     'html &quot;test&quot; &amp; &lt;brothers&gt;'
     '''
-    if not isinstance(html, string_types):
+    if not isinstance(html, str):
         html = str(html)
     return html.replace('&', '&amp;').replace('<', '&lt;').replace('>', '&gt;').replace('"', '&quot;').replace("'", '&apos;')
 
@@ -155,7 +153,7 @@ def decode_html(html):
     """
     if isinstance(html, bytes):
         html = html.decode('utf-8')
-    uchr = unichr
+    uchr = chr
 
     def entitydecode(match, uchr=uchr):
         entity = match.group(1)

ox/js.py

@@ -2,19 +2,12 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
 
-from six import PY2
 from .utils import json
 
 def minify(source, comment=''):
     # see https://github.com/douglascrockford/JSMin/blob/master/README
     def get_next_non_whitespace_token():
         pass
-    # python2 performance with unicode string is terrible
-    if PY2:
-        if isinstance(source, unicode):  # pylint: disable=undefined-variable
-            source = source.encode('utf-8')
-        if isinstance(comment, unicode):  # pylint: disable=undefined-variable
-            comment = comment.encode('utf-8')
     tokens = tokenize(source)
     length = len(tokens)
     minified = '/*' + comment + '*/' if comment else ''

ox/net.py

@@ -13,8 +13,8 @@ try:
     USE_REQUESTS = True
 except:
     USE_REQUESTS = False
-from six import BytesIO, PY2
+from io import BytesIO
-from six.moves import urllib
+import urllib
 from chardet.universaldetector import UniversalDetector
 
 
@@ -59,14 +59,10 @@ def get_json(url, data=None, headers=None):
 def open_url(url, data=None, headers=None):
     if headers is None:
         headers = DEFAULT_HEADERS.copy()
-    if PY2:
+    if isinstance(url, bytes):
-        if not isinstance(url, bytes):
+        url = url.decode('utf-8')
-            url = url.encode('utf-8')
-    else:
-        if isinstance(url, bytes):
-            url = url.decode('utf-8')
     url = url.replace(' ', '%20')
-    if data and not PY2 and not isinstance(data, bytes):
+    if data and not isinstance(data, bytes):
         data = data.encode('utf-8')
     req = urllib.request.Request(url, data, headers)
     return urllib.request.urlopen(req)

ox/normalize.py

@@ -4,8 +4,6 @@
 import re
 import unicodedata
 
-from six import string_types
-
 
 _articles = ('the', 'la', 'a', 'die', 'der', 'le', 'el',
              "l'", 'il', 'das', 'les', 'o', 'ein', 'i', 'un', 'los', 'de',
@@ -103,7 +101,7 @@ def normalize_imdbid(imdbId):
     >>> normalize_imdbid('tt0159206')
     '0159206'
     """
-    if isinstance(imdbId, string_types):
+    if isinstance(imdbId, str):
         imdbId = re.sub('.*(\d{7}).*', '\\1', imdbId)
     elif isinstance(imdbId, int):
         imdbId = "%07d" % imdbId

ox/srt.py

@@ -5,7 +5,6 @@ import codecs
 import re
 
 import chardet
-from six import PY2
 import ox
 
 
@@ -24,10 +23,7 @@ def _detect_encoding(fp):
     # go to beginning of file and get the first 4 bytes
     oldFP = fp.tell()
     fp.seek(0)
-    if PY2:
+    (byte1, byte2, byte3, byte4) = fp.read(4)
-        (byte1, byte2, byte3, byte4) = [ord(b) for b in fp.read(4)]
-    else:
-        (byte1, byte2, byte3, byte4) = fp.read(4)
 
     # try bom detection using 4 bytes, 3 bytes, or 2 bytes
     bomDetection = bomDict.get((byte1, byte2, byte3, byte4))

ox/text.py

@@ -1,11 +1,13 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
 # GPL 2008
+import gzip
 import math
 import re
 import unicodedata
+from io import BytesIO
 
-from six.moves import reduce
+from functools import reduce
 
 ARTICLES = list(set([
     # def sg, def pl, indef sg, indef pl (each m/f/n)
@@ -646,8 +648,6 @@ def phone2numeric(phone):
     return letters.sub(char2number, phone)
 
 def compress_string(s):
-    import gzip
-    from six import BytesIO
     zbuf = BytesIO()
     zfile = gzip.GzipFile(mode='wb', compresslevel=6, fileobj=zbuf)
     zfile.write(s)

ox/torrent/__init__.py

@@ -5,12 +5,8 @@
 from threading import Event
 from hashlib import sha1
 import os
-from six import PY2
 
-if PY2:
+from .bencode3 import bencode, bdecode
-    from .bencode import bencode, bdecode
-else:
-    from .bencode3 import bencode, bdecode
 
 __all__ = ['create_torrent', 'get_info_hash', 'get_torrent_info', 'get_files', 'get_torrent_size']
 

ox/torrent/bencode.py

@@ -1,321 +0,0 @@
-# Written by Petru Paler, Uoti Urpala, Ross Cohen and John Hoffman
-# see LICENSE.txt for license information
-from __future__ import print_function
-
-from types import IntType, LongType, StringType, ListType, TupleType, DictType
-try:
-    from types import BooleanType
-except ImportError:
-    BooleanType = None
-try:
-    from types import UnicodeType
-except ImportError:
-    UnicodeType = None
-from cStringIO import StringIO
-
-def decode_int(x, f):
-    f += 1
-    newf = x.index('e', f)
-    try:
-        n = int(x[f:newf])
-    except:
-        n = long(x[f:newf])
-    if x[f] == '-':
-        if x[f + 1] == '0':
-            raise ValueError
-    elif x[f] == '0' and newf != f+1:
-        raise ValueError
-    return (n, newf+1)
-  
-def decode_string(x, f):
-    colon = x.index(':', f)
-    try:
-        n = int(x[f:colon])
-    except (OverflowError, ValueError):
-        n = long(x[f:colon])
-    if x[f] == '0' and colon != f+1:
-        raise ValueError
-    colon += 1
-    return (x[colon:colon+n], colon+n)
-
-def decode_unicode(x, f):
-    s, f = decode_string(x, f+1)
-    return (s.decode('UTF-8'),f)
-
-def decode_list(x, f):
-    r, f = [], f+1
-    while x[f] != 'e':
-        v, f = decode_func[x[f]](x, f)
-        r.append(v)
-    return (r, f + 1)
-
-def decode_dict(x, f):
-    r, f = {}, f+1
-    lastkey = None
-    while x[f] != 'e':
-        k, f = decode_string(x, f)
-        #  why is this needed
-        #  if lastkey >= k:
-        #    raise ValueError
-        lastkey = k
-        r[k], f = decode_func[x[f]](x, f)
-    return (r, f + 1)
-
-decode_func = {}
-decode_func['l'] = decode_list
-decode_func['d'] = decode_dict
-decode_func['i'] = decode_int
-decode_func['0'] = decode_string
-decode_func['1'] = decode_string
-decode_func['2'] = decode_string
-decode_func['3'] = decode_string
-decode_func['4'] = decode_string
-decode_func['5'] = decode_string
-decode_func['6'] = decode_string
-decode_func['7'] = decode_string
-decode_func['8'] = decode_string
-decode_func['9'] = decode_string
-#decode_func['u'] = decode_unicode
-  
-def bdecode(x, sloppy = 1):
-    try:
-        r, l = decode_func[x[0]](x, 0)
-#    except (IndexError, KeyError):
-    except (IndexError, KeyError, ValueError):
-        raise ValueError("bad bencoded data")
-    if not sloppy and l != len(x):
-        raise ValueError("bad bencoded data")
-    return r
-
-def test_bdecode():
-    try:
-        bdecode('0:0:')
-        assert 0
-    except ValueError:
-        pass
-    try:
-        bdecode('ie')
-        assert 0
-    except ValueError:
-        pass
-    try:
-        bdecode('i341foo382e')
-        assert 0
-    except ValueError:
-        pass
-    assert bdecode('i4e') == 4
-    assert bdecode('i0e') == 0
-    assert bdecode('i123456789e') == 123456789
-    assert bdecode('i-10e') == -10
-    try:
-        bdecode('i-0e')
-        assert 0
-    except ValueError:
-        pass
-    try:
-        bdecode('i123')
-        assert 0
-    except ValueError:
-        pass
-    try:
-        bdecode('')
-        assert 0
-    except ValueError:
-        pass
-    try:
-        bdecode('i6easd')
-        assert 0
-    except ValueError:
-        pass
-    try:
-        bdecode('35208734823ljdahflajhdf')
-        assert 0
-    except ValueError:
-        pass
-    try:
-        bdecode('2:abfdjslhfld')
-        assert 0
-    except ValueError:
-        pass
-    assert bdecode('0:') == ''
-    assert bdecode('3:abc') == 'abc'
-    assert bdecode('10:1234567890') == '1234567890'
-    try:
-        bdecode('02:xy')
-        assert 0
-    except ValueError:
-        pass
-    try:
-        bdecode('l')
-        assert 0
-    except ValueError:
-        pass
-    assert bdecode('le') == []
-    try:
-        bdecode('leanfdldjfh')
-        assert 0
-    except ValueError:
-        pass
-    assert bdecode('l0:0:0:e') == ['', '', '']
-    try:
-        bdecode('relwjhrlewjh')
-        assert 0
-    except ValueError:
-        pass
-    assert bdecode('li1ei2ei3ee') == [1, 2, 3]
-    assert bdecode('l3:asd2:xye') == ['asd', 'xy']
-    assert bdecode('ll5:Alice3:Bobeli2ei3eee') == [['Alice', 'Bob'], [2, 3]]
-    try:
-        bdecode('d')
-        assert 0
-    except ValueError:
-        pass
-    try:
-        bdecode('defoobar')
-        assert 0
-    except ValueError:
-        pass
-    assert bdecode('de') == {}
-    assert bdecode('d3:agei25e4:eyes4:bluee') == {'age': 25, 'eyes': 'blue'}
-    assert bdecode('d8:spam.mp3d6:author5:Alice6:lengthi100000eee') == {'spam.mp3': {'author': 'Alice', 'length': 100000}}
-    try:
-        bdecode('d3:fooe')
-        assert 0
-    except ValueError:
-        pass
-    try:
-        bdecode('di1e0:e')
-        assert 0
-    except ValueError:
-        pass
-    try:
-        bdecode('d1:b0:1:a0:e')
-        assert 0
-    except ValueError:
-        pass
-    try:
-        bdecode('d1:a0:1:a0:e')
-        assert 0
-    except ValueError:
-        pass
-    try:
-        bdecode('i03e')
-        assert 0
-    except ValueError:
-        pass
-    try:
-        bdecode('l01:ae')
-        assert 0
-    except ValueError:
-        pass
-    try:
-        bdecode('9999:x')
-        assert 0
-    except ValueError:
-        pass
-    try:
-        bdecode('l0:')
-        assert 0
-    except ValueError:
-        pass
-    try:
-        bdecode('d0:0:')
-        assert 0
-    except ValueError:
-        pass
-    try:
-        bdecode('d0:')
-        assert 0
-    except ValueError:
-        pass
-
-bencached_marker = []
-
-class Bencached:
-    def __init__(self, s):
-        self.marker = bencached_marker
-        self.bencoded = s
-
-BencachedType = type(Bencached('')) # insufficient, but good as a filter
-
-def encode_bencached(x,r):
-    assert x.marker == bencached_marker
-    r.append(x.bencoded)
-
-def encode_int(x,r):
-    r.extend(('i',str(x),'e'))
-
-def encode_bool(x,r):
-    encode_int(int(x),r)
-
-def encode_string(x,r):    
-    r.extend((str(len(x)),':',x))
-
-def encode_unicode(x,r):
-    #r.append('u')
-    encode_string(x.encode('UTF-8'),r)
-
-def encode_list(x,r):
-        r.append('l')
-        for e in x:
-            encode_func[type(e)](e, r)
-        r.append('e')
-
-def encode_dict(x,r):
-    r.append('d')
-    ilist = x.items()
-    ilist.sort()
-    for k,v in ilist:
-        r.extend((str(len(k)),':',k))
-        encode_func[type(v)](v, r)
-    r.append('e')
-
-encode_func = {}
-encode_func[BencachedType] = encode_bencached
-encode_func[IntType] = encode_int
-encode_func[LongType] = encode_int
-encode_func[StringType] = encode_string
-encode_func[ListType] = encode_list
-encode_func[TupleType] = encode_list
-encode_func[DictType] = encode_dict
-if BooleanType:
-    encode_func[BooleanType] = encode_bool
-if UnicodeType:
-    encode_func[UnicodeType] = encode_unicode
-    
-def bencode(x):
-    r = []
-    try:
-        encode_func[type(x)](x, r)
-    except:
-        print("*** error *** could not encode type %s (value: %s)" % (type(x), x))
-        assert 0
-    return ''.join(r)
-
-def test_bencode():
-    assert bencode(4) == 'i4e'
-    assert bencode(0) == 'i0e'
-    assert bencode(-10) == 'i-10e'
-    assert bencode(12345678901234567890) == 'i12345678901234567890e'
-    assert bencode('') == '0:'
-    assert bencode('abc') == '3:abc'
-    assert bencode('1234567890') == '10:1234567890'
-    assert bencode([]) == 'le'
-    assert bencode([1, 2, 3]) == 'li1ei2ei3ee'
-    assert bencode([['Alice', 'Bob'], [2, 3]]) == 'll5:Alice3:Bobeli2ei3eee'
-    assert bencode({}) == 'de'
-    assert bencode({'age': 25, 'eyes': 'blue'}) == 'd3:agei25e4:eyes4:bluee'
-    assert bencode({'spam.mp3': {'author': 'Alice', 'length': 100000}}) == 'd8:spam.mp3d6:author5:Alice6:lengthi100000eee'
-    try:
-        bencode({1: 'foo'})
-        assert 0
-    except AssertionError:
-        pass
-
-  
-try:
-    import psyco
-    psyco.bind(bdecode)
-    psyco.bind(bencode)
-except ImportError:
-    pass

ox/torrent/makemetafile.py

@@ -8,11 +8,7 @@ from hashlib import sha1 as sha
 from copy import copy
 import re
 
-from six import PY2
+from .bencode3 import bencode
-if PY2:
-    from .bencode import bencode
-else:
-    from .bencode3 import bencode
 from threading import Event
 from time import time
 from traceback import print_exc

ox/web/amazon.py

@@ -2,7 +2,7 @@
 # vi:si:et:sw=4:sts=4:ts=4
 from __future__ import print_function
 import re
-from six.moves.urllib.parse import quote
+from urllib.parse import quote
 
 from ox import find_re, strip_tags, decode_html
 from ox.cache import read_url

ox/web/apple.py

@@ -2,7 +2,6 @@ from __future__ import print_function
 import json
 import re
 
-from six import text_type
 from ox.cache import read_url
 
 HEADERS = {
@@ -17,9 +16,9 @@ USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7) '
 USER_AGENT += 'AppleWebKit/534.48.3 (KHTML, like Gecko) Version/5.1 Safari/534.48.3'
 
 def get_movie_data(title, director):
-    if isinstance(title, text_type):
+    if isinstance(title, str):
         title = title.encode('utf-8')
-    if isinstance(director, text_type):
+    if isinstance(director, str):
         director = director.encode('utf-8')
     data = {}
     # itunes section (preferred source for link)

ox/web/archive.py

@@ -3,8 +3,6 @@
 from .. import cache
 from ..utils import json
 
-from six import string_types
-
 def get_id(url):
     return url.split("/")[-1]
 
@@ -21,7 +19,7 @@ def get_data(id):
             data[key] = details['metadata'][key]
             if isinstance(data[key], list):
                 data[key] = data[key][0]
-            if isinstance(data[key], string_types):
+            if isinstance(data[key], str):
                 data[key] = data[key].strip()
                 if data[key][0] == '[' and data[key][-1] == ']':
                     data[key] = data[key][1:-1] 

ox/web/dailymotion.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
 import re
-from six.moves.urllib.parse import unquote
+from urllib.parse import unquote
 from ox.cache import read_url
 
 

ox/web/duckduckgo.py

@@ -2,7 +2,7 @@
 # vi:si:et:sw=4:sts=4:ts=4
 import re
 
-from six.moves import urllib
+import urllib
 import ox
 from ox import strip_tags, decode_html
 from ox.cache import read_url

ox/web/google.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
 import re
-from six.moves import urllib
+import urllib
 
 import ox
 from ox import strip_tags, decode_html

ox/web/imdb.py

@@ -7,8 +7,7 @@ import re
 import time
 import unicodedata
 
-from six.moves.urllib.parse import urlencode
+from urllib.parse import urlencode
-from six import string_types
 
 from .. import find_re, strip_tags, decode_html
 from .. import cache
@@ -449,7 +448,7 @@ class Imdb(SiteParser):
 
         if 'alternativeTitles' in self:
             if len(self['alternativeTitles']) == 2 and \
-               isinstance(self['alternativeTitles'][0], string_types):
+               isinstance(self['alternativeTitles'][0], str):
                self['alternativeTitles'] = [self['alternativeTitles']]
 
         for key in ('country', 'genre', 'language', 'sound', 'color'):
@@ -514,7 +513,7 @@ class Imdb(SiteParser):
             self['sound'] = list(sorted(set(self['sound'])))
 
         if 'cast' in self:
-            if isinstance(self['cast'][0], string_types):
+            if isinstance(self['cast'][0], str):
                 self['cast'] = [self['cast']]
             self['actor'] = [c[0] for c in self['cast']]
             def cleanup_character(c):

ox/web/itunes.py

@@ -2,7 +2,7 @@
 # encoding: utf-8
 from __future__ import print_function
 import re
-from six.moves.urllib.parse import urlencode
+from urllib.parse import urlencode
 
 from ox.cache import read_url
 from ox.html import decode_html, strip_tags

ox/web/metacritic.py

@@ -2,7 +2,7 @@
 # vi:si:et:sw=4:sts=4:ts=4
 import re
 
-from six.moves.urllib.parse import quote
+from urllib.parse import quote
 from lxml.html import document_fromstring
 
 from ox.cache import read_url

ox/web/siteparser.py

@@ -4,8 +4,6 @@ import re
 import json
 from multiprocessing.pool import ThreadPool
 
-from six import string_types
-
 from ..cache import read_url
 from .. import decode_html
 from ..utils import datetime
@@ -13,15 +11,15 @@ from ..utils import datetime
 
 def cleanup(key, data, data_type):
     if data:
-        if isinstance(data[0], string_types):
+        if isinstance(data[0], str):
             #FIXME: some types need strip_tags
             #data = [strip_tags(decode_html(p)).strip() for p in data]
             data = [decode_html(p).strip() for p in data]
         elif isinstance(data[0], list) or isinstance(data[0], tuple):
             data = [cleanup(key, p, data_type) for p in data]
-        while len(data) == 1 and not isinstance(data, string_types):
+        while len(data) == 1 and not isinstance(data, str):
             data = data[0]
-        if data_type == 'list' and isinstance(data, string_types):
+        if data_type == 'list' and isinstance(data, str):
             data = [data, ]
     elif data_type != 'list':
         data = ''
@@ -49,7 +47,7 @@ class SiteParser(dict):
         for key in self.regex:
             url = self.get_url(self.regex[key]['page'])
             data = self.read_url(url, timeout)
-            if isinstance(self.regex[key]['re'], string_types):
+            if isinstance(self.regex[key]['re'], str):
                 data = re.compile(self.regex[key]['re'], re.DOTALL).findall(data)
                 data = cleanup(key, data, self.regex[key]['type'])
             elif callable(self.regex[key]['re']):
@@ -60,7 +58,7 @@ class SiteParser(dict):
                         f = r
                     else:
                         f = re.compile(r, re.DOTALL).findall
-                    if isinstance(data, string_types):
+                    if isinstance(data, str):
                         data = f(data)
                     else:
                         data = [f(d) for d in data]

ox/web/startpage.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
-from six.moves import urllib
+import urllib
 
 import lxml.html
 import ox

ox/web/thepiratebay.py

@@ -3,7 +3,7 @@
 from datetime import datetime
 import re
 
-from six.moves.urllib.parse import quote
+from urllib.parse import quote
 
 from ox import find_re, cache, strip_tags, decode_html, get_torrent_info, normalize_newlines
 from ox.normalize import normalize_imdbid

ox/web/twitter.py

@@ -2,7 +2,7 @@
 # vi:si:et:sw=4:sts=4:ts=4
 import re
 from datetime import datetime
-from six.moves.urllib.parse import quote
+from urllib.parse import quote
 
 import lxml.html
 import ox

ox/web/wikipedia.py

@@ -4,8 +4,7 @@ from __future__ import print_function
 
 import re
 
-from six.moves import urllib
+import urllib
-from six import string_types
 
 from ox.utils import json
 from ox.cache import read_url
@@ -69,7 +68,7 @@ def get_movie_data(wikipedia_url):
                     value = value.split('<br>')
                 if value:
                     if key in filmbox:
-                        if isinstance(value, list) and isinstance(filmbox[key], string_types):
+                        if isinstance(value, list) and isinstance(filmbox[key], str):
                             filmbox[key] = [filmbox[key]] + value
                         else:
                             filmbox[key] += value

ox/web/youtube.py

@@ -1,8 +1,8 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
-from six.moves.urllib.parse import quote, unquote_plus
+from urllib.parse import quote, unquote_plus
-from six.moves import urllib
+import urllib
-from six.moves import http_cookiejar as cookielib
+from http import cookiejar as cookielib
 import re
 from xml.dom.minidom import parseString
 import json

requirements.txt

@@ -1,4 +1,3 @@
 chardet
-six>=1.5.2
 lxml
 requests

setup.py

@@ -50,7 +50,7 @@ setup(
     url="https://code.0x2620.org/0x2620/python-ox",
     license="GPLv3",
     packages=['ox', 'ox.torrent', 'ox.web'],
-    install_requires=['six>=1.5.2', 'chardet'],
+    install_requires=['chardet'],
     keywords=[
     ],
     classifiers=[