drop six and python2 support

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 six import string_types
+from urllib.parse import urlencode
 
 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
-from six import string_types
+import urllib
 
 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 six.moves import urllib
-from six.moves import http_cookiejar as cookielib
+from urllib.parse import quote, unquote_plus
+import urllib
+from http import cookiejar as cookielib
 import re
 from xml.dom.minidom import parseString
 import json