Removing is_py3 method and duplicated by urllib.

ebook_converter/ebooks/oeb/polish/container.py

@@ -11,6 +11,7 @@ import uuid
 from collections import defaultdict
 from io import BytesIO
 from itertools import count
+import urllib.parse
 
 from css_parser import getUrls, replaceUrls
 
@@ -49,7 +50,6 @@ from ebook_converter.utils.logging import default_log
 from ebook_converter.utils.xml_parse import safe_xml_fromstring
 from ebook_converter.utils.zipfile import ZipFile
 from ebook_converter.polyglot.builtins import iteritems, unicode_type
-from ebook_converter.polyglot.urllib import urlparse
 
 exists, join, relpath = os.path.exists, os.path.join, os.path.relpath
 
@@ -107,7 +107,7 @@ def name_to_href(name, root, base=None, quote=urlquote):
 def href_to_name(href, root, base=None):
     base = root if base is None else os.path.dirname(name_to_abspath(base, root))
     try:
-        purl = urlparse(href)
+        purl = urllib.parse.urlparse(href)
     except ValueError:
         return None
     if purl.scheme or not purl.path:

ebook_converter/ebooks/oeb/polish/replace.py

@@ -2,13 +2,13 @@ import codecs, shutil, os, posixpath
 from ebook_converter.polyglot.builtins import iteritems, itervalues
 from functools import partial
 from collections import Counter, defaultdict
+import urllib.parse
 
 from ebook_converter import sanitize_file_name
 from ebook_converter.ebooks.chardet import strip_encoding_declarations
 from ebook_converter.ebooks.oeb.base import css_text
 from ebook_converter.ebooks.oeb.polish.css import iter_declarations, remove_property_value
 from ebook_converter.ebooks.oeb.polish.utils import extract
-from ebook_converter.polyglot.urllib import urlparse, urlunparse
 
 
 __license__ = 'GPL v3'
@@ -38,7 +38,7 @@ class LinkReplacer(object):
         nname = self.link_map.get(name, None)
         if not nname:
             return url
-        purl = urlparse(url)
+        purl = urllib.parse.urlparse(url)
         href = self.container.name_to_href(nname, self.base)
         if purl.fragment:
             nfrag = self.frag_map(name, purl.fragment)
@@ -68,12 +68,12 @@ class IdReplacer(object):
         id_map = self.id_map.get(name)
         if id_map is None:
             return url
-        purl = urlparse(url)
+        purl = urllib.parse.urlparse(url)
         nfrag = id_map.get(purl.fragment)
         if nfrag is None:
             return url
         purl = purl._replace(fragment=nfrag)
-        href = urlunparse(purl)
+        href = urllib.parse.urlunparse(purl)
         if href != url:
             self.replaced = True
         return href
@@ -89,7 +89,7 @@ class LinkRebaser(object):
     def __call__(self, url):
         if url and url.startswith('#'):
             return url
-        purl = urlparse(url)
+        purl = urllib.parse.urlparse(url)
         frag = purl.fragment
         name = self.container.href_to_name(url, self.old_name)
         if not name:

ebook_converter/ebooks/oeb/polish/split.py

@@ -1,12 +1,12 @@
 import copy, os, re
 from ebook_converter.polyglot.builtins import string_or_bytes
+import urllib.parse
 
 from ebook_converter.ebooks.oeb.base import barename, XPNSMAP, XPath, OPF, XHTML, OEB_DOCS
 from ebook_converter.ebooks.oeb.polish.errors import MalformedMarkup
 from ebook_converter.ebooks.oeb.polish.toc import node_from_loc
 from ebook_converter.ebooks.oeb.polish.replace import LinkRebaser
 from ebook_converter.polyglot.builtins import iteritems, unicode_type
-from ebook_converter.polyglot.urllib import urlparse
 
 
 __license__ = 'GPL v3'
@@ -160,7 +160,7 @@ class SplitLinkReplacer(object):
         name = self.container.href_to_name(url, self.base)
         if name != self.top_name:
             return url
-        purl = urlparse(url)
+        purl = urllib.parse.urlparse(url)
         if purl.fragment and purl.fragment in self.bottom_anchors:
             url = self.container.name_to_href(self.bottom_name, self.base) + '#' + purl.fragment
             self.replaced = True
@@ -225,7 +225,7 @@ def split(container, name, loc_or_xpath, before=True, totals=None):
             else:
                 fname = container.href_to_name(url, name)
             if fname == name:
-                purl = urlparse(url)
+                purl = urllib.parse.urlparse(url)
                 if purl.fragment in anchors_in_top:
                     if r is root2:
                         a.set('href', '%s#%s' % (container.name_to_href(name, bottom_name), purl.fragment))
@@ -310,7 +310,7 @@ class MergeLinkReplacer(object):
         amap = self.anchor_map.get(name, None)
         if amap is None:
             return url
-        purl = urlparse(url)
+        purl = urllib.parse.urlparse(url)
         frag = purl.fragment or ''
         frag = amap.get(frag, frag)
         url = self.container.name_to_href(self.master, self.base) + '#' + frag

ebook_converter/ebooks/oeb/polish/toc.py

@@ -3,6 +3,7 @@ from collections import Counter, OrderedDict
 from functools import partial
 from operator import itemgetter
 import pkg_resources
+import urllib.parse
 
 from lxml import etree
 from lxml.builder import ElementMaker
@@ -16,7 +17,6 @@ from ebook_converter.ebooks.oeb.polish.opf import set_guide_item, get_book_langu
 from ebook_converter.ebooks.oeb.polish.pretty import pretty_html_tree
 from ebook_converter.utils.localization import get_lang, canonicalize_lang, lang_as_iso639_1
 from ebook_converter.polyglot.builtins import iteritems, unicode_type
-from ebook_converter.polyglot.urllib import urlparse
 
 
 __license__ = 'GPL v3'
@@ -150,7 +150,7 @@ def add_from_navpoint(container, navpoint, parent, ncx_name):
         href = content.get('src', None)
         if href:
             dest = container.href_to_name(href, base=ncx_name)
-            frag = urlparse(href).fragment or None
+            frag = urllib.parse.urlparse(href).fragment or None
     return parent.add(text or None, dest or None, frag or None)
 
 
@@ -183,7 +183,7 @@ def parse_ncx(container, ncx_name):
                 href = pt.xpath('descendant::*[calibre:lower-case(local-name()) = "content"]/@src')
                 if href:
                     dest = container.href_to_name(href[0], base=ncx_name)
-                    frag = urlparse(href[0]).fragment or None
+                    frag = urllib.parse.urlparse(href[0]).fragment or None
                     toc_root.page_list.append({'dest': dest, 'pagenum': pagenum, 'frag': frag})
     return toc_root
 
@@ -195,7 +195,7 @@ def add_from_li(container, li, parent, nav_name):
         href = x.get('href')
         if href:
             dest = nav_name if href.startswith('#') else container.href_to_name(href, base=nav_name)
-            frag = urlparse(href).fragment or None
+            frag = urllib.parse.urlparse(href).fragment or None
         break
     return parent.add(text or None, dest or None, frag or None)