[svn r3831] r4511@delle: sbehnel | 2008-06-19 10:46:05 +0200

 fixes for Py3k stdlib restructuring

--HG--
branch : trunk

6 files changed, 34 insertions, 14 deletions

diff --git a/src/lxml/ElementInclude.py b/src/lxml/ElementInclude.py
index 471893fa..a0224bb3 100644
--- a/src/lxml/ElementInclude.py
+++ b/src/lxml/ElementInclude.py
@@ -52,12 +52,18 @@ form of custom URL resolvers.
 
 from lxml import etree
 import copy
-from urlparse import urljoin
-from urllib2 import urlopen
+try:
+    from urlparse import urljoin
+    from urllib2 import urlopen
+except ImportError:
+    # Python 3
+    from urllib.parse import urljoin
+    from urllib.request import urlopen
 
 try:
     set
 except NameError:
+    # Python 2.3
     from sets import Set as set
 
 XINCLUDE = "{http://www.w3.org/2001/XInclude}"
diff --git a/src/lxml/html/__init__.py b/src/lxml/html/__init__.py
index ed662858..ae047aaf 100644
--- a/src/lxml/html/__init__.py
+++ b/src/lxml/html/__init__.py
@@ -3,7 +3,11 @@
 
 import threading
 import re
-import urlparse
+try:
+    from urlparse import urljoin
+except ImportError:
+    # Python 3
+    from urllib.parse import urljoin
 import copy
 from lxml import etree
 from lxml.html import defs
@@ -269,7 +273,7 @@ class HtmlMixin(object):
         if resolve_base_href:
             self.resolve_base_href()
         def link_repl(href):
-            return urlparse.urljoin(base_url, href)
+            return urljoin(base_url, href)
         self.rewrite_links(link_repl)
 
     def resolve_base_href(self):
@@ -316,13 +320,13 @@ class HtmlMixin(object):
                     if attrib in attribs:
                         value = el.get(attrib)
                         if codebase is not None:
-                            value = urlparse.urljoin(codebase, value)
+                            value = urljoin(codebase, value)
                         yield (el, attrib, value, 0)
                 if 'archive' in attribs:
                     for match in _archive_re.finditer(el.get('archive')):
                         value = match.group(0)
                         if codebase is not None:
-                            value = urlparse.urljoin(codebase, value)
+                            value = urljoin(codebase, value)
                         yield (el, 'archive', value, match.start())
             if tag == 'param':
                 valuetype = el.get('valuetype') or ''
@@ -751,7 +755,7 @@ class FormElement(HtmlElement):
         base_url = self.base_url
         action = self.get('action')
         if base_url and action is not None:
-            return urlparse.urljoin(base_url, action)
+            return urljoin(base_url, action)
         else:
             return action
     def _action__set(self, value):
diff --git a/src/lxml/html/clean.py b/src/lxml/html/clean.py
index c5837e6f..ecb9d998 100644
--- a/src/lxml/html/clean.py
+++ b/src/lxml/html/clean.py
@@ -6,7 +6,11 @@ details.
 
 import re
 import copy
-import urlparse
+try:
+    from urlparse import urlsplit
+except ImportError:
+    # Python 3
+    from urllib.parse import urlsplit
 from lxml import etree
 from lxml.html import defs
 from lxml.html import fromstring, tostring, XHTML_NAMESPACE
@@ -418,7 +422,7 @@ class Cleaner(object):
         if (self.whitelist_tags is not None
             and el.tag not in self.whitelist_tags):
             return False
-        scheme, netloc, path, query, fragment = urlparse.urlsplit(url)
+        scheme, netloc, path, query, fragment = urlsplit(url)
         netloc = netloc.lower().split(':', 1)[0]
         if scheme not in ('http', 'https'):
             return False
diff --git a/src/lxml/html/tests/test_feedparser_data.py b/src/lxml/html/tests/test_feedparser_data.py
index 3efc9d88..b1d94213 100644
--- a/src/lxml/html/tests/test_feedparser_data.py
+++ b/src/lxml/html/tests/test_feedparser_data.py
@@ -1,7 +1,11 @@
 import sys
 import os
 import re
-import rfc822
+try:
+    from rfc822 import Message
+except ImportError:
+    # Python 3
+    from email import message_from_file as Message
 import unittest
 from lxml.tests.common_imports import doctest
 if sys.version_info >= (2,4):
@@ -28,7 +32,7 @@ class FeedTestCase(unittest.TestCase):
 
     def parse(self):
         f = open(self.filename, 'r')
-        headers = rfc822.Message(f)
+        headers = Message(f)
         c = f.read()
         f.close()
         if not headers.keys():
diff --git a/src/lxml/html/tests/test_forms.txt b/src/lxml/html/tests/test_forms.txt
index 3f4f3144..11d67ae9 100644
--- a/src/lxml/html/tests/test_forms.txt
+++ b/src/lxml/html/tests/test_forms.txt
@@ -120,8 +120,9 @@ Traceback (most recent call last):
 ValueError: There is no option with the value 'asdf'
 >>> select.value_options
 ['1', '2', '3']
->>> import urllib
->>> print(urllib.urlencode(f.form_values()))
+>>> try: from urllib import urlencode
+... except ImportError: from urllib.parse import urlencode
+>>> print(urlencode(f.form_values()))
 hidden_field=new+value&text_field=text_value&single_checkbox=on&single_checkbox2=good&check_group=1&check_group=2&check_group=3&textarea_field=some+text&select1=&select2=1&select2=2&select2=3
 >>> fields = f.fields
 >>> fields # doctest:+NOPARSE_MARKUP
diff --git a/src/lxml/html/tests/test_rewritelinks.txt b/src/lxml/html/tests/test_rewritelinks.txt
index 674fcb2e..b4cdd779 100644
--- a/src/lxml/html/tests/test_rewritelinks.txt
+++ b/src/lxml/html/tests/test_rewritelinks.txt
@@ -1,7 +1,8 @@
 We'll define a link translation function:
 
     >>> base_href = 'http://old/base/path.html'
-    >>> import urlparse
+    >>> try: import urlparse
+    ... except ImportError: import urllib.parse as urlparse
     >>> def relocate_href(link):
     ...     link = urlparse.urljoin(base_href, link)
     ...     if link.startswith('http://old'):