Hello community,
here is the log from the commit of package python-feedparser for
openSUSE:Factory checked in at 2020-09-28 14:30:03
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Comparing /work/SRC/openSUSE:Factory/python-feedparser (Old)
and /work/SRC/openSUSE:Factory/.python-feedparser.new.4249 (New)
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "python-feedparser"
Mon Sep 28 14:30:03 2020 rev:27 rq:838247 version:6.0.1
Changes:
--------
--- /work/SRC/openSUSE:Factory/python-feedparser/python-feedparser.changes
2020-09-25 16:31:40.563897928 +0200
+++
/work/SRC/openSUSE:Factory/.python-feedparser.new.4249/python-feedparser.changes
2020-09-28 14:30:52.854242157 +0200
@@ -1,0 +2,7 @@
+Mon Sep 28 11:20:26 UTC 2020 - Dirk Mueller <[email protected]>
+
+- update to 6.0.1:
+ * Remove all Python 2 compatibility code (#228)
+ * Add *python_requires* to ``setup.py`` (#2
+
+-------------------------------------------------------------------
Old:
----
feedparser-6.0.0.tar.gz
New:
----
feedparser-6.0.1.tar.gz
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Other differences:
------------------
++++++ python-feedparser.spec ++++++
--- /var/tmp/diff_new_pack.nr3ztG/_old 2020-09-28 14:30:53.558242768 +0200
+++ /var/tmp/diff_new_pack.nr3ztG/_new 2020-09-28 14:30:53.562242771 +0200
@@ -16,10 +16,10 @@
#
-%define skip_python2 1
%{?!python_module:%define python_module() python-%{**} python3-%{**}}
+%define skip_python2 1
Name: python-feedparser
-Version: 6.0.0
+Version: 6.0.1
Release: 0
Summary: Universal Feed Parser Module for Python
License: BSD-2-Clause
++++++ feedparser-6.0.0.tar.gz -> feedparser-6.0.1.tar.gz ++++++
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/NEWS new/feedparser-6.0.1/NEWS
--- old/feedparser-6.0.0/NEWS 2020-09-12 21:27:17.000000000 +0200
+++ new/feedparser-6.0.1/NEWS 2020-09-15 13:50:57.000000000 +0200
@@ -1,5 +1,9 @@
coming in the next release:
+6.0.1 - 15 September 2020
+ * Remove all Python 2 compatibility code (#228)
+ * Add *python_requires* to ``setup.py`` (#231)
+
6.0.0 - 12 September 2020
* Support Python 3.6, 3.7, 3.8 and 3.9
* Drop support for Python 2.4 through 2.7, and Python 3.0 through 3.5
(#169)
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/PKG-INFO
new/feedparser-6.0.1/PKG-INFO
--- old/feedparser-6.0.0/PKG-INFO 2020-09-12 21:27:28.846880000 +0200
+++ new/feedparser-6.0.1/PKG-INFO 2020-09-15 13:51:18.969905000 +0200
@@ -1,6 +1,6 @@
Metadata-Version: 2.1
Name: feedparser
-Version: 6.0.0
+Version: 6.0.1
Summary: Universal feed parser, handles RSS 0.9x, RSS 1.0, RSS 2.0, CDF, Atom
0.3, and Atom 1.0 feeds
Home-page: https://github.com/kurtmckee/feedparser
Author: Kurt McKee
@@ -75,4 +75,5 @@
Classifier: Programming Language :: Python :: 3.9
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Text Processing :: Markup :: XML
+Requires-Python: >=3.6
Description-Content-Type: text/x-rst
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/__init__.py
new/feedparser-6.0.1/feedparser/__init__.py
--- old/feedparser-6.0.0/feedparser/__init__.py 2020-09-12 21:27:17.000000000
+0200
+++ new/feedparser-6.0.1/feedparser/__init__.py 2020-09-15 13:50:57.000000000
+0200
@@ -25,9 +25,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE."""
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
from .api import parse
from .datetimes import registerDateHandler
from .exceptions import *
@@ -35,7 +32,7 @@
__author__ = 'Kurt McKee <[email protected]>'
__license__ = 'BSD 2-clause'
-__version__ = '6.0.0'
+__version__ = '6.0.1'
# HTTP "User-Agent" header to send to servers when downloading feeds.
# If you are embedding feedparser in a larger application, you should
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/api.py
new/feedparser-6.0.1/feedparser/api.py
--- old/feedparser-6.0.0/feedparser/api.py 2020-09-01 05:42:10.000000000
+0200
+++ new/feedparser-6.0.1/feedparser/api.py 2020-09-15 13:49:58.000000000
+0200
@@ -26,29 +26,10 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
+import io
+import urllib.parse
import xml.sax
-try:
- from io import BytesIO as _StringIO
-except ImportError:
- # Python 2.7
- try:
- from cStringIO import StringIO as _StringIO
- except ImportError:
- from StringIO import StringIO as _StringIO
-
-try:
- import urllib.parse
-except ImportError:
- from urlparse import urlparse
-
- class urllib(object):
- class parse(object):
- urlparse = staticmethod(urlparse)
-
from .datetimes import registerDateHandler, _parse_date
from .encodings import convert_to_utf8
from .exceptions import *
@@ -63,14 +44,6 @@
from .urls import convert_to_idn, make_safe_absolute_uri
from .util import FeedParserDict
-bytes_ = type(b'')
-unicode_ = type('')
-try:
- unichr
- basestring
-except NameError:
- unichr = chr
- basestring = str
# List of preferred XML parsers, by SAX driver name. These will be tried
first,
# but if they're not installed, Python will keep searching through its own list
@@ -130,13 +103,13 @@
if request_headers is supplied it is a dictionary of HTTP request headers
that will override the values generated by FeedParser.
- :return: A :class:`StringIO.StringIO` or :class:`io.BytesIO`.
+ :return: A bytes object.
"""
if hasattr(url_file_stream_or_string, 'read'):
return url_file_stream_or_string.read()
- if isinstance(url_file_stream_or_string, basestring) \
+ if isinstance(url_file_stream_or_string, str) \
and urllib.parse.urlparse(url_file_stream_or_string)[0] in ('http',
'https', 'ftp', 'file', 'feed'):
return http.get(url_file_stream_or_string, etag, modified, agent,
referrer, handlers, request_headers, result)
@@ -145,7 +118,7 @@
with open(url_file_stream_or_string, 'rb') as f:
data = f.read()
except (IOError, UnicodeEncodeError, TypeError, ValueError):
- # if url_file_stream_or_string is a unicode object that
+ # if url_file_stream_or_string is a str object that
# cannot be converted to the encoding returned by
# sys.getfilesystemencoding(), a UnicodeEncodeError
# will be thrown
@@ -157,19 +130,19 @@
return data
# treat url_file_stream_or_string as string
- if not isinstance(url_file_stream_or_string, bytes_):
+ if not isinstance(url_file_stream_or_string, bytes):
return url_file_stream_or_string.encode('utf-8')
return url_file_stream_or_string
LooseFeedParser = type(
- str('LooseFeedParser'), # `str()` call required for Python 2.7
+ 'LooseFeedParser',
(_LooseFeedParser, _FeedParserMixin, _BaseHTMLProcessor, object),
{},
)
StrictFeedParser = type(
- str('StrictFeedParser'), # `str()` call required for Python 2.7
+ 'StrictFeedParser',
(_StrictFeedParser, _FeedParserMixin, xml.sax.handler.ContentHandler,
object),
{},
)
@@ -257,7 +230,7 @@
baseuri = make_safe_absolute_uri(href, contentloc) or
make_safe_absolute_uri(contentloc) or href
baselang = result['headers'].get('content-language', None)
- if isinstance(baselang, bytes_) and baselang is not None:
+ if isinstance(baselang, bytes) and baselang is not None:
baselang = baselang.decode('utf-8', 'ignore')
if not _XML_AVAILABLE:
@@ -277,14 +250,14 @@
saxparser.setContentHandler(feedparser)
saxparser.setErrorHandler(feedparser)
source = xml.sax.xmlreader.InputSource()
- source.setByteStream(_StringIO(data))
+ source.setByteStream(io.BytesIO(data))
try:
saxparser.parse(source)
except xml.sax.SAXException as e:
result['bozo'] = 1
result['bozo_exception'] = feedparser.exc or e
use_strict_parser = 0
- if not use_strict_parser and _SGML_AVAILABLE:
+ if not use_strict_parser:
feedparser = LooseFeedParser(baseuri, baselang, 'utf-8', entities)
feedparser.resolve_relative_uris = resolve_relative_uris
feedparser.sanitize_html = sanitize_html
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/datetimes/__init__.py
new/feedparser-6.0.1/feedparser/datetimes/__init__.py
--- old/feedparser-6.0.0/feedparser/datetimes/__init__.py 2020-09-01
05:42:10.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/datetimes/__init__.py 2020-09-15
13:49:58.000000000 +0200
@@ -25,8 +25,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-
from .asctime import _parse_date_asctime
from .greek import _parse_date_greek
from .hungarian import _parse_date_hungarian
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/datetimes/asctime.py
new/feedparser-6.0.1/feedparser/datetimes/asctime.py
--- old/feedparser-6.0.0/feedparser/datetimes/asctime.py 2020-09-01
05:42:10.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/datetimes/asctime.py 2020-09-15
13:49:58.000000000 +0200
@@ -25,9 +25,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
from .rfc822 import _parse_date_rfc822
_months = [
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/datetimes/greek.py
new/feedparser-6.0.1/feedparser/datetimes/greek.py
--- old/feedparser-6.0.0/feedparser/datetimes/greek.py 2020-09-01
05:42:10.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/datetimes/greek.py 2020-09-15
13:49:58.000000000 +0200
@@ -25,9 +25,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
import re
from .rfc822 import _parse_date_rfc822
@@ -56,13 +53,13 @@
}
_greek_wdays = {
- '\u039a\u03c5\u03c1': 'Sun', # caf5f1 in iso-8859-7
- '\u0394\u03b5\u03c5': 'Mon', # c4e5f5 in iso-8859-7
- '\u03a4\u03c1\u03b9': 'Tue', # d4f1e9 in iso-8859-7
- '\u03a4\u03b5\u03c4': 'Wed', # d4e5f4 in iso-8859-7
- '\u03a0\u03b5\u03bc': 'Thu', # d0e5ec in iso-8859-7
- '\u03a0\u03b1\u03c1': 'Fri', # d0e1f1 in iso-8859-7
- '\u03a3\u03b1\u03b2': 'Sat', # d3e1e2 in iso-8859-7
+ '\u039a\u03c5\u03c1': 'Sun', # caf5f1 in iso-8859-7
+ '\u0394\u03b5\u03c5': 'Mon', # c4e5f5 in iso-8859-7
+ '\u03a4\u03c1\u03b9': 'Tue', # d4f1e9 in iso-8859-7
+ '\u03a4\u03b5\u03c4': 'Wed', # d4e5f4 in iso-8859-7
+ '\u03a0\u03b5\u03bc': 'Thu', # d0e5ec in iso-8859-7
+ '\u03a0\u03b1\u03c1': 'Fri', # d0e1f1 in iso-8859-7
+ '\u03a3\u03b1\u03b2': 'Sat', # d3e1e2 in iso-8859-7
}
_greek_date_format_re =
re.compile(r'([^,]+),\s+(\d{2})\s+([^\s]+)\s+(\d{4})\s+(\d{2}):(\d{2}):(\d{2})\s+([^\s]+)')
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/datetimes/hungarian.py
new/feedparser-6.0.1/feedparser/datetimes/hungarian.py
--- old/feedparser-6.0.0/feedparser/datetimes/hungarian.py 2020-09-01
05:42:10.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/datetimes/hungarian.py 2020-09-15
13:49:58.000000000 +0200
@@ -25,9 +25,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
import re
from .w3dtf import _parse_date_w3dtf
@@ -48,7 +45,7 @@
'december': '12',
}
-_hungarian_date_format_re =
re.compile(r'(\d{4})-([^-]+)-(\d{,2})T(\d{,2}):(\d{2})((\+|-)(\d{,2}:\d{2}))')
+_hungarian_date_format_re =
re.compile(r'(\d{4})-([^-]+)-(\d{,2})T(\d{,2}):(\d{2})([+-](\d{,2}:\d{2}))')
def _parse_date_hungarian(date_string):
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/datetimes/iso8601.py
new/feedparser-6.0.1/feedparser/datetimes/iso8601.py
--- old/feedparser-6.0.0/feedparser/datetimes/iso8601.py 2020-09-01
05:42:10.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/datetimes/iso8601.py 2020-09-15
13:49:58.000000000 +0200
@@ -25,9 +25,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
import re
import time
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/datetimes/korean.py
new/feedparser-6.0.1/feedparser/datetimes/korean.py
--- old/feedparser-6.0.0/feedparser/datetimes/korean.py 2020-09-01
05:42:10.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/datetimes/korean.py 2020-09-15
13:49:58.000000000 +0200
@@ -25,9 +25,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
import re
from .w3dtf import _parse_date_w3dtf
@@ -55,8 +52,8 @@
if not m:
return
w3dtfdate =
'%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s:%(second)s%(zonediff)s' % \
- {'year': m.group(1), 'month': m.group(2), 'day': m.group(3),\
- 'hour': m.group(4), 'minute': m.group(5), 'second':
m.group(6),\
+ {'year': m.group(1), 'month': m.group(2), 'day': m.group(3),
+ 'hour': m.group(4), 'minute': m.group(5), 'second':
m.group(6),
'zonediff': '+09:00'}
return _parse_date_w3dtf(w3dtfdate)
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/datetimes/perforce.py
new/feedparser-6.0.1/feedparser/datetimes/perforce.py
--- old/feedparser-6.0.0/feedparser/datetimes/perforce.py 2020-09-01
05:42:10.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/datetimes/perforce.py 2020-09-15
13:49:58.000000000 +0200
@@ -25,14 +25,7 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
-try:
- import rfc822
-except ImportError:
- from email import _parseaddr as rfc822
-
+import email._parseaddr
import re
import time
@@ -48,6 +41,6 @@
dow, year, month, day, hour, minute, second, tz = m.groups()
months = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep',
'Oct', 'Nov', 'Dec']
new_date_string = "%s, %s %s %s %s:%s:%s %s" % (dow, day,
months[int(month) - 1], year, hour, minute, second, tz)
- tm = rfc822.parsedate_tz(new_date_string)
+ tm = email._parseaddr.parsedate_tz(new_date_string)
if tm:
- return time.gmtime(rfc822.mktime_tz(tm))
+ return time.gmtime(email._parseaddr.mktime_tz(tm))
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/datetimes/rfc822.py
new/feedparser-6.0.1/feedparser/datetimes/rfc822.py
--- old/feedparser-6.0.0/feedparser/datetimes/rfc822.py 2020-09-12
21:27:17.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/datetimes/rfc822.py 2020-09-15
13:49:58.000000000 +0200
@@ -25,9 +25,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
import datetime
timezone_names = {
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/datetimes/w3dtf.py
new/feedparser-6.0.1/feedparser/datetimes/w3dtf.py
--- old/feedparser-6.0.0/feedparser/datetimes/w3dtf.py 2020-09-01
05:42:10.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/datetimes/w3dtf.py 2020-09-15
13:49:58.000000000 +0200
@@ -25,9 +25,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
import datetime
timezonenames = {
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/encodings.py
new/feedparser-6.0.1/feedparser/encodings.py
--- old/feedparser-6.0.0/feedparser/encodings.py 2020-09-01
05:42:10.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/encodings.py 2020-09-15
13:49:58.000000000 +0200
@@ -26,9 +26,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
import cgi
import codecs
import re
@@ -43,12 +40,7 @@
lazy_chardet_encoding = None
else:
def lazy_chardet_encoding(data):
- chardet_encoding = chardet.detect(data)['encoding']
- if not chardet_encoding:
- chardet_encoding = ''
- if isinstance(chardet_encoding, bytes_):
- chardet_encoding = chardet_encoding.encode('ascii', 'ignore')
- return chardet_encoding
+ return chardet.detect(data)['encoding'] or ''
from .exceptions import (
CharacterEncodingOverride,
@@ -56,8 +48,6 @@
NonXMLContentType,
)
-bytes_ = type(b'')
-unicode_ = type('')
# Each marker represents some of the characters of the opening XML
# processing instruction ('<?xm') in the specified encoding.
@@ -193,7 +183,7 @@
http_content_type = http_headers.get('content-type') or ''
http_content_type, params = cgi.parse_header(http_content_type)
http_encoding = params.get('charset', '').replace("'", "")
- if isinstance(http_encoding, bytes_):
+ if isinstance(http_encoding, bytes):
http_encoding = http_encoding.decode('utf-8', 'ignore')
acceptable_content_type = 0
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/exceptions.py
new/feedparser-6.0.1/feedparser/exceptions.py
--- old/feedparser-6.0.0/feedparser/exceptions.py 2020-09-01
05:42:10.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/exceptions.py 2020-09-15
13:49:58.000000000 +0200
@@ -26,9 +26,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
__all__ = [
'ThingsNobodyCaresAboutButMe',
'CharacterEncodingOverride',
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/html.py
new/feedparser-6.0.1/feedparser/html.py
--- old/feedparser-6.0.0/feedparser/html.py 2020-09-01 05:42:10.000000000
+0200
+++ new/feedparser-6.0.1/feedparser/html.py 2020-09-15 13:49:58.000000000
+0200
@@ -25,18 +25,9 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
+import html.entities
import re
-try:
- from html.entities import name2codepoint
-except ImportError:
- # Python 2
- # noinspection PyUnresolvedReferences
- from htmlentitydefs import name2codepoint
-
from .sgml import *
_cp1252 = {
@@ -251,7 +242,7 @@
# Called for each entity reference, e.g. '©' will extract 'copy'
# Reconstruct the original entity reference.
- if ref in name2codepoint or ref == 'apos':
+ if ref in html.entities.name2codepoint or ref == 'apos':
self.pieces.append('&%s;' % ref)
else:
self.pieces.append('&%s' % ref)
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/http.py
new/feedparser-6.0.1/feedparser/http.py
--- old/feedparser-6.0.0/feedparser/http.py 2020-09-12 21:27:17.000000000
+0200
+++ new/feedparser-6.0.1/feedparser/http.py 2020-09-15 13:49:58.000000000
+0200
@@ -25,29 +25,19 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
+import base64
import datetime
import gzip
+import io
import re
import struct
-import zlib
-
-import base64
-from io import BytesIO as _StringIO
import urllib.parse
import urllib.request
+import zlib
from .datetimes import _parse_date
from .urls import convert_to_idn
-try:
- basestring
-except NameError:
- basestring = str
-
-bytes_ = type(b'')
# HTTP "Accept" header to send to servers when downloading feeds. If you don't
# want to send an Accept header, set this to None.
@@ -102,7 +92,7 @@
request.add_header('User-Agent', agent)
if etag:
request.add_header('If-None-Match', etag)
- if isinstance(modified, basestring):
+ if isinstance(modified, str):
modified = _parse_date(modified)
elif isinstance(modified, datetime.datetime):
modified = modified.utctimetuple()
@@ -158,7 +148,7 @@
auth =
base64.standard_b64encode(f'{url_pieces.username}:{url_pieces.password}').strip()
# iri support
- if not isinstance(url, bytes_):
+ if not isinstance(url, bytes):
url = convert_to_idn(url)
# try to open with urllib2 (to use optional headers)
@@ -175,7 +165,7 @@
# if feed is gzip-compressed, decompress it
if data and 'gzip' in result['headers'].get('content-encoding', ''):
try:
- data = gzip.GzipFile(fileobj=_StringIO(data)).read()
+ data = gzip.GzipFile(fileobj=io.BytesIO(data)).read()
except (EOFError, IOError, struct.error) as e:
# IOError can occur if the gzip header is bad.
# struct.error can occur if the data is damaged.
@@ -200,7 +190,7 @@
# save HTTP headers
if 'etag' in result['headers']:
etag = result['headers'].get('etag', '')
- if isinstance(etag, bytes_):
+ if isinstance(etag, bytes):
etag = etag.decode('utf-8', 'ignore')
if etag:
result['etag'] = etag
@@ -209,7 +199,7 @@
if modified:
result['modified'] = modified
result['modified_parsed'] = _parse_date(modified)
- if isinstance(f.url, bytes_):
+ if isinstance(f.url, bytes):
result['href'] = f.url.decode('utf-8', 'ignore')
else:
result['href'] = f.url
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/mixin.py
new/feedparser-6.0.1/feedparser/mixin.py
--- old/feedparser-6.0.0/feedparser/mixin.py 2020-09-12 21:27:17.000000000
+0200
+++ new/feedparser-6.0.1/feedparser/mixin.py 2020-09-15 13:49:58.000000000
+0200
@@ -25,21 +25,12 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
import base64
import binascii
import copy
+import html.entities
import re
-from xml.sax.saxutils import escape as _xmlescape
-
-try:
- from html.entities import name2codepoint, entitydefs
-except ImportError:
- # Python 2
- # noinspection PyUnresolvedReferences
- from htmlentitydefs import name2codepoint, entitydefs
+import xml.sax.saxutils
from .html import _cp1252
from .namespaces import _base, cc, dc, georss, itunes, mediarss, psc
@@ -48,15 +39,6 @@
from .urls import _urljoin, make_safe_absolute_uri, resolve_relative_uris
-bytes_ = type(b'')
-try:
- # Python 2
- # noinspection PyUnresolvedReferences,PyShadowingBuiltins
- chr = unichr
-except NameError:
- pass
-
-
class _FeedParserMixin(
_base.Namespace,
cc.Namespace,
@@ -237,7 +219,7 @@
# track xml:base and xml:lang
attrs_d = dict(attrs)
baseuri = attrs_d.get('xml:base', attrs_d.get('base')) or self.baseuri
- if isinstance(baseuri, bytes_):
+ if isinstance(baseuri, bytes):
baseuri = baseuri.decode(self.encoding, 'ignore')
# ensure that self.baseuri is always an absolute URI that
# uses a whitelisted URI scheme (e.g. not `javscript:`)
@@ -388,11 +370,11 @@
return self.handle_entityref(text)
else:
try:
- name2codepoint[ref]
+ html.entities.name2codepoint[ref]
except KeyError:
text = '&%s;' % ref
else:
- text = chr(name2codepoint[ref]).encode('utf-8')
+ text = chr(html.entities.name2codepoint[ref]).encode('utf-8')
self.elementstack[-1][2].append(text)
def handle_data(self, text, escape=1):
@@ -401,7 +383,7 @@
if not self.elementstack:
return
if escape and self.contentparams.get('type') ==
'application/xhtml+xml':
- text = _xmlescape(text)
+ text = xml.sax.saxutils.escape(text)
self.elementstack[-1][2].append(text)
def handle_comment(self, text):
@@ -423,7 +405,7 @@
# CDATA block began but didn't finish
k = len(self.rawdata)
return k
- self.handle_data(_xmlescape(self.rawdata[i+9:k]), 0)
+ self.handle_data(xml.sax.saxutils.escape(self.rawdata[i+9:k]), 0)
return k+3
else:
k = self.rawdata.find('>', i)
@@ -473,7 +455,7 @@
@staticmethod
def strattrs(attrs):
return ''.join(
- ' %s="%s"' % (t[0], _xmlescape(t[1], {'"': '"'}))
+ ' %s="%s"' % (t[0], xml.sax.saxutils.escape(t[1], {'"': '"'}))
for t in attrs
)
@@ -490,7 +472,7 @@
# Ensure each piece is a str for Python 3
for (i, v) in enumerate(pieces):
- if isinstance(v, bytes_):
+ if isinstance(v, bytes):
pieces[i] = v.decode('utf-8')
if self.version == 'atom10' and self.contentparams.get('type', 'text')
== 'application/xhtml+xml':
@@ -566,19 +548,19 @@
if element in self.can_contain_dangerous_markup:
output = _sanitize_html(output, self.encoding,
self.contentparams.get('type', 'text/html'))
- if self.encoding and isinstance(output, bytes_):
+ if self.encoding and isinstance(output, bytes):
output = output.decode(self.encoding, 'ignore')
# address common error where people take data that is already
# utf-8, presume that it is iso-8859-1, and re-encode it.
- if self.encoding in ('utf-8', 'utf-8_INVALID_PYTHON_3') and not
isinstance(output, bytes_):
+ if self.encoding in ('utf-8', 'utf-8_INVALID_PYTHON_3') and not
isinstance(output, bytes):
try:
output = output.encode('iso-8859-1').decode('utf-8')
except (UnicodeEncodeError, UnicodeDecodeError):
pass
# map win-1252 extensions to the proper code points
- if not isinstance(output, bytes_):
+ if not isinstance(output, bytes):
output = output.translate(_cp1252)
# categories/tags/keywords/whatever are handled in _end_category or
@@ -670,7 +652,7 @@
return False
# all entities must have been defined as valid HTML entities
- if any((e for e in re.findall(r'&(\w+);', s) if e not in entitydefs)):
+ if any((e for e in re.findall(r'&(\w+);', s) if e not in
html.entities.entitydefs)):
return False
return True
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/namespaces/_base.py
new/feedparser-6.0.1/feedparser/namespaces/_base.py
--- old/feedparser-6.0.0/feedparser/namespaces/_base.py 2020-09-01
05:42:10.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/namespaces/_base.py 2020-09-15
13:49:58.000000000 +0200
@@ -26,9 +26,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
import copy
from ..datetimes import _parse_date
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/namespaces/admin.py
new/feedparser-6.0.1/feedparser/namespaces/admin.py
--- old/feedparser-6.0.0/feedparser/namespaces/admin.py 2020-09-01
05:42:10.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/namespaces/admin.py 2020-09-15
13:49:58.000000000 +0200
@@ -26,9 +26,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
from ..util import FeedParserDict
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/namespaces/cc.py
new/feedparser-6.0.1/feedparser/namespaces/cc.py
--- old/feedparser-6.0.0/feedparser/namespaces/cc.py 2020-09-01
05:42:10.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/namespaces/cc.py 2020-09-15
13:49:58.000000000 +0200
@@ -26,9 +26,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
from ..util import FeedParserDict
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/namespaces/dc.py
new/feedparser-6.0.1/feedparser/namespaces/dc.py
--- old/feedparser-6.0.0/feedparser/namespaces/dc.py 2020-09-01
05:42:10.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/namespaces/dc.py 2020-09-15
13:49:58.000000000 +0200
@@ -26,9 +26,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
from ..datetimes import _parse_date
from ..util import FeedParserDict
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/namespaces/georss.py
new/feedparser-6.0.1/feedparser/namespaces/georss.py
--- old/feedparser-6.0.0/feedparser/namespaces/georss.py 2020-09-01
05:42:10.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/namespaces/georss.py 2020-09-15
13:49:58.000000000 +0200
@@ -26,8 +26,7 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
+# Required for Python 3.6 compatibility.
from __future__ import generator_stop
from ..util import FeedParserDict
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/namespaces/itunes.py
new/feedparser-6.0.1/feedparser/namespaces/itunes.py
--- old/feedparser-6.0.0/feedparser/namespaces/itunes.py 2020-09-12
21:27:17.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/namespaces/itunes.py 2020-09-15
13:49:58.000000000 +0200
@@ -26,9 +26,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
from ..util import FeedParserDict
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/namespaces/mediarss.py
new/feedparser-6.0.1/feedparser/namespaces/mediarss.py
--- old/feedparser-6.0.0/feedparser/namespaces/mediarss.py 2020-09-01
05:42:10.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/namespaces/mediarss.py 2020-09-15
13:49:58.000000000 +0200
@@ -26,9 +26,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
from ..util import FeedParserDict
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/namespaces/psc.py
new/feedparser-6.0.1/feedparser/namespaces/psc.py
--- old/feedparser-6.0.0/feedparser/namespaces/psc.py 2020-09-01
05:42:10.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/namespaces/psc.py 2020-09-15
13:49:59.000000000 +0200
@@ -26,9 +26,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
import datetime
import re
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/parsers/loose.py
new/feedparser-6.0.1/feedparser/parsers/loose.py
--- old/feedparser-6.0.0/feedparser/parsers/loose.py 2020-09-01
05:42:10.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/parsers/loose.py 2020-09-15
13:49:59.000000000 +0200
@@ -26,10 +26,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
-
class _LooseFeedParser(object):
contentparams = None
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/parsers/strict.py
new/feedparser-6.0.1/feedparser/parsers/strict.py
--- old/feedparser-6.0.0/feedparser/parsers/strict.py 2020-09-01
05:42:10.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/parsers/strict.py 2020-09-15
13:49:59.000000000 +0200
@@ -26,8 +26,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import, unicode_literals
-
from ..exceptions import UndeclaredNamespace
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/sanitizer.py
new/feedparser-6.0.1/feedparser/sanitizer.py
--- old/feedparser-6.0.0/feedparser/sanitizer.py 2020-09-12
21:27:17.000000000 +0200
+++ new/feedparser-6.0.1/feedparser/sanitizer.py 2020-09-15
13:49:59.000000000 +0200
@@ -25,13 +25,9 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
import re
from .html import _BaseHTMLProcessor
-from .sgml import _SGML_AVAILABLE
from .urls import make_safe_absolute_uri
@@ -882,8 +878,6 @@
def _sanitize_html(html_source, encoding, _type):
- if not _SGML_AVAILABLE:
- return html_source
p = _HTMLSanitizer(encoding, _type)
html_source = html_source.replace('<![CDATA[', '<![CDATA[')
p.feed(html_source)
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/sgml.py
new/feedparser-6.0.1/feedparser/sgml.py
--- old/feedparser-6.0.0/feedparser/sgml.py 2020-09-01 05:42:10.000000000
+0200
+++ new/feedparser-6.0.1/feedparser/sgml.py 2020-09-15 13:49:59.000000000
+0200
@@ -25,12 +25,11 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-
import re
+import sgmllib
+
__all__ = [
- '_SGML_AVAILABLE',
'sgmllib',
'charref',
'tagfind',
@@ -44,93 +43,56 @@
'endbracket',
]
-# sgmllib is not available by default in Python 3; if the end user doesn't have
-# it available then we'll lose illformed XML parsing and content sanitizing
-try:
- import sgmllib
-except ImportError:
- # This is probably Python 3, which doesn't include sgmllib anymore
- _SGML_AVAILABLE = 0
-
- # Mock sgmllib enough to allow subclassing later on
- class sgmllib(object):
- SGMLParseError = EnvironmentError
-
- class SGMLParser(object):
- lasttag = None
- rawdata = None
-
- def close(self):
- pass
-
- def feed(self, data):
- pass
-
- def goahead(self, i):
- pass
-
- def parse_declaration(self, i):
- pass
-
- def parse_starttag(self, i):
- pass
-
- def reset(self):
- pass
-
-else:
- _SGML_AVAILABLE = 1
-
- # sgmllib defines a number of module-level regular expressions that are
- # insufficient for the XML parsing feedparser needs. Rather than modify
- # the variables directly in sgmllib, they're defined here using the same
- # names, and the compiled code objects of several sgmllib.SGMLParser
- # methods are copied into _BaseHTMLProcessor so that they execute in
- # feedparser's scope instead of sgmllib's scope.
- charref = re.compile(r'&#(\d+|[xX][0-9a-fA-F]+);')
- tagfind = re.compile(r'[a-zA-Z][-_.:a-zA-Z0-9]*')
- attrfind = re.compile(
- r"""\s*([a-zA-Z_][-:.a-zA-Z_0-9]*)[$]?(\s*=\s*"""
- r"""('[^']*'|"[^"]*"|[][\-a-zA-Z0-9./,:;+*%?!&$()_#=~'"@]*))?"""
- )
-
- # Unfortunately, these must be copied over to prevent NameError exceptions
- entityref = sgmllib.entityref
- incomplete = sgmllib.incomplete
- interesting = sgmllib.interesting
- shorttag = sgmllib.shorttag
- shorttagopen = sgmllib.shorttagopen
- starttagopen = sgmllib.starttagopen
-
-
- class _EndBracketRegEx:
- def __init__(self):
- # Overriding the built-in sgmllib.endbracket regex allows the
- # parser to find angle brackets embedded in element attributes.
- self.endbracket = re.compile(
- r'('
- r"""[^'"<>]"""
- r"""|"[^"]*"(?=>|/|\s|\w+=)"""
- r"""|'[^']*'(?=>|/|\s|\w+=))*(?=[<>])"""
- r"""|.*?(?=[<>]"""
- r')'
- )
-
- def search(self, target, index=0):
- match = self.endbracket.match(target, index)
- if match is not None:
- # Returning a new object in the calling thread's context
- # resolves a thread-safety.
- return EndBracketMatch(match)
- return None
-
-
- class EndBracketMatch:
- def __init__(self, match):
- self.match = match
+# sgmllib defines a number of module-level regular expressions that are
+# insufficient for the XML parsing feedparser needs. Rather than modify
+# the variables directly in sgmllib, they're defined here using the same
+# names, and the compiled code objects of several sgmllib.SGMLParser
+# methods are copied into _BaseHTMLProcessor so that they execute in
+# feedparser's scope instead of sgmllib's scope.
+charref = re.compile(r'&#(\d+|[xX][0-9a-fA-F]+);')
+tagfind = re.compile(r'[a-zA-Z][-_.:a-zA-Z0-9]*')
+attrfind = re.compile(
+ r"""\s*([a-zA-Z_][-:.a-zA-Z_0-9]*)[$]?(\s*=\s*"""
+ r"""('[^']*'|"[^"]*"|[][\-a-zA-Z0-9./,:;+*%?!&$()_#=~'"@]*))?"""
+)
+
+# Unfortunately, these must be copied over to prevent NameError exceptions
+entityref = sgmllib.entityref
+incomplete = sgmllib.incomplete
+interesting = sgmllib.interesting
+shorttag = sgmllib.shorttag
+shorttagopen = sgmllib.shorttagopen
+starttagopen = sgmllib.starttagopen
+
+
+class _EndBracketRegEx:
+ def __init__(self):
+ # Overriding the built-in sgmllib.endbracket regex allows the
+ # parser to find angle brackets embedded in element attributes.
+ self.endbracket = re.compile(
+ r'('
+ r"""[^'"<>]"""
+ r"""|"[^"]*"(?=>|/|\s|\w+=)"""
+ r"""|'[^']*'(?=>|/|\s|\w+=))*(?=[<>])"""
+ r"""|.*?(?=[<>]"""
+ r')'
+ )
+
+ def search(self, target, index=0):
+ match = self.endbracket.match(target, index)
+ if match is not None:
+ # Returning a new object in the calling thread's context
+ # resolves a thread-safety.
+ return EndBracketMatch(match)
+ return None
+
+
+class EndBracketMatch:
+ def __init__(self, match):
+ self.match = match
- def start(self, n):
- return self.match.end(n)
+ def start(self, n):
+ return self.match.end(n)
- endbracket = _EndBracketRegEx()
+endbracket = _EndBracketRegEx()
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/urls.py
new/feedparser-6.0.1/feedparser/urls.py
--- old/feedparser-6.0.0/feedparser/urls.py 2020-09-01 05:42:10.000000000
+0200
+++ new/feedparser-6.0.1/feedparser/urls.py 2020-09-15 13:49:59.000000000
+0200
@@ -25,15 +25,8 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
import re
-
-try:
- import urllib.parse as urlparse
-except ImportError:
- import urlparse as urlparse
+import urllib.parse
from .html import _BaseHTMLProcessor
@@ -59,7 +52,7 @@
def _urljoin(base, uri):
uri = _urifixer.sub(r'\1\3', uri)
try:
- uri = urlparse.urljoin(base, uri)
+ uri = urllib.parse.urljoin(base, uri)
except ValueError:
uri = ''
return uri
@@ -70,7 +63,7 @@
# this function should only be called with a unicode string
# strategy: if the host cannot be encoded in ascii, then
# it'll be necessary to encode it in idn form
- parts = list(urlparse.urlsplit(url))
+ parts = list(urllib.parse.urlsplit(url))
try:
parts[1].encode('ascii')
except UnicodeEncodeError:
@@ -85,7 +78,7 @@
parts[1] = '.'.join(newhost)
if port:
parts[1] += ':' + port
- return urlparse.urlunsplit(parts)
+ return urllib.parse.urlunsplit(parts)
else:
return url
@@ -98,7 +91,7 @@
return rel or ''
if not rel:
try:
- scheme = urlparse.urlparse(base)[0]
+ scheme = urllib.parse.urlparse(base)[0]
except ValueError:
return ''
if not scheme or scheme in ACCEPTABLE_URI_SCHEMES:
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser/util.py
new/feedparser-6.0.1/feedparser/util.py
--- old/feedparser-6.0.0/feedparser/util.py 2020-09-01 05:42:10.000000000
+0200
+++ new/feedparser-6.0.1/feedparser/util.py 2020-09-15 13:49:59.000000000
+0200
@@ -25,9 +25,6 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
import warnings
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/feedparser.egg-info/PKG-INFO
new/feedparser-6.0.1/feedparser.egg-info/PKG-INFO
--- old/feedparser-6.0.0/feedparser.egg-info/PKG-INFO 2020-09-12
21:27:23.000000000 +0200
+++ new/feedparser-6.0.1/feedparser.egg-info/PKG-INFO 2020-09-15
13:51:13.000000000 +0200
@@ -1,6 +1,6 @@
Metadata-Version: 2.1
Name: feedparser
-Version: 6.0.0
+Version: 6.0.1
Summary: Universal feed parser, handles RSS 0.9x, RSS 1.0, RSS 2.0, CDF, Atom
0.3, and Atom 1.0 feeds
Home-page: https://github.com/kurtmckee/feedparser
Author: Kurt McKee
@@ -75,4 +75,5 @@
Classifier: Programming Language :: Python :: 3.9
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Text Processing :: Markup :: XML
+Requires-Python: >=3.6
Description-Content-Type: text/x-rst
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/setup.py
new/feedparser-6.0.1/setup.py
--- old/feedparser-6.0.0/setup.py 2020-09-12 21:27:17.000000000 +0200
+++ new/feedparser-6.0.1/setup.py 2020-09-15 13:49:59.000000000 +0200
@@ -59,6 +59,7 @@
platforms=['POSIX', 'Windows'],
packages=['feedparser', 'feedparser.datetimes', 'feedparser.namespaces',
'feedparser.parsers'],
install_requires=['sgmllib3k'],
+ python_requires='>=3.6',
keywords=['atom', 'cdf', 'feed', 'parser', 'rdf', 'rss'],
classifiers=[
'Development Status :: 5 - Production/Stable',
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/feedparser-6.0.0/tests/runtests.py
new/feedparser-6.0.1/tests/runtests.py
--- old/feedparser-6.0.0/tests/runtests.py 2020-09-12 21:27:17.000000000
+0200
+++ new/feedparser-6.0.1/tests/runtests.py 2020-09-15 13:49:59.000000000
+0200
@@ -23,15 +23,13 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
__author__ = "Kurt McKee <[email protected]>"
__license__ = "BSD 2-clause"
import codecs
import datetime
import glob
+import http.server
import io
import os
import posixpath
@@ -46,13 +44,6 @@
import xml.sax
import zlib
-# Account for stdlib differences between Python 2 and Python 3.
-try:
- from BaseHTTPServer import HTTPServer
- from SimpleHTTPServer import SimpleHTTPRequestHandler
-except ImportError:
- from http.server import HTTPServer, SimpleHTTPRequestHandler
-
import feedparser
import feedparser.api
import feedparser.datetimes
@@ -76,7 +67,7 @@
_HOST = '127.0.0.1' # also not really configurable
-class FeedParserTestRequestHandler(SimpleHTTPRequestHandler):
+class FeedParserTestRequestHandler(http.server.SimpleHTTPRequestHandler):
headers_re = re.compile(br"^Header:\s+([^:]+):(.+)$", re.MULTILINE)
def send_head(self):
@@ -93,7 +84,7 @@
self.send_response(304)
self.send_header('Content-type', 'text/xml')
self.end_headers()
- return feedparser.api._StringIO(b'')
+ return io.BytesIO(b'')
path = self.translate_path(self.path)
# the compression tests' filenames determine the header sent
if self.path.startswith('/tests/compression'):
@@ -142,7 +133,7 @@
self.httpd = None
def run(self):
- self.httpd = HTTPServer((_HOST, _PORT), FeedParserTestRequestHandler)
+ self.httpd = http.server.HTTPServer((_HOST, _PORT),
FeedParserTestRequestHandler)
self.ready.set()
while self.requests:
self.httpd.handle_request()
@@ -382,7 +373,7 @@
"""Ensure that `_open_resource()` interprets its arguments as URIs,
file-like objects, or in-memory feeds as expected"""
def test_fileobj(self):
- r = feedparser.api._open_resource(feedparser.api._StringIO(b''), '',
'', '', '', [], {}, {})
+ r = feedparser.api._open_resource(io.BytesIO(b''), '', '', '', '', [],
{}, {})
self.assertEqual(r, b'')
def test_feed(self):
@@ -755,7 +746,7 @@
doc = b"<feed>&illformed_charref</feed>"
# Importing lxml.etree currently causes libxml2 to
# throw SAXException instead of SAXParseException.
- feedparser.parse(feedparser.api._StringIO(doc))
+ feedparser.parse(io.BytesIO(doc))
self.assertTrue(True)
