github/pelican
1
0
Fork 1
mirror of https://github.com/getpelican/pelican.git synced 2025-10-15 20:28:56 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix HTMLParser related deprecation warnings in Py3.4

Browse source
This commit is contained in:
Deniz Turgut 2014-06-11 15:58:06 -04:00
commit ce8574aff4
2 changed files with 10 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

12
pelican/readers.py
View file

@ -21,10 +21,7 @@ try:
from html import escape from html import escape
except ImportError: except ImportError:
from cgi import escape from cgi import escape
try: from six.moves.html_parser import HTMLParser
from html.parser import HTMLParser
except ImportError:
from HTMLParser import HTMLParser
from pelican import signals from pelican import signals
from pelican.contents import Page, Category, Tag, Author from pelican.contents import Page, Category, Tag, Author
@ -43,7 +40,6 @@ METADATA_PROCESSORS = {
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
class BaseReader(object): class BaseReader(object):
"""Base class to read files. """Base class to read files.
@ -231,7 +227,11 @@ class HTMLReader(BaseReader):
class _HTMLParser(HTMLParser): class _HTMLParser(HTMLParser):
def __init__(self, settings, filename): def __init__(self, settings, filename):
HTMLParser.__init__(self) try:
# Python 3.4+
HTMLParser.__init__(self, convert_charrefs=False)
except TypeError:
HTMLParser.__init__(self)
self.body = '' self.body = ''
self.metadata = {} self.metadata = {}
self.settings = settings self.settings = settings

9
pelican/tools/pelican_import.py
View file

@ -4,11 +4,10 @@
from __future__ import unicode_literals, print_function from __future__ import unicode_literals, print_function
import argparse import argparse
try: try:
# py3k import from html import unescape # py3.4+
from html.parser import HTMLParser
except ImportError: except ImportError:
# py2 import from six.moves.html_parser import HTMLParser
from HTMLParser import HTMLParser # NOQA unescape = HTMLParser().unescape
import os import os
import re import re
import subprocess import subprocess
@ -129,7 +128,7 @@ def wp2fields(xml, wp_custpost=False):
try: try:
# Use HTMLParser due to issues with BeautifulSoup 3 # Use HTMLParser due to issues with BeautifulSoup 3
title = HTMLParser().unescape(item.title.contents[0]) title = unescape(item.title.contents[0])
except IndexError: except IndexError:
title = 'No title [%s]' % item.find('post_name').string title = 'No title [%s]' % item.find('post_name').string
logger.warning('Post "%s" is lacking a proper title' % title) logger.warning('Post "%s" is lacking a proper title' % title)