import codecs
import os
import re
-from htmlentitydefs import name2codepoint
+try:
+ from html.entities import name2codepoint
+except ImportError:
+ from htmlentitydefs import name2codepoint
from compat import unicode, unichr
entity_re.match(part):
_part = name2codepoint.get(part[1:-1], None)
if _part is not None:
- part = unichr(_part).encode(charset)
+ part = unichr(_part)
output.append(part)
title = ''.join(output)
for part in num_entity_re.split(title):
if num_entity_re.match(part):
try:
- part = unichr(int(part[2:-1])).encode(charset)
+ part = unichr(int(part[2:-1]))
except UnicodeEncodeError:
pass # Leave the entity as is
output.append(part)
p, parser = _parsers[0]
if log: log(" Using %s" % p.__module__)
- title = parser.title
- if isinstance(title, unicode):
- if parser.charset:
- parser.title = title.encode(parser.charset)
- else:
- try:
- parser.title = title.encode('ascii')
- except UnicodeEncodeError:
- try:
- parser.title = title.encode(DEFAULT_CHARSET)
- except UnicodeEncodeError:
- parser.title = title.encode(universal_charset)
- parser.charset = universal_charset
- else:
- parser.charset = DEFAULT_CHARSET
- else:
- parser.charset = 'ascii'
+ #title = parser.title
+ #if isinstance(title, unicode):
+ # if parser.charset:
+ # parser.title = title.encode(parser.charset)
+ # else:
+ # try:
+ # parser.title = title.encode('ascii')
+ # except UnicodeEncodeError:
+ # try:
+ # parser.title = title.encode(DEFAULT_CHARSET)
+ # except UnicodeEncodeError:
+ # parser.title = title.encode(universal_charset)
+ # parser.charset = universal_charset
+ # else:
+ # parser.charset = DEFAULT_CHARSET
+ # else:
+ # parser.charset = 'ascii'
converted_title = title = parser.title
if title and (not parser.charset):
if log: log(" guessed charset: %s" % parser.charset)
# if log: log(" current charset: %s" % universal_charset)
if log: log(" title : %s" % title)
- if parser.charset != universal_charset:
- try:
- converted_title = title.decode(parser.charset).\
- encode(universal_charset)
- except UnicodeError:
- if log:
- log(" incorrect conversion from %s,"
- "converting from %s"
- % (parser.charset, DEFAULT_CHARSET))
- converted_title = \
- title.decode(DEFAULT_CHARSET, "replace").\
- encode(universal_charset, "replace")
- parser.charset = DEFAULT_CHARSET
- if log and (converted_title != title):
- log(" converted title: %s" % converted_title)
+ #if parser.charset != universal_charset:
+ # try:
+ # converted_title = title.decode(parser.charset).\
+ # encode(universal_charset)
+ # except UnicodeError:
+ # if log:
+ # log(" incorrect conversion from %s,"
+ # "converting from %s"
+ # % (parser.charset, DEFAULT_CHARSET))
+ # converted_title = \
+ # title.decode(DEFAULT_CHARSET, "replace").\
+ # encode(universal_charset, "replace")
+ # parser.charset = DEFAULT_CHARSET
+ #if log and (converted_title != title):
+ # log(" converted title: %s" % converted_title)
except LookupError:
if log: log(" unknown charset: '%s'" % parser.charset)
else:
log(" final title : %s" % final_title)
parser.title = final_title
- icon = parser.icon
- if isinstance(icon, unicode):
- try:
- parser.icon = icon.encode('ascii')
- except UnicodeEncodeError:
- if parser.charset:
- parser.icon = icon.encode(parser.charset)
+ #icon = parser.icon
+ #if isinstance(icon, unicode):
+ # try:
+ # parser.icon = icon.encode('ascii')
+ # except UnicodeEncodeError:
+ # if parser.charset:
+ # parser.icon = icon.encode(parser.charset)
return parser
def parse_filename(filename, charset=None, log=None):
- fp = open(filename, 'r')
+ fp = open(filename, 'rt')
try:
parser = parse_html(fp.read(), charset=charset, log=log)
finally: