entity_re = re.compile("(&\w+;)")
num_entity_re = re.compile("(&#[0-9]+;)")
+
def recode_entities(title, charset):
output = []
for part in entity_re.split(title):
import os
BKMK_DEBUG_HTML_PARSERS = os.environ.get("BKMK_DEBUG_HTML_PARSERS")
+
def parse_html(html_text, charset=None, log=None):
if not parsers:
return None
parser.icon = icon.encode(parser.charset)
return parser
+
def parse_filename(filename, charset=None, log=None):
fp = open(filename, 'r')
try: