git-svn-id: file:///home/phd/archive/SVN/bookmarks_db/trunk@184
fdd5c36f-1aea-0310-aeeb-
c58d7e2b6c23
-from htmlentitydefs import entitydefs
+from htmlentitydefs import name2codepoint
entity_re = re.compile("(&\w+;)")
num_entity_re = re.compile("(&#[0-9]+;)")
entity_re = re.compile("(&\w+;)")
num_entity_re = re.compile("(&#[0-9]+;)")
for part in entity_re.split(title):
if part not in ("&", "<", ">", ""e;", " ") and \
entity_re.match(part):
for part in entity_re.split(title):
if part not in ("&", "<", ">", ""e;", " ") and \
entity_re.match(part):
- part = entitydefs.get(part[1:-1], part)
+ part = unichr(name2codepoint.get(part[1:-1], part)).encode(charset)
+ title = ''.join(output)
- output2 = []
- for part in num_entity_re.split(''.join(output)):
+ output = []
+ for part in num_entity_re.split(title):
if num_entity_re.match(part):
try:
part = unichr(int(part[2:-1])).encode(charset)
except UnicodeEncodeError:
pass # Leave the entity as is
if num_entity_re.match(part):
try:
part = unichr(int(part[2:-1])).encode(charset)
except UnicodeEncodeError:
pass # Leave the entity as is
- return ''.join(output2)
def parse_html(filename, charset=None, log=None):
def parse_html(filename, charset=None, log=None):