import urllib.request
import http.client
import html
+import html.parser
# Defaults, may be overwritten by command line arguments.
SERVER = "irc.freenode.net"
NICKNAME = USERNAME
+class HTMLParser(html.parser.HTMLParser):
+ def __init__(self, html, tag):
+ super().__init__()
+ self._tag_to_check = tag
+ self._tag = ""
+ self.data = ""
+ self.feed(html)
+ def handle_starttag(self, tag, attrs):
+ if self.data == "" and tag == self._tag_to_check:
+ self._tag = tag
+ def handle_endtag(self, tag):
+ self._tag = ""
+ def handle_data(self, data):
+ if self._tag != "":
+ self.data = data
+
+
class ExceptionForRestart(Exception):
pass
continue
charset = webpage.info().get_content_charset()
if not charset:
- charset = "utf-8"
+ notice("TROUBLE READING PAGE TITLE: no charset in header")
+ continue
content_type = webpage.info().get_content_type()
if content_type not in ('text/html', 'text/xml',
'application/xhtml+xml'):
+ content_type)
continue
content = webpage.read().decode(charset)
- title = str(content).split('<title>')[1].split('</title>')[0]
+ title = HTMLParser(content, "title").data
title = html.unescape(title)
notice("PAGE TITLE FOR URL: " + title)