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
self._pingtest(send_ping)
return None
self.last_pong = time.time()
- received_runes = self.socket.recv(1024).decode("UTF-8")
+ received_bytes = self.socket.recv(1024)
+ try:
+ received_runes = received_bytes.decode("UTF-8")
+ except UnicodeDecodeError:
+ received_runes = received_bytes.decode("latin1")
if len(received_runes) == 0:
print("SOCKET CONNECTION BROKEN")
raise ExceptionForRestart
def act_on_privmsg(tokens):
def url_check(msg):
+
+ def notice(msg):
+ io.send_line("NOTICE " + target + " :" + msg)
+
matches = re.findall("(https?://[^\s>]+)", msg)
for i in range(len(matches)):
url = matches[i]
webpage = urllib.request.urlopen(request, timeout=15)
except (urllib.error.HTTPError, urllib.error.URLError,
UnicodeError, http.client.BadStatusLine) as error:
- print("TROUBLE FOLLOWING URL: " + str(error))
+ notice("TROUBLE FOLLOWING URL: " + str(error))
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'):
- print("TROUBLE INTERPRETING URL: bad content type "
- + content_type)
+ notice("TROUBLE READING PAGE TITLE: bad content type "
+ + 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)
- io.send_line("NOTICE " + target + " :page title for url: "
- + title)
+ notice("PAGE TITLE FOR URL: " + title)
sender = ""
for rune in tokens[0]: