From: Christian Heller Date: Tue, 19 Jan 2016 00:01:38 +0000 (+0100) Subject: Use proper HTML parsing for page title retrieval. X-Git-Url: https://plomlompom.com/repos/%7B%7Bprefix%7D%7D/tasks?a=commitdiff_plain;h=f093ae1177a3f7193b061febb74a249fc2e7a389;p=plomlombot-irc.git Use proper HTML parsing for page title retrieval. --- diff --git a/plomlombot.py b/plomlombot.py index 8ac8f01..f34d97a 100755 --- a/plomlombot.py +++ b/plomlombot.py @@ -9,6 +9,7 @@ import re import urllib.request import http.client import html +import html.parser # Defaults, may be overwritten by command line arguments. SERVER = "irc.freenode.net" @@ -18,6 +19,22 @@ USERNAME = "plomlombot" NICKNAME = USERNAME +class HTMLParser(html.parser.HTMLParser): + def __init__(self, html, tag): + super().__init__() + self._tag = "" + self.data = "" + self.feed(html) + def handle_starttag(self, tag, attrs): + if self.data == "": + 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 @@ -131,7 +148,7 @@ def lineparser_loop(io, nickname): + content_type) continue content = webpage.read().decode(charset) - title = str(content).split('')[1].split('')[0] + title = HTMLParser(content, "title").data title = html.unescape(title) notice("PAGE TITLE FOR URL: " + title)