X-Git-Url: https://plomlompom.com/repos/?p=plomlombot-irc.git;a=blobdiff_plain;f=plomlombot.py;h=f34d97a821378c5e092cf064a78a2137d82350c7;hp=0b605e9946b04f79a8f3e843da56eee2b59b0169;hb=f093ae1177a3f7193b061febb74a249fc2e7a389;hpb=0d17c0577b6e816dc1c6e02667fc03f74ef5f4a8 diff --git a/plomlombot.py b/plomlombot.py index 0b605e9..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 @@ -122,7 +139,8 @@ def lineparser_loop(io, nickname): 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'): @@ -130,7 +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)