X-Git-Url: https://plomlompom.com/repos/?p=plomlombot-irc.git;a=blobdiff_plain;f=plomlombot.py;h=f7c7e32899704b705baf8b8ca49ea16c0fd7ccb3;hp=a47158c302a3341cbe3e3777410b6e073c0a485d;hb=a7db2ddce21f684abf6d835e9450fcf370caa5f2;hpb=f80a0c00f5961833279e2c95ea34ff0fc5ae42f7 diff --git a/plomlombot.py b/plomlombot.py index a47158c..f7c7e32 100755 --- a/plomlombot.py +++ b/plomlombot.py @@ -6,8 +6,9 @@ import datetime import select import time import re -import urllib.request +import requests import html +import html.parser # Defaults, may be overwritten by command line arguments. SERVER = "irc.freenode.net" @@ -17,6 +18,23 @@ USERNAME = "plomlombot" 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 @@ -66,7 +84,11 @@ class IO: 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 @@ -99,29 +121,24 @@ def lineparser_loop(io, nickname): def act_on_privmsg(tokens): def url_check(msg): - matches = re.findall("(https?://[^\s]+)", 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] try: - webpage = urllib.request.urlopen(url, timeout=15) - except (urllib.error.HTTPError, urllib.error.URLError, - UnicodeError) as error: - print("TROUBLE FOLLOWING URL: " + str(error)) - continue - charset = webpage.info().get_content_charset() - if not charset: - charset = "utf-8" - 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) + r = requests.get(url, timeout=15) + except (requests.exceptions.TooManyRedirects, + requests.exceptions.ConnectionError, + requests.exceptions.InvalidSchema) as error: + notice("TROUBLE FOLLOWING URL: " + str(error)) continue - content = webpage.read().decode(charset) - title = str(content).split('')[1].split('')[0] + content = r.text + title = HTMLParser(content, "title").data title = html.unescape(title) - io.send_line("PRIVMSG " + target + " :page title for url: " - + title) + notice("PAGE TITLE FOR URL: " + title) sender = "" for rune in tokens[0]: @@ -141,7 +158,7 @@ def lineparser_loop(io, nickname): msg = str.join(" ", tokens[3:])[1:] url_check(msg) - while 1: + while True: line = io.recv_line() if not line: continue @@ -177,7 +194,7 @@ def parse_command_line_arguments(): return opts opts = parse_command_line_arguments() -while 1: +while True: try: io = init_session(opts.server, opts.port, opts.timeout, opts.nickname, opts.username, opts.CHANNEL)