X-Git-Url: https://plomlompom.com/repos/%7B%7B%20web_path%20%7D%7D/decks/%7B%7Bdeck_id%7D%7D/cards/%7B%7Bcard_id%7D%7D/%7B%7Bdb.prefix%7D%7D/tasks?a=blobdiff_plain;f=plomlombot.py;h=089fa6f61997fabdfd7ba8bfe84a7d512960be25;hb=ca9116ba25fc5febad8aaa793270a67dff5a2a11;hp=c1c23089ba01450ef5f2cd686f000580e44398cb;hpb=0358a1448b3b715454461917cb2570f97ff44317;p=plomlombot-irc.git diff --git a/plomlombot.py b/plomlombot.py index c1c2308..089fa6f 100755 --- a/plomlombot.py +++ b/plomlombot.py @@ -6,9 +6,11 @@ import datetime import select import time import re -import urllib.request -import http.client -import html +import requests +import bs4 +import random +import hashlib +import os # Defaults, may be overwritten by command line arguments. SERVER = "irc.freenode.net" @@ -67,7 +69,11 @@ 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 @@ -99,30 +105,54 @@ def lineparser_loop(io, nickname): def act_on_privmsg(tokens): + def notice(msg): + io.send_line("NOTICE " + target + " :" + msg) + def url_check(msg): - matches = re.findall("(https?://[^\s]+)", 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, http.client.BadStatusLine) 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.InvalidURL, + requests.exceptions.InvalidSchema) as error: + notice("TROUBLE FOLLOWING URL: " + str(error)) continue - content = webpage.read().decode(charset) - title = str(content).split('