X-Git-Url: https://plomlompom.com/repos/%7Broute%7D?a=blobdiff_plain;f=plomlombot.py;h=2b59a0b9a5bc5331c21988dbc8997b8dbefefff6;hb=9385b26b0c173828699e414544671f421bbff355;hp=a47158c302a3341cbe3e3777410b6e073c0a485d;hpb=f80a0c00f5961833279e2c95ea34ff0fc5ae42f7;p=plomlombot-irc.git diff --git a/plomlombot.py b/plomlombot.py index a47158c..2b59a0b 100755 --- a/plomlombot.py +++ b/plomlombot.py @@ -6,8 +6,8 @@ import datetime import select import time import re -import urllib.request -import html +import requests +import bs4 # Defaults, may be overwritten by command line arguments. SERVER = "irc.freenode.net" @@ -66,7 +66,11 @@ 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 +103,26 @@ 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.InvalidURL, + requests.exceptions.InvalidSchema) as error: + notice("TROUBLE FOLLOWING URL: " + str(error)) continue - content = webpage.read().decode(charset) - title = str(content).split('