X-Git-Url: https://plomlompom.com/repos/%7B%7Bdb.prefix%7D%7D/task?a=blobdiff_plain;f=plomlombot.py;h=d6feb9377b4e36a1c5af96adb078f480c1c6f5fa;hb=bb71779ed0fc15241836b3430d9bf365d3f341f9;hp=dc6577a554841a0a218f20c5ae936c142a54d12f;hpb=6b4d6c5c7ad1a3cd855572e54b43a72a60191d17;p=plomlombot-irc.git diff --git a/plomlombot.py b/plomlombot.py index dc6577a..d6feb93 100755 --- a/plomlombot.py +++ b/plomlombot.py @@ -7,6 +7,7 @@ import select import time import re import urllib.request +import http.client import html # Defaults, may be overwritten by command line arguments. @@ -16,9 +17,11 @@ TIMEOUT = 240 USERNAME = "plomlombot" NICKNAME = USERNAME + class ExceptionForRestart(Exception): pass + class IO: def __init__(self, server, port, timeout): @@ -44,7 +47,7 @@ class IO: if len(msg.encode("utf-8")) > 510: print("NOT SENT LINE TO SERVER (too long): " + msg) print("LINE TO SERVER: " - + str(datetime.datetime.now()) + ": " + msg) + + str(datetime.datetime.now()) + ": " + msg) msg = msg + "\r\n" msg_len = len(msg) total_sent_len = 0 @@ -68,7 +71,7 @@ class IO: if len(received_runes) == 0: print("SOCKET CONNECTION BROKEN") raise ExceptionForRestart - self.rune_buffer += received_runes + self.rune_buffer += received_runes lines_split = str.split(self.rune_buffer, "\r\n") self.line_buffer += lines_split[:-1] self.rune_buffer = lines_split[-1] @@ -79,9 +82,10 @@ class IO: line = self._recv_line_wrapped(send_ping) if line: print("LINE FROM SERVER " + str(datetime.datetime.now()) + ": " + - line) + line) return line + def init_session(server, port, timeout, nickname, username, channel): print("CONNECTING TO " + server) io = IO(server, port, timeout) @@ -90,34 +94,35 @@ def init_session(server, port, timeout, nickname, username, channel): io.send_line("JOIN " + channel) return io + def lineparser_loop(io, nickname): def act_on_privmsg(tokens): 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) \ - as error: + 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" + charset = "utf-8" content_type = webpage.info().get_content_type() - if not content_type in ('text/html', 'text/xml', - 'application/xhtml+xml'): + if content_type not in ('text/html', 'text/xml', + 'application/xhtml+xml'): print("TROUBLE INTERPRETING URL: bad content type " - + content_type) + + content_type) continue content = webpage.read().decode(charset) title = str(content).split('