X-Git-Url: https://plomlompom.com/repos/day_todos?a=blobdiff_plain;f=plomlombot.py;h=7d0f5355a1f70eb1cc946249d1d5e76154b33b49;hb=4a2678aba39982c7912a697bf421d1fefb57ac41;hp=9a8a85329ffafb3c34642fa75def9b55f57422ac;hpb=b9a1f66a57f6225f8d50c63c7827e279d598bcc7;p=plomlombot-irc.git diff --git a/plomlombot.py b/plomlombot.py index 9a8a853..7d0f535 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) @@ -90,33 +94,39 @@ 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] + request = urllib.request.Request(url, headers={ + "User-Agent": "plomlombot" + }) try: - webpage = urllib.request.urlopen(url, timeout=15) - except urllib.error.HTTPError as error: + webpage = urllib.request.urlopen(request, timeout=15) + except (urllib.error.HTTPError, urllib.error.URLError, + UnicodeError, http.client.BadStatusLine, + UnicodeDecodeError) 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('