X-Git-Url: https://plomlompom.com/repos/%7Broute%7D?a=blobdiff_plain;ds=inline;f=plomlombot.py;h=f7c7e32899704b705baf8b8ca49ea16c0fd7ccb3;hb=a7db2ddce21f684abf6d835e9450fcf370caa5f2;hp=dc6577a554841a0a218f20c5ae936c142a54d12f;hpb=6b4d6c5c7ad1a3cd855572e54b43a72a60191d17;p=plomlombot-irc.git diff --git a/plomlombot.py b/plomlombot.py index dc6577a..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" @@ -16,9 +17,28 @@ TIMEOUT = 240 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 + class IO: def __init__(self, server, port, timeout): @@ -44,7 +64,7 @@ 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 @@ -64,11 +84,15 @@ 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 - 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 +103,10 @@ 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 +115,30 @@ 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) + + 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) \ - as error: - print("TROUBLE FOLLOWING URL: " + str(error)) + 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 - charset = webpage.info().get_content_charset() - if not charset: - charset="utf-8" - content_type = webpage.info().get_content_type() - if not content_type in ('text/html', 'text/xml', - 'application/xhtml+xml'): - print("TROUBLE INTERPRETING URL: bad content type " - + content_type) - continue - content = webpage.read().decode(charset) - title = str(content).split('