X-Git-Url: https://plomlompom.com/repos/%7B%7Bdb.prefix%7D%7D/task?a=blobdiff_plain;f=plomlombot.py;h=0b605e9946b04f79a8f3e843da56eee2b59b0169;hb=0d17c0577b6e816dc1c6e02667fc03f74ef5f4a8;hp=5fcd517a95f563cfba7a00146d1e6359780a0472;hpb=20c385a79d109d1da623c517c9458d02e79c343c;p=plomlombot-irc.git diff --git a/plomlombot.py b/plomlombot.py index 5fcd517..0b605e9 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. @@ -66,7 +67,11 @@ 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 @@ -99,14 +104,21 @@ 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] + request = urllib.request.Request(url, headers={ + "User-Agent": "plomlombot" + }) try: - webpage = urllib.request.urlopen(url, timeout=15) + webpage = urllib.request.urlopen(request, timeout=15) except (urllib.error.HTTPError, urllib.error.URLError, - UnicodeError) as error: - print("TROUBLE FOLLOWING URL: " + str(error)) + UnicodeError, http.client.BadStatusLine) as error: + notice("TROUBLE FOLLOWING URL: " + str(error)) continue charset = webpage.info().get_content_charset() if not charset: @@ -114,14 +126,13 @@ def lineparser_loop(io, nickname): 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) + notice("TROUBLE READING PAGE TITLE: bad content type " + + content_type) continue content = webpage.read().decode(charset) title = str(content).split('