X-Git-Url: https://plomlompom.com/repos/new_day?a=blobdiff_plain;f=plomlombot.py;h=a1ef7f8c3e2b60f9a61a4c2db1e8485e1b5ec5ae;hb=2623ca2bdf9d23e08c539ae68ad8521291bf2264;hp=5fcd517a95f563cfba7a00146d1e6359780a0472;hpb=20c385a79d109d1da623c517c9458d02e79c343c;p=plomlombot-irc.git diff --git a/plomlombot.py b/plomlombot.py index 5fcd517..a1ef7f8 100755 --- a/plomlombot.py +++ b/plomlombot.py @@ -6,8 +6,11 @@ import datetime import select import time import re -import urllib.request -import html +import requests +import bs4 +import random +import hashlib +import os # Defaults, may be overwritten by command line arguments. SERVER = "irc.freenode.net" @@ -66,7 +69,11 @@ 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 @@ -98,30 +105,87 @@ def lineparser_loop(io, nickname): def act_on_privmsg(tokens): + def notice(msg): + io.send_line("NOTICE " + target + " :" + msg) + def url_check(msg): - matches = re.findall("(https?://[^\s]+)", msg) - for i in range(len(matches)): - url = matches[i] + + def handle_url(url, show_url=False): + + def mobile_twitter_hack(url): + re1 = 'https?://(mobile.twitter.com/)[^/]+(/status/)' + re2 = 'https?://mobile.twitter.com/([^/]+)/status/([^\?]+)' + m = re.search(re1, url) + if m and m.group(1) == 'mobile.twitter.com/' \ + and m.group(2) == '/status/': + m = re.search(re2, url) + url = 'https://twitter.com/' + m.group(1) + '/status/' \ + + m.group(2) + handle_url(url, True) + return True + 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) - continue - content = webpage.read().decode(charset) - title = str(content).split('