X-Git-Url: https://plomlompom.com/repos/%7B%7B%20web_path%20%7D%7D/decks/%7B%7Bdeck_id%7D%7D/cards/%7B%7Bcard_id%7D%7D/day?a=blobdiff_plain;f=plomlombot.py;h=b45c67a7aa12feeee10695c218f6a05dfe1d1912;hb=d74caeac225204bc1f9e5a978678f741ac7dfaf3;hp=0b605e9946b04f79a8f3e843da56eee2b59b0169;hpb=0d17c0577b6e816dc1c6e02667fc03f74ef5f4a8;p=plomlombot-irc.git diff --git a/plomlombot.py b/plomlombot.py index 0b605e9..b45c67a 100755 --- a/plomlombot.py +++ b/plomlombot.py @@ -6,9 +6,11 @@ import datetime import select import time import re -import urllib.request -import http.client -import html +import requests +import bs4 +import random +import hashlib +import os # Defaults, may be overwritten by command line arguments. SERVER = "irc.freenode.net" @@ -103,36 +105,66 @@ def lineparser_loop(io, nickname): def act_on_privmsg(tokens): - def url_check(msg): - - def notice(msg): - io.send_line("NOTICE " + target + " :" + msg) + 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] - request = urllib.request.Request(url, headers={ - "User-Agent": "plomlombot" - }) try: - webpage = urllib.request.urlopen(request, timeout=15) - except (urllib.error.HTTPError, urllib.error.URLError, - UnicodeError, http.client.BadStatusLine) as error: + r = requests.get(url, timeout=15) + except (requests.exceptions.TooManyRedirects, + requests.exceptions.ConnectionError, + requests.exceptions.InvalidURL, + 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 content_type not in ('text/html', 'text/xml', - 'application/xhtml+xml'): - notice("TROUBLE READING PAGE TITLE: bad content type " - + content_type) - continue - content = webpage.read().decode(charset) - title = str(content).split('