X-Git-Url: https://plomlompom.com/repos/?p=plomlombot-irc.git;a=blobdiff_plain;f=plomlombot.py;h=4befc396de3539871b95c1442bcbfd77b9e259b4;hp=f34d97a821378c5e092cf064a78a2137d82350c7;hb=25eb45ae6cb294744e92406acfa9fe931550ffcb;hpb=f093ae1177a3f7193b061febb74a249fc2e7a389 diff --git a/plomlombot.py b/plomlombot.py index f34d97a..4befc39 100755 --- a/plomlombot.py +++ b/plomlombot.py @@ -6,10 +6,11 @@ import datetime import select import time import re -import urllib.request -import http.client -import html -import html.parser +import requests +import bs4 +import random +import hashlib +import os # Defaults, may be overwritten by command line arguments. SERVER = "irc.freenode.net" @@ -19,22 +20,6 @@ USERNAME = "plomlombot" NICKNAME = USERNAME -class HTMLParser(html.parser.HTMLParser): - def __init__(self, html, tag): - super().__init__() - self._tag = "" - self.data = "" - self.feed(html) - def handle_starttag(self, tag, attrs): - if self.data == "": - 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 @@ -120,37 +105,55 @@ 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: - notice("TROUBLE READING PAGE TITLE: no charset in header") - continue - 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 = HTMLParser(content, "title").data - title = html.unescape(title) - notice("PAGE TITLE FOR URL: " + title) + title = bs4.BeautifulSoup(r.text).title + if title: + notice("PAGE TITLE: " + title.string.strip()) + else: + notice("PAGE HAS NO TITLE TAG") + + def command_check(msg): + if msg[0] != "!": + return + tokens = msg[1:].split() + hash_string = hashlib.md5(target.encode("utf-8")).hexdigest() + quotesfile_name = "quotes_" + hash_string + if tokens[0] == "addquote": + if not os.access(quotesfile_name, os.F_OK): + quotesfile = open(quotesfile_name, "w") + quotesfile.write("QUOTES FOR " + target + ":\n") + quotesfile.close() + quotesfile = open(quotesfile_name, "a") + quotesfile.write(str.join(" ", tokens[1:]) + "\n") + quotesfile.close() + quotesfile = open(quotesfile_name, "r") + lines = quotesfile.readlines() + quotesfile.close() + notice("ADDED QUOTE #" + str(len(lines) - 1)) + elif tokens[0] == "quote": + if not os.access(quotesfile_name, os.F_OK): + notice("NO QUOTES AVAILABLE") + return + quotesfile = open(quotesfile_name, "r") + lines = quotesfile.readlines() + quotesfile.close() + lines = lines[1:] + i = random.randrange(len(lines)) + notice("QUOTE #" + str(i + 1) + ": " + lines[i]) sender = "" for rune in tokens[0]: @@ -168,6 +171,7 @@ def lineparser_loop(io, nickname): if receiver != nickname: target = receiver msg = str.join(" ", tokens[3:])[1:] + command_check(msg) url_check(msg) while True: