X-Git-Url: https://plomlompom.com/repos/?p=plomlombot-irc.git;a=blobdiff_plain;f=plomlombot.py;h=0f738f0003e5c8dca674e97b2df0bde7c9b9c460;hp=8ac8f01c00cf0cc4e00ad6e4a664a743926ac2f6;hb=057a62fe23a19af870b72684e50755c4e93821fc;hpb=73d956fc4322397624652d1a63341f3092988679 diff --git a/plomlombot.py b/plomlombot.py index 8ac8f01..0f738f0 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" @@ -103,37 +105,84 @@ def lineparser_loop(io, nickname): def act_on_privmsg(tokens): + def notice(msg): + io.send_line("NOTICE " + target + " :" + msg) + def url_check(msg): - def notice(msg): - io.send_line("NOTICE " + target + " :" + msg) + def handle_url(url): + + 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) + return True - 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 = str(content).split('