A simple IRC bot which displays urls titles

ircbot_url_title.py

#!/usr/bin/env python3
#-*- encoding: utf-8 -*-

# ircbot_url_title.py
# Simple bot which displays urls titles
#
# Copyright (c) 2010 Mick@el and Zopieux
# Copyright (c) 2014 gustavi
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Lesser General Public License as
# published by the Free Software Foundation, either version 3 of
# the License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU Lesser General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.

import time
from urllib import parse
import re
import unicodedata
import difflib

import requests
from pypeul import *
from bs4 import BeautifulSoup
from itertools import groupby

# Bot informations
BOT_NAME = 'SimpleB00t'
BOT_CHAN = '##gustavi'
BOT_SERVER = 'irc.freenode.net'
BOT_PORT = 6667

# Main settings
settings = {
    'ratio' : 0.6, # Display or not title, use in SimpleUrlBot.show_url()
    'buffer_url_len' : 25,
    'title_len_min' : 18,
    'title_len_max' : 136,
    'content_length_max' : 2097152,
}

# Contain lasts urls
buffer_url = []

# The urls we can't displays title
exceptions_domain = [
    'docs.google.com',
    'translate.google.com',
    'paste.awesom.eu',
]

class SimpleUrlBot(IRC):

    def get_title(self, url):
        """
        Get the url title.  Return error message if http error or domain does
        not exist.
        """

        req = requests.get(url, stream=True, verify=False)
        try:
            if int(req.headers.get('content-length')) > settings['content_length_max']:
                return '', ''
        except TypeError:
            pass

        soup = BeautifulSoup(req.content)

        # Exclude binary
        try:
            title = soup.title.string.replace('\n', '')
        except AttributeError:
            return '', ''

        # Cut the title if too big
        if len(title) > settings['title_len_max']:
            title = title[:settings['title_len_max']] + '...'

        # Compute a compact redirection path
        hist = (parse.urlsplit(u.url).netloc for u in list(req.history) + [req])
        nodup_hist = ((k, sum(1 for i in g)) for k, g in groupby(hist))
        path = ' → '.join('%s%s' % (host, ' ×%d' % c if c > 1 else '') for host, c in nodup_hist)
        return '[{}] {}'.format(path, title), req.url

    def slugify(self, value):
        """
        Converts to lowercase, removes non-word characters (alphanumerics and
        underscores) and converts spaces to hyphens. Also strips leading and
        trailing whitespace.
        """

        value = unicodedata.normalize('NFKD', value).encode('ascii', 'ignore').decode('ascii')
        value = re.sub('[^\w\s-]', '', value).strip().lower()
        return re.sub('[-\s]+', '-', value)

    def show_url(self, url, title, final_url):
        """
        Displays title only if:
            - url does not contain title
            - url is not recent (is not in 'buffer_url')
            - lenght of title is bigger than 'url_title_min' (in settings)
            - not in exeptions list
        """

        # Check the min lenght
        if len(title) < settings['title_len_min']:
            return False

        # Check if not in exceptions list
        if final_url in exceptions_domain:
            return False

        url_dif = parse.urlsplit(url).path.split('/')[-1]
        title_dif = self.slugify(title)
        # Check if url does not contain title
        if difflib.SequenceMatcher(None, url_dif, title_dif).ratio() < settings['ratio']:
            # Check if is recent
            if final_url in buffer_url:
                return False
            # Check if buffer is over
            if len(buffer_url) == settings['buffer_url_len']:
                del buffer_url[0]
            buffer_url.append(final_url)
            return True
        return False

    def on_ready(self):
        """
        If you want your bot to join a channel when it connects, you should do
        that in the on_ready event handler.
        """

        self.join(BOT_CHAN)

    def on_channel_message(self, umask, target, msg):
        """
        Main event handler, called when someone speaks on a channel where the
        bot is.
        Just displays the title for each url.
        """

        urls = urls = re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', msg)
        for i in urls:
            title, final_url = self.get_title(i)
            if self.show_url(i, title, final_url) and title != '':
                self.message(target, title)

    def on_ctcp_version_request(self, umask, value):
        """
        There are event handlers for CTCP too.
        Here the bot replies its own __version__ string on a CTCP "version".
        """

        self.ctcp_reply(umask.nick,
                        'VERSION',
                        "{}, powered by pypeul and <3".format(BOT_NAME))

    def on_disconnected(self):
        logger.info('Disconnected. Trying to reconnect...')
        time_sleep = 30
        while True:
            try:
                self.connect(BOT_SERVER, BOT_PORT)
                self.ident(BOT_NAME)
                self.run()
                break
            except:
                logger.error('Attempt failed. Retrying in {}s...'.format(time_spleep))
            time_sleep += 30
            time.sleep(time_sleep)

if __name__ == '__main__':
    # Enable debug-level logging
    import logging
    logging.basicConfig(level=logging.DEBUG)

    # Instanciate our SimpleUrlBot class and let it run
    bot = SimpleUrlBot()
    bot.connect(BOT_SERVER, BOT_PORT)
    bot.ident(BOT_NAME)
    bot.run()