forked from tan/xkcdtextbot
135 lines
3.8 KiB
Python
135 lines
3.8 KiB
Python
#!/usr/bin/env python
|
|
# -*- coding: utf-8 -*-
|
|
|
|
from uuid import uuid4
|
|
from os import environ
|
|
from collections import namedtuple
|
|
from json import loads
|
|
|
|
import logging
|
|
|
|
from telegram import InlineQueryResultArticle
|
|
from telegram import InputTextMessageContent
|
|
from telegram import ParseMode
|
|
from telegram.ext import CommandHandler
|
|
from telegram.ext import InlineQueryHandler
|
|
from telegram.ext import Updater
|
|
|
|
import requests
|
|
from bs4 import BeautifulSoup
|
|
|
|
# Enable logging
|
|
logging.basicConfig(format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
|
|
level=logging.INFO)
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
Xkcd = namedtuple('Xkcd', ['title', 'link', 'transcript', 'alt', 'number'])
|
|
|
|
URL_FMT_STR = "http://www.ohnorobot.com/index.php?Search=Search&comic=56&s={}"
|
|
# FIXME HTML parsemode + escaping
|
|
MSG_FMT_STR = "[{number}]({link}): *{title}*\n\n_{alt}_"
|
|
XKCD_JSON_FMT_STR = "https://xkcd.com/{}/info.0.json"
|
|
MAX_SEARCH_RESULTS = 10
|
|
|
|
# blockquote element -> Xkcd
|
|
def parse_blockquote(elem):
|
|
children = list(elem.children)
|
|
title = children[0].text
|
|
link = 'https' + children[-1].text[4:]
|
|
|
|
number = link.rsplit('/', 2)[1]
|
|
info = loads(requests.get(XKCD_JSON_FMT_STR.format(number)).text)
|
|
alt = info['alt']
|
|
|
|
# TODO markdown bold the <span> matches
|
|
text = ''.join(
|
|
[e.text if hasattr(e, 'text') else e
|
|
for
|
|
e in children[1:-1]]
|
|
)
|
|
|
|
return Xkcd(title, link, text, alt, number)
|
|
|
|
# string -> [Xkcd]
|
|
def get_xkcds(text):
|
|
logger.info("getting %s", text)
|
|
if text == '':
|
|
return []
|
|
# TODO return newest when empty
|
|
soup = BeautifulSoup(requests.get(URL_FMT_STR.format(text)).text, "html.parser")
|
|
|
|
bqs = soup.find_all("blockquote")[:MAX_SEARCH_RESULTS]
|
|
logger.info(bqs)
|
|
return (parse_blockquote(e) for e in bqs)
|
|
|
|
|
|
# Define a few command handlers. These usually take the two arguments bot and
|
|
# update. Error handlers also receive the raised TelegramError object in error.
|
|
def start(bot, update):
|
|
"""Send a message when the command /start is issued."""
|
|
# TODO
|
|
update.message.reply_text('Hi!')
|
|
|
|
|
|
def help(bot, update):
|
|
"""Send a message when the command /help is issued."""
|
|
# TODO
|
|
update.message.reply_text('Help!')
|
|
|
|
def inlinequery(bot, update):
|
|
"""Handle the inline query."""
|
|
# TODO show transcript in result but not message?
|
|
query = update.inline_query.query
|
|
results = []
|
|
for xkcd in get_xkcds(query):
|
|
number = xkcd.number
|
|
link = xkcd.link
|
|
title = xkcd.title
|
|
alt = xkcd.alt
|
|
|
|
results.append(InlineQueryResultArticle(
|
|
id=uuid4(),
|
|
title=xkcd.title,
|
|
url=xkcd.link,
|
|
input_message_content=InputTextMessageContent(
|
|
MSG_FMT_STR.format(number=number, link=link, title=title, alt=alt),
|
|
parse_mode=ParseMode.MARKDOWN)))
|
|
|
|
update.inline_query.answer(results)
|
|
|
|
|
|
def error(bot, update, error):
|
|
"""Log Errors caused by Updates."""
|
|
logger.warning('Update "%s" caused error "%s"', update, error)
|
|
|
|
|
|
def main():
|
|
# Create the Updater and pass it your bot's token.
|
|
updater = Updater(environ["TOKEN"])
|
|
|
|
# Get the dispatcher to register handlers
|
|
dp = updater.dispatcher
|
|
|
|
# on different commands - answer in Telegram
|
|
dp.add_handler(CommandHandler("start", start))
|
|
dp.add_handler(CommandHandler("help", help))
|
|
|
|
# on noncommand i.e message - echo the message on Telegram
|
|
dp.add_handler(InlineQueryHandler(inlinequery))
|
|
|
|
# log all errors
|
|
dp.add_error_handler(error)
|
|
|
|
# Start the Bot
|
|
updater.start_polling()
|
|
|
|
# Block until the user presses Ctrl-C or the process receives SIGINT,
|
|
# SIGTERM or SIGABRT. This should be used most of the time, since
|
|
# start_polling() is non-blocking and will stop the bot gracefully.
|
|
updater.idle()
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|