Coder Social home page Coder Social logo

shirosaidev / airbnbbot Goto Github PK

View Code? Open in Web Editor NEW
30.0 5.0 6.0 447 KB

Airbnb Messaging Bot (TOBOT) - AI assistant for Airbnb Hosts

License: Apache License 2.0

Python 100.00%
bot airbnb ai machine-learning nltk sklearn python chatbot messaging auto-responser chat-bot

airbnbbot's Introduction

Airbnb Messaging Bot (TOBOT)

Hi, I'm TOBOT. I'll respond to all your guest requests, so you don't have to. I'm an intelligent property manager for Airbnb Hosts. I make you more productive by managing your short term rentals. My goal is to get you more guests and make you more money. Download my beta software, I'm ready to help.

License Release Sponsor Patreon Donate PayPal

What is Tobot?

Tobot is an intelligent Airbnb host assistant which uses AI and machine learning. It will try to reply to all your guest messages. It can send replies to your guests for commonly asked questions and also send messages for new booking instructions and check out day messages, etc.. It's written in Python, you can run it on your Mac/Linux/Windows computer or in cloud such as AWS.

Tobot is still in very early beta development and not all functionality is working/tested.

TOBOT terminal

TOBOT cli

Patreon

If you are a fan of the project or using Tobot and it's helping you host your guests, please consider becoming a Patron to help advance Tobot.

Requirements

  • Python 3. (tested with Python 3.6.5)
  • nltk python module
  • requests python module
  • beautifulsoup4 python module
  • textblob python module
  • sklearn python module

Download

$ git clone https://github.com/shirosaidev/airbnbbot.git
$ cd airbnbbot

Download latest version

How to use

Install python requirements using pip

$ pip install -r requirements.txt

Copy config.py.sample to config.py and edit.

Copy corpus file tobot_corpus.txt.sample to tobot_corpus.txt.

Edit tobot_corpus.txt and create word and sentence tokens. Corpus file is the base brain for the bot which contains words/sentences used by nltk and sklearn to help the bot respond to questions.

Set environment variables for Airbnb login username and password (you can also set these in config.py).

$ export TOBOT_LOGIN=<airbnb_login_username>
$ export TOBOT_PASSWORD=<airbnb_login_password>

Set environment variables for Airbnb api key and oauth token. If you don't know these, don't set now and TOBOT will ask you if you want to look them up. (you can also set these in config.py)

$ export TOBOT_APIKEY=<airbnb_apikey>
$ export TOBOT_OAUTHTOKEN=<airbnb_oauthtoken>

Start up TOBOT:

$ python airbnb_bot.py

On first start up tobot_db.sqlite (sqlite3) database will be created in same directory. This database is where TOBOT stores new things it learns and associations between sentences and words.

Options/Settings

By default, Tobot runs in testing and training mode. This is helpful for the first few days or so to test and train Tobot. To turn off these modes, set training and testing to False in config file.

Tobot will send replies to new guests that have approved bookings. To turn this off set send_new_booking_msg to False in config.

Tobot also sends messages to guests in the morning on their check out day. To turn this off set send_checkout_msg to False in config.

airbnbbot's People

Contributors

shirosaidev avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

airbnbbot's Issues

Can't get OAUTHTOKEN

Hi @shirosaidev ~

I checked oauth_token function, and print body from "body = json.loads(src)"
It's show...
body:{'error_code': 420, 'error': 'unknown_error', 'error_message': 'Unable to perform action. Please try again through the website or contact support if you need immediate assistance.'}

Where is the app?

This looks like a great project based on the readme and I'd love to contribute but I don't see any code! Please let me know if you're planning on publishing what you have so far. Cheers!

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.