__
      / \`\          __
      |  \ `\      /`/ \
      \_/`\  \-"-/` /\  \
           |       |  \  |
           (d     b)   \_/
           /       \
       ,".|.'.\_/.'.|.",
      /   /\' _|_ '/\   \
      |  /  '-`"`-'  \  |
      | |             | |
      | \    \   /    / |
       \ \    \ /    / /
        `"`\   :   /'"`
            `""`""`

TingMo utilizes the Minhash LSH model as implemented in datasketch to identify copycat domains in sublinear runtime. The code takes the set of unique bigrams from the input domains and queries to model to identify similar newly registered domains, as provided by whoisds. It also has the built-in capability of ignoring matches with newly registered domains that have a brand TLD, as those are generally benign.

git clone https://github.com/cvint13/tingmo.git
pip install -r requirements.txt
python app.py

This app will be hosted on Heroku shortly, hence the Procfile.

File upload/download option.