Extract and visualize geolocation from any text file

Abstract:

There are variety of text file formats such as PDF, HTML and more which contains words about locations(countries, cities, regions and more). GeoParser developed as one of sub-projects under DARPA Memex to help finding any geolocation information crawled website data. It is a web application benefiting from Apache Tika to extract locations from any text file format and visualize geolocations on the map.

https://github.com/MBoustani/GeoParser

https://github.com/chrismattmann/tika-python

http://www.darpa.mil/program/memex