TextMaps

This is a repository accompanying our paper "Deep Neural Networks for Web Page Information Extraction".

Prerequisites

In order to run this project, you need to install following dependencies:

• Our build of Caffe
• [PhantomJS] (http://phantomjs.org/)

*Please note that you need to add PhantomJS to your PATH and pycaffe to your PYTHONPATH.

Demo

If you have dependencies installed, you can try to run demo by:

cd tools
python demo.py --url [URL_TO_SOME_PRODUCT_PAGE]

Data set

Data set will be available after paper publication. Thank you for your patience.