Building CDs hydrothermal synthesis database
The following repository contains the python scripts used to retrieve articles and extract data from them. The Jupyter notebooks contain the data analysis and code for evaluating extraction performance
This folder contains the code for article search to collect relevant DOIs
This folder contains code to convert html/xml articles to json format as well as code to find and extract specific article sections
This folder contains all notebooks with data analysis and extraction performance evaluation
This folder contains code for the scripts to extract data from text using a variety of text mining algorithms
This folder contains code to classify paragraphs into hydrothermal synthesis related and non-related
This folder contains code to retrieve full text articles using their DOI