BW_Data_Extraction_1842_1848

This repository contains material required for the automated data extraction from the Bozner Wochenblatt for the years 1842-1848 (starting with 1856 the newspaper is called Bozner Zeitung).
The source code is stored in the Python Jupyter notebook BW_Data_Extraction_1842_1848.ipynb and is also provided as Python file. The folder trained_RF_algorithms_zipped.zip holds the 3 trained random forest classifier required for code execution. The folder was compressed using Microsoft Windows 10 Zip Tool and needs to be decompressed when used together with the source code. The png file included is an example of a data table published in the Bozner Wochenblatt (Source: Landesbibliothek Dr. Friedrich Teßmann, last access 15.9.2022. License: CC BY-NC-ND 4.0.) The csv file included contains the automatically extracted data from the png file.