sociofillmore/femicides/extract_texts.py

import pandas as pd


def extract_texts():
    df = pd.read_excel("data/femicides/rai/EventiFemminicidio_from2015to2017_fonti.xlsx")
    print(df)
    for _, row in df.iterrows():
        source_id = row["ID"]
        text = f"{row['title']}\n\n{row['text']}"
        with open(f"output/femicides/extract_text/source_{source_id}.txt", "w", encoding="utf-8") as f:
            f.write(text)


if __name__ == '__main__':
    extract_texts()