data_extraction_from_pdf.py

"""Read pdf files and extract tabular data."""
from tabula import read_pdf


def file_to_dataframe(file_path):
    """Read and save tables from pdf."""
    tables = read_pdf(file_path, multiple_tables=True)
    # extract and format potency table
    potency_table = tables[0]
    potency_table = potency_table.drop(potency_table.index[[0, 1]])
    potency_table = potency_table.drop(potency_table.columns[2], axis=1)
    potency_table.columns = ['cannabinoid', 'w/w']
    # extract and format terpenes table
    terpenes_table = tables[3]
    terpenes_table = terpenes_table.drop(terpenes_table.index[[0, 1]])
    terpenes_table = terpenes_table.drop(terpenes_table.columns[2], axis=1)
    terpenes_table.columns = ['terpenes', 'w/w']
    # save tables as csv
    potency_table.to_csv(file_path.replace('.pdf', '_potency.csv'))
    terpenes_table.to_csv(file_path.replace('.pdf', '_terpenes.csv'))