Convert a spreadsheet from pdf to csv

rh_pdf_csv

import pandas as pd
import tabula

def rh_pdf_to_csv(pdf_filepath, csv_filepath):
    df_list = tabula.read_pdf(pdf_filepath, pages='all', pandas_options={'header': None})

    df = pd.concat(df_list, axis=0, ignore_index=True)

    # Take the first row as header
    new_header = df.iloc[0]  # grab the first row for the header
    df = df[1:]  # take the data less the header row
    df.columns = new_header  # set the header row as the df header

    df.to_csv(csv_filepath, index=False)

# Usage
filepath = '/path/to/Robinhoodrh-gains-losses.pdf'
csv_filepath = '/path/to/Robinhoodrh-gains-losses.csv'

rh_pdf_to_csv(filepath, csv_filepath)
print('done!')