PdftoTXT

import tabula
from tabulate import tabulate
import camelot
import os
os.environ['PATH'] += os.pathsep + r'D:\DEV\Ghostcript\gs10.01.2\bin'


def extract_lecturers_table(file_path):
    tables = tabula.read_pdf(file_path, pages='all')
    lecturers_table = tables[0].values.tolist()  # Załóżmy, że pierwsza tabela zawiera dane wykładowców
    return lecturers_table

def extract_schedule_table(file_path):
    tables = camelot.read_pdf(file_path, pages='all', backend='ghostscript')
    schedule_table = []
    for table in tables:
        table_data = table.df.iloc[:, :4].values.tolist()  # Załóżmy, że cztery kolumny zawierają godziny, daty i sale
        schedule_table.extend(table_data)
    return schedule_table

def save_table_to_txt(table_contents, output_file):
    table_str = tabulate(table_contents, headers="firstrow", tablefmt='grid')
    with open(output_file, 'w', encoding='utf-8') as file:
        file.write(table_str)

# Ścieżka do Twojego pliku PDF
pdf_file_path = r'C:\Users\deade\Desktop\inz_03072023\st-informatyka-sem-6.pdf'
output_file_path = r'C:\Users\deade\Desktop\tabela.txt'

# Ekstrahuj dane z tabel
lecturers_table = extract_lecturers_table(pdf_file_path)
schedule_table = extract_schedule_table(pdf_file_path)

# Wyświetl zawartość tabel
lecturers_table_str = tabulate(lecturers_table, headers="firstrow", tablefmt='grid')
print("Tabela wykładowców:")
print(lecturers_table_str)
print()

schedule_table_str = tabulate(schedule_table, headers=["Godzina", "Data", "Sala"], tablefmt='grid')
print("Tabela planu zajęć:")
print(schedule_table_str)

# Zapisz tabele do pliku tekstowego
save_table_to_txt(lecturers_table, output_file_path + '_wykladowcy.txt')
save_table_to_txt(schedule_table, output_file_path + '_plan_zajec.txt')