llm modeli eğitilebilir mi

saçma sapan convert siteleriyle uğraşmak yerine şu betiği kullanmanız yeterli olacaktır,
ben ubuntunun varsayılan dosya yöneticisini kullandım seçim işlemi için,

görsel
import subprocess
import pdfplumber
import pandas as pd
import os

def pdf_to_excel(pdf_path, excel_path):
with pdfplumber.open(pdf_path) as pdf:
dfs = []

for page in pdf.pages:
tables = page.extract_tables()

for table in tables:
if len(table) > 1: # Ensure there is at least one row of data
# Use the first row as headers and the rest as data
df = pd.DataFrame(table[1:], columns=table[0])
# Ensure column names are unique by appending a number if necessary
df.columns = [f"{col}_{i}" if df.columns.duplicated().any() and df.columns.duplicated()[j] else col
for i, col in enumerate(df.columns) for j, _ in enumerate(df.columns) if i == j]
dfs.append(df)

if dfs: # Check if any DataFrames were created
combined_df = pd.concat(dfs, ignore_index=True)
combined_df.to_excel(excel_path, index=False)
else:
print("No tables found in the PDF.")

def excel_to_csv(excel_path, csv_path):
df = pd.read_excel(excel_path)
df.to_csv(csv_path, index=False)

def select_file_and_convert():
pdf_path = subprocess.check_output(['zenity', '--file-selection', '--title=Select PDF File', '--file-filter=*.pdf']).decode('utf-8').strip()

if pdf_path:
desktop_path = os.path.join(os.path.expanduser('~'), 'Masaüstü')
excel_path = os.path.join(desktop_path, 'output.xlsx')
csv_path = os.path.join(desktop_path, 'output.csv')

pdf_to_excel(pdf_path, excel_path)
excel_to_csv(excel_path, csv_path)

print(f"Conversion complete. Excel file saved to {excel_path} and CSV file saved to {csv_path}")

if __name__ == "__main__":
select_file_and_convert()