[회사원] 업무 코딩기록 - (Fitz, Pandas) pdf에서 표 추출(.csv)

# import package PyMuPDF and pandas

import fitz  

import pandas as pd

import os

# Define input and output directories

input_folder = r"C:\Users\user\Desktop\VSCode(python)\(CODE)PDF,OCR\pdf_raw"

output_folder = r"C:\Users\user\Desktop\VSCode(python)\(CODE)PDF,OCR\pdf_result"

# Create the output directory if it doesn't exist

os.makedirs(output_folder, exist_ok=True)

# Open the PDF document

doc = fitz.open(os.path.join(input_folder, "test.pdf"))

# Load a desired page. This works via 0-based numbers

page = doc[0]

# Look for tables on this page and display the table count

tabs = page.find_tables()

print(f"{len(tabs.tables)} table(s) on {page}")

# Check if there are any tables found

if len(tabs.tables) > 0:

    # Select the first table

    tab = tabs[0]

    # Convert the table to a pandas DataFrame

    df = tab.to_pandas()

    print("Table:")

    print(df)

    # Save the DataFrame to a CSV file in the output folder

    output_file = os.path.join(output_folder, "extracted_table.csv")

    df.to_csv(output_file, index=False)

    print(f"Table saved to {output_file}")

else:

    print("No tables found on the page.")

# Close the document

doc.close()