app.py

import gradio as gr
import pdfplumber
import pandas as pd
import re
import warnings
import logging

# Configure logging for pdfminer
logging.getLogger('pdfminer').setLevel(logging.ERROR)  # Only show errors, not warnings

def extract_text_from_pdf(pdf_path, suppress_warnings=True):
    """
    Extracts all text from a PDF, including text from nested tables and complex layouts.
    
    Parameters:
        pdf_path (str): Path to the PDF file
        suppress_warnings (bool): Whether to suppress PDF parsing warnings (default: True)
    """
    text = ""
    
    # Create a custom filter for the specific warning
    if suppress_warnings:
        warnings.filterwarnings("ignore", category=UserWarning, message="CropBox.*")
    
    with pdfplumber.open(pdf_path) as pdf:
        for page in pdf.pages:
            # Extract text from the page
            page_text = page.extract_text()
            if page_text:
                text += page_text + "\n"
            
            # Extract text from tables (if any)
            for table in page.extract_tables():
                for row in table:
                    for cell in row:
                        if isinstance(cell, str):
                            text += cell + " "
                    text += "\n"
    return text

def process_pdf(file):
    """
    Processes the uploaded PDF file and returns the extracted text.
    """
    if file is None:
        return "Please upload a PDF file."
    
    try:
        extracted_text = extract_text_from_pdf(file.name)
        return extracted_text
    except Exception as e:
        return f"Error processing PDF: {str(e)}"

# Create the Gradio interface
with gr.Blocks() as demo:
    gr.Markdown("# PDF Text Extractor")
    gr.Markdown("Upload a PDF file to extract its text content.")
    
    with gr.Row():
        with gr.Column():
            file_input = gr.File(label="Upload PDF", file_types=[".pdf"])
            submit_btn = gr.Button("Extract Text")
        with gr.Column():
            text_output = gr.Textbox(label="Extracted Text", lines=30, max_lines=50, interactive=False)
    
    submit_btn.click(
        fn=process_pdf,
        inputs=file_input,
        outputs=text_output
    )

# Run the app
if __name__ == "__main__":
    demo.launch()