app.py

import gradio as gr
import re
from docx import Document
from PyPDF2 import PdfReader  # Use PdfReader from PyPDF2

# Function to extract text from a PDF file
def extract_text_from_pdf(pdf_file):
    text = ""
    pdf = PdfReader(pdf_file)
    for page in pdf.pages:
        text += page.extract_text()
    return text

# Function to extract text from a DOCX file
def extract_text_from_docx(docx_file):
    doc = Document(docx_file)
    text = "\n".join([para.text for para in doc.paragraphs])
    return text
def extract_text_from_pdf(pdf_file):
    text = ""
    pdf = PdfReader(pdf_file)
    
    if not pdf.pages:
        raise ValueError("The PDF file is empty.")
    
    for page in pdf.pages:
        text += page.extract_text()
    return text
# Function to extract information from a resume
def extract_info_from_resume(resume_path):
    if resume_path.name.endswith('.pdf'):
        text = extract_text_from_pdf(resume_path)
    elif resume_path.name.endswith('.docx'):
        text = extract_text_from_docx(resume_path)
    else:
        raise ValueError("Unsupported file format. Only PDF and DOCX are supported.")

    # Define regular expressions to extract information
    name_pattern = r"([A-Z][a-z]+(?: [A-Z][a-z]+)+)"
    email_pattern = r"[\w\.-]+@[\w\.-]+"
    phone_pattern = r"(\(?\d{3}\)?[-.\s]?\d{3}[-.\s]?\d{4})"

    name = re.search(name_pattern, text)
    email = re.search(email_pattern, text)
    phone = re.search(phone_pattern, text)

    extracted_info = {
        "Name": name.group() if name else "Name not found",
        "Email": email.group() if email else "Email not found",
        "Phone": phone.group() if phone else "Phone number not found",
    }

    return extracted_info

# Define a Gradio interface
iface = gr.Interface(
    fn=extract_info_from_resume,
    inputs=gr.inputs.File(type="file"),
    outputs="json"
)

# Deploy the Gradio interface
iface.launch(share=True)