File size: 2,404 Bytes
7627f9b 8a8733e 7627f9b 2543fdd 7627f9b 2543fdd 7627f9b 2543fdd 7627f9b 2543fdd 7627f9b 8a8733e 7627f9b 8a8733e 7627f9b 8a8733e 7627f9b 2543fdd 7627f9b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 |
import gradio as gr
import torch
from transformers import pipeline
import pdfplumber
import re
import pandas as pd
# Load pre-trained model for Named Entity Recognition (NER) to extract details
nlp = pipeline("ner", model="dbmdz/bert-large-cased-finetuned-conll03-english", framework="pt")
def extract_text_from_pdf(pdf_file):
"""Extract text from the uploaded PDF resume."""
with pdfplumber.open(pdf_file) as pdf:
text = ""
for page in pdf.pages:
text += page.extract_text()
return text
def parse_resume(resume_text):
"""Parse the resume and extract details like name, email, phone, and skills."""
# Define regex for phone and email extraction
phone_pattern = r'\(?\d{3}\)?[-.\s]?\d{3}[-.\s]?\d{4}'
email_pattern = r'[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}'
# Extract phone and email using regex
phone = re.findall(phone_pattern, resume_text)
email = re.findall(email_pattern, resume_text)
# Extract named entities for skills
entities = nlp(resume_text)
skills = [entity['word'] for entity in entities if 'MISC' in entity['entity']]
# Create a dictionary of parsed data (exclude Experience, Education, Certifications)
parsed_data = {
"Phone": phone[0] if phone else "Not found",
"Email": email[0] if email else "Not found",
"Skills": ", ".join(skills),
}
return parsed_data
def process_resumes(pdf_files):
"""Process multiple resumes and output a single Excel file."""
all_parsed_data = []
# Loop through each uploaded PDF file and parse the data
for pdf_file in pdf_files:
resume_text = extract_text_from_pdf(pdf_file)
parsed_info = parse_resume(resume_text)
all_parsed_data.append(parsed_info)
# Convert the parsed data into a pandas DataFrame
df = pd.DataFrame(all_parsed_data)
# Save the DataFrame to an Excel file
output_file = "parsed_resumes.xlsx"
df.to_excel(output_file, index=False)
return output_file
# Define Gradio interface
gr.Interface(
fn=process_resumes,
inputs=gr.File(file_count="multiple", label="Upload Resumes (PDFs)"),
outputs=gr.File(label="Download Parsed Data (Excel)"),
title="AI Resume Parser",
description="Upload multiple resumes (PDFs) to extract details like Name, Email, Phone, and Skills. The results will be saved in an Excel file."
).launch()
|