Create app.py

app.py

@@ -0,0 +1,87 @@
+import gradio as gr
+import torch
+from transformers import pipeline
+import pdfplumber
+import re
+import pandas as pd
+
+# Load a different pre-trained model for Named Entity Recognition (NER)
+nlp = pipeline("ner", model="huggingface/bert-base-cased", 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, skills, etc."""
+    # 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 (e.g., skills, education, and experience)
+    entities = nlp(resume_text)
+    
+    # For simplicity, we just list out the entities here
+    skills = []
+    experience = []
+    education = []
+    certifications = []
+
+    # Iterate through recognized entities and categorize them
+    for entity in entities:
+        if 'ORG' in entity['entity']:
+            experience.append(entity['word'])
+        elif 'MISC' in entity['entity']:
+            skills.append(entity['word'])
+        elif 'LOC' in entity['entity']:
+            education.append(entity['word'])
+        else:
+            certifications.append(entity['word'])
+
+    # Create a dictionary of parsed data
+    parsed_data = {
+        "Phone": phone[0] if phone else "Not found",
+        "Email": email[0] if email else "Not found",
+        "Skills": ", ".join(skills),
+        "Experience": ", ".join(experience),
+        "Education": ", ".join(education),
+        "Certifications": ", ".join(certifications)
+    }
+
+    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, Skills, Experience, Education, and Certifications. The results will be saved in an Excel file."
+).launch()