Spaces:
Sleeping
Sleeping
| import re | |
| import PyPDF2 | |
| import gradio as gr | |
| from transformers import pipeline | |
| from collections import Counter | |
| # Load the Hugging Face NER pipeline | |
| ner_pipeline = pipeline("ner", model="dslim/bert-base-NER", tokenizer="dslim/bert-base-NER", aggregation_strategy="simple") | |
| def clean_resume_text(text): | |
| """Clean resume text by removing unwanted characters and formatting.""" | |
| text = re.sub(r'http\S+', ' ', text) | |
| text = re.sub(r'#\S+', '', text) | |
| text = re.sub(r'@\S+', ' ', text) | |
| text = re.sub(r'[^\w\s]', ' ', text) | |
| text = re.sub(r'[^\x00-\x7f]', ' ', text) | |
| return re.sub(r'\s+', ' ', text).strip() | |
| def extract_resume_text(file): | |
| """Extract raw text from uploaded PDF file.""" | |
| try: | |
| reader = PyPDF2.PdfReader(file) | |
| text = "" | |
| for page in reader.pages: | |
| page_text = page.extract_text() | |
| if page_text: | |
| text += page_text + " " | |
| if not text.strip(): | |
| return None, "Error: No text extracted from PDF." | |
| return text, None | |
| except Exception as e: | |
| return None, f"Error reading PDF: {str(e)}" | |
| def classify_resume(entities): | |
| """Classify resume based on dominant entity types.""" | |
| orgs = [e['word'] for e in entities if e['entity_group'] == 'ORG'] | |
| locs = [e['word'] for e in entities if e['entity_group'] == 'LOC'] | |
| jobs = [e['word'] for e in entities if e['entity_group'] == 'MISC'] | |
| dominant_org = Counter(orgs).most_common(1) | |
| dominant_loc = Counter(locs).most_common(1) | |
| dominant_job = Counter(jobs).most_common(1) | |
| return { | |
| "Main_Organization": dominant_org[0][0] if dominant_org else "Unknown", | |
| "Main_Location": dominant_loc[0][0] if dominant_loc else "Unknown", | |
| "Possible_Job/Field": dominant_job[0][0] if dominant_job else "General" | |
| } | |
| def extract_entities_from_pdfs(files): | |
| """Process multiple resumes, extract entities, and classify.""" | |
| summary = {} | |
| for file in files: | |
| file_name = file.name.split("/")[-1] | |
| resume_text, error = extract_resume_text(file) | |
| if error: | |
| summary[file_name] = {"error": error} | |
| continue | |
| cleaned_text = clean_resume_text(resume_text) | |
| entities = ner_pipeline(cleaned_text) | |
| result = { | |
| "Persons": list({e["word"] for e in entities if e["entity_group"] == "PER"}), | |
| "Organizations": list({e["word"] for e in entities if e["entity_group"] == "ORG"}), | |
| "Locations": list({e["word"] for e in entities if e["entity_group"] == "LOC"}), | |
| "Other": list({e["word"] for e in entities if e["entity_group"] not in ["PER", "ORG", "LOC"]}), | |
| "Cleaned_Text": cleaned_text, | |
| "Classification": classify_resume(entities) | |
| } | |
| summary[file_name] = result | |
| return summary | |
| # Gradio UI | |
| iface = gr.Interface( | |
| fn=extract_entities_from_pdfs, | |
| inputs=gr.File(file_types=[".pdf"], label="Upload Resumes (PDF)", file_count="multiple"), | |
| outputs=gr.JSON(label="Resume Classification & Entity Summary"), | |
| title="📂 Multi-Resume Entity Extractor & Classifier", | |
| description="Upload multiple PDF resumes. This tool extracts text, identifies key entities, and classifies each resume by organizations, locations, and possible job/field." | |
| ) | |
| if __name__ == "__main__": | |
| iface.launch() | |