Spaces:
Sleeping
Sleeping
File size: 4,751 Bytes
cf8a522 8e1d297 9b62bb7 8e1d297 cf8a522 8e1d297 6088e9d 0755951 8e1d297 fda9c54 8e1d297 6088e9d 8e1d297 6088e9d 8e1d297 6088e9d 8e1d297 6088e9d 8e1d297 6088e9d 8e1d297 6088e9d 8e1d297 6088e9d 8e1d297 6088e9d 8e1d297 6088e9d 8e1d297 6088e9d 8e1d297 6088e9d |
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 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 |
import os
import re
import torch # Explicitly imported if you want to use torch directly
import tempfile
from io import BytesIO
import streamlit as st
from PIL import Image
from transformers import pipeline
from pdf2image import convert_from_bytes
#####################################
# Load the OCR Pipeline (Uses Torch)
#####################################
try:
# Ensure your transformers library is updated (>=4.x)
ocr_pipeline = pipeline("image-to-text", model="YouLiXiya/tinyllava-v1.0-1.1b-hf")
st.write("Model loaded successfully!")
except Exception as e:
st.error(f"Error loading model: {e}")
st.stop()
#####################################
# Utility: Convert PDF to Images
#####################################
def convert_pdf_to_images(pdf_bytes):
try:
images = convert_from_bytes(pdf_bytes)
return images
except Exception as e:
st.error(f"PDF conversion error: {e}")
return []
#####################################
# Pipeline: Extract Text with OCR Pipeline
#####################################
def extract_text_from_file(file_obj):
file_extension = os.path.splitext(file_obj.name)[1].lower()
full_text = ""
if file_extension == ".pdf":
file_bytes = file_obj.read()
images = convert_pdf_to_images(file_bytes)
for img in images:
result = ocr_pipeline(img)
if isinstance(result, list) and "text" in result[0]:
full_text += result[0]["text"] + "\n"
else:
try:
img = Image.open(file_obj)
result = ocr_pipeline(img)
if isinstance(result, list) and "text" in result[0]:
full_text = result[0]["text"]
except Exception as e:
full_text = f"Error processing image: {e}"
return full_text
#####################################
# Information Extraction Functions
#####################################
def extract_resume_info(text):
info = {
"Name": None,
"Age": None,
"Job Experience": None,
"Skills": None,
"Expected Industry/Direction": None,
}
# Extract name (e.g., "Name: John Doe")
name_match = re.search(r"[Nn]ame[:\-]\s*([A-Za-z\s]+)", text)
if name_match:
info["Name"] = name_match.group(1).strip()
else:
# Heuristic: pick the first sequence of capitalized words
potential_names = re.findall(r'\b[A-Z][a-z]+(?:\s+[A-Z][a-z]+)+\b', text)
if potential_names:
info["Name"] = potential_names[0]
# Extract age
age_match = re.search(r"[Aa]ge[:\-]\s*(\d{1,2})", text)
if age_match:
info["Age"] = age_match.group(1)
# Extract job experience (years)
exp_match = re.search(r"(\d+)\s+(?:years|yrs)\s+(?:of\s+)?experience", text, re.IGNORECASE)
if exp_match:
info["Job Experience"] = exp_match.group(1) + " years"
else:
exp_line = re.search(r"(Experience|Background)[:\-]\s*(.*)", text, re.IGNORECASE)
if exp_line:
info["Job Experience"] = exp_line.group(2).strip()
# Extract skills (e.g., "Skills: Python, Java, SQL")
skills_match = re.search(r"[Ss]kills[:\-]\s*(.+)", text)
if skills_match:
skills_text = skills_match.group(1)
skills = [s.strip() for s in re.split(r",|\n", skills_text) if s.strip()]
info["Skills"] = skills
# Extract expected industry/direction
industry_match = re.search(r"(Industry|Interest|Direction)[:\-]\s*(.+)", text, re.IGNORECASE)
if industry_match:
info["Expected Industry/Direction"] = industry_match.group(2).strip()
return info
#####################################
# Main Processing Logic
#####################################
def process_resume(file_obj):
if file_obj is None:
return None, None
resume_text = extract_text_from_file(file_obj)
resume_info = extract_resume_info(resume_text)
return resume_text, resume_info
#####################################
# Streamlit UI
#####################################
st.title("Resume Extraction and Information Parsing")
st.markdown("""
Upload a resume file (in PDF or image format) and the app will extract its text and parse critical candidate information.
""")
uploaded_file = st.file_uploader("Upload Resume (PDF or Image)", type=["pdf", "png", "jpg", "jpeg"])
if st.button("Extract Info"):
if uploaded_file is None:
st.error("Please upload a file first.")
else:
with st.spinner("Processing..."):
resume_text, resume_info = process_resume(uploaded_file)
st.subheader("Extracted Resume Text")
st.text_area("", resume_text, height=200)
st.subheader("Parsed Resume Information")
st.json(resume_info) |