resume_parser.py

import os
import re
import tempfile
import pytesseract
import PyPDF2
import docx

from PIL import Image
from pdf2image import convert_from_path


def clean_text(text):
    if not text:
        return ""
    text = str(text)
    text = re.sub(r"\s+", " ", text)
    return text.strip()


def extract_text_from_image(file_path):
    try:
        img = Image.open(file_path)
        text = pytesseract.image_to_string(img)
        return clean_text(text)
    except:
        return ""


def extract_text_from_docx(file_path):
    try:
        doc = docx.Document(file_path)
        text = " ".join([p.text for p in doc.paragraphs])
        return clean_text(text)
    except:
        return ""


def extract_text_from_pdf(file_path):
    text = ""

    try:
        with open(file_path, "rb") as f:
            reader = PyPDF2.PdfReader(f)

            for page in reader.pages:
                page_text = page.extract_text()
                if page_text:
                    text += page_text + " "
    except:
        pass

    if len(text.strip()) < 100:
        try:
            images = convert_from_path(file_path)

            for image in images:
                with tempfile.NamedTemporaryFile(suffix=".png") as tmp:
                    image.save(tmp.name)
                    text += extract_text_from_image(tmp.name)
        except:
            pass

    return clean_text(text)


def parse_resume(file_path):

    ext = os.path.splitext(file_path)[1].lower()

    if ext == ".pdf":
        return extract_text_from_pdf(file_path)

    if ext in [".docx", ".doc"]:
        return extract_text_from_docx(file_path)

    if ext in [".png", ".jpg", ".jpeg"]:
        return extract_text_from_image(file_path)

    return ""