src/resume_parser.py

import os
import re
import pdfplumber


class ResumeParser:
    def __init__(self, pdf_path: str):
        self.pdf_path = pdf_path

    def parse(self) -> str:
        if not os.path.exists(self.pdf_path):
            raise FileNotFoundError(
                f"Resume not found at '{self.pdf_path}'.\n"
                "Please place your PDF resume at: data/resume/resume.pdf"
            )

        text = ""
        with pdfplumber.open(self.pdf_path) as pdf:
            for page in pdf.pages:
                page_text = page.extract_text()
                if page_text:
                    text += page_text + "\n"

        if not text.strip():
            raise ValueError("Could not extract text from resume PDF. Make sure it's not scanned/image-only.")

        return self._clean_text(text)

    def _clean_text(self, text: str) -> str:
        # Remove excessive whitespace
        text = re.sub(r"\n{3,}", "\n\n", text)
        text = re.sub(r"[ \t]{2,}", " ", text)
        return text.strip()

    def get_contact_info(self, text: str) -> dict:
        info = {}
        email_match = re.search(r"[\w.+-]+@[\w-]+\.[a-zA-Z]{2,}", text)
        if email_match:
            info["email"] = email_match.group()

        phone_match = re.search(r"[\+]?[0-9]{1,4}[\s.-]?[0-9]{4,5}[\s.-]?[0-9]{4,5}", text)
        if phone_match:
            info["phone"] = phone_match.group()

        linkedin_match = re.search(r"linkedin\.com/in/[\w-]+", text, re.I)
        if linkedin_match:
            info["linkedin"] = "https://" + linkedin_match.group()

        return info