Model/backend/pashub_fetcher/spreadsheet.py

import re
from typing import Dict, List
from openpyxl import load_workbook

from backend.pashub_fetcher.job import Job


def extract_jobs(filepath: str) -> List[Job]:
    wb = load_workbook(filepath, data_only=True)
    ws = wb["filtered"]

    HEADER_ROW = 3

    headers: Dict[str, int] = {}
    for col in range(1, ws.max_column + 1):
        value = str(ws.cell(row=HEADER_ROW, column=col).value)
        if value:
            headers[value.strip()] = col

    name_col = headers["Name"]
    link_col = headers["PasHub Link"]

    jobs: List[Job] = []

    for row in range(HEADER_ROW + 1, ws.max_row + 1):
        name = ws.cell(row=row, column=name_col).value
        link = ws.cell(row=row, column=link_col).value

        if not name or not link:
            continue

        match = re.search(r"/jobs/([0-9a-fA-F\-]+)/", str(link))
        if not match:
            continue

        jobs.append(
            {
                "id": match.group(1),
                "address": str(name),
            }
        )

    return jobs