JoblinkApply Jobs API.

import re

# JoblinkApply boards and jobs both live under /Joblink/{tenantId} (numeric).
def tenant_id_from_url(url: str) -> str:
    match = re.search(r"/Joblink/(\d+)", url)
    if not match:
        raise ValueError(f"No numeric JoblinkApply tenant in URL: {url}")
    return match.group(1)

tenant_id = tenant_id_from_url("https://www.joblinkapply.com/Joblink/6924")

import requests

BASE = "https://www.joblinkapply.com"
HEADERS = {"User-Agent": "Mozilla/5.0 (compatible; JoboBot/1.0)"}

def fetch_listings_html(tenant_id: str) -> str:
    url = (
        f"{BASE}/Joblink/{tenant_id}"
        "/Search/SearchWithFilters?WithinDistance=25&SortDirection=Descending"
    )
    resp = requests.get(url, headers=HEADERS, timeout=30)
    resp.raise_for_status()
    return resp.text

from bs4 import BeautifulSoup

JOB_PATH = re.compile(r"^/Joblink/(\d+)/Job/Index/(\d+)")

def parse_listings(html: str, tenant_id: str) -> list[dict]:
    soup = BeautifulSoup(html, "html.parser")
    jobs, seen = [], set()
    for anchor in soup.select("tr a[href]"):
        match = JOB_PATH.match(anchor.get("href", ""))
        if not match:
            continue
        href_tenant, job_id = match.group(1), match.group(2)
        # Defensive: only accept rows that belong to the requested tenant.
        if href_tenant != tenant_id or job_id in seen:
            continue
        seen.add(job_id)
        jobs.append({
            "job_id": job_id,
            "title": anchor.get_text(strip=True),
            "detail_url": f"{BASE}/Joblink/{tenant_id}/Job/Index/{job_id}",
        })
    return jobs

import json

def fetch_job_detail(tenant_id: str, job_id: str) -> dict:
    url = f"{BASE}/Joblink/{tenant_id}/Job/Index/{job_id}"
    resp = requests.get(url, headers=HEADERS, timeout=30)
    resp.raise_for_status()
    soup = BeautifulSoup(resp.text, "html.parser")

    posting = None
    for tag in soup.find_all("script", type="application/ld+json"):
        try:
            data = json.loads(tag.string or "")
        except (json.JSONDecodeError, TypeError):
            continue  # unescaped quotes in description can break the block
        for node in (data if isinstance(data, list) else [data]):
            if isinstance(node, dict) and node.get("@type") == "JobPosting":
                posting = node
                break

    posting = posting or {}
    heading = soup.select_one("h1#JobTitle") or soup.select_one("h1")
    title = posting.get("title") or (heading.get_text(strip=True) if heading else None)

    description = posting.get("description")
    if not description:
        section = (soup.select_one("section[aria-label='Job Summary']")
                   or soup.select_one("#JobSeekerContentArea"))
        description = section.get_text("\n", strip=True) if section else None

    org = posting.get("hiringOrganization") or {}
    return {
        "job_id": job_id,
        "title": title,
        "description": description,
        "company_name": org.get("name") if isinstance(org, dict) else None,
        "employment_type": posting.get("employmentType"),
        "date_posted": posting.get("datePosted"),
        "valid_through": posting.get("validThrough"),
        "apply_url": url,
    }