Apploi Jobs API.

from urllib.parse import urlparse

HOST = "apply-jobs.apploi.com"

def parse_apploi(url: str):
    """Return (company_token, job_id) from any canonical Apploi URL."""
    parsed = urlparse(url)
    if parsed.netloc.lower() != HOST:
        return None
    segments = [s for s in parsed.path.split("/") if s]

    if len(segments) >= 2 and segments[0] == "jobs":
        return segments[1].lower(), None
    if len(segments) >= 4 and segments[0] == "job":
        # /job/{jobId}/{companyToken}/{slug}
        return segments[2].lower(), segments[1]
    return None

print(parse_apploi("https://apply-jobs.apploi.com/job/531470/lincoln-park/dietary-porter"))
# ('lincoln-park', '531470')

import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin

def fetch_board(session, company_token: str) -> list[dict]:
    board_url = f"https://{HOST}/jobs/{company_token}"
    resp = session.get(board_url, headers={"Accept": "text/html"}, timeout=30)
    resp.raise_for_status()

    soup = BeautifulSoup(resp.text, "html.parser")
    listings, seen = [], set()
    for anchor in soup.select("a[href]"):
        parsed = parse_apploi(urljoin(f"https://{HOST}", anchor["href"]))
        if not parsed:
            continue
        token, job_id = parsed
        if job_id is None or token != company_token or job_id in seen:
            continue
        seen.add(job_id)
        listings.append({
            "id": job_id,
            "title": " ".join(anchor.get_text().split()),
            "url": urljoin(f"https://{HOST}", anchor["href"]).split("?")[0],
        })
    return listings

session = requests.Session()
listings = fetch_board(session, "lincoln-park")
print(f"{len(listings)} open jobs")

import json
import time

def find_job_posting(html: str) -> dict | None:
    soup = BeautifulSoup(html, "html.parser")
    for tag in soup.find_all("script", type="application/ld+json"):
        try:
            data = json.loads(tag.string or "")
        except (json.JSONDecodeError, TypeError):
            continue
        for node in (data if isinstance(data, list) else [data]):
            if isinstance(node, dict) and node.get("@type") == "JobPosting":
                return node
    return None

def fetch_detail(session, listing: dict) -> dict | None:
    resp = session.get(listing["url"], headers={"Accept": "text/html"}, timeout=30)
    if resp.status_code in (404, 410):
        return None  # posting removed
    resp.raise_for_status()

    posting = find_job_posting(resp.text)
    if not posting:
        return None

    address = ((posting.get("jobLocation") or {}).get("address")) or {}
    return {
        "id": listing["id"],
        "title": posting.get("title") or listing["title"],
        "description_html": posting.get("description"),
        "employment_type": posting.get("employmentType"),
        "posted_at": posting.get("datePosted"),
        "closes_at": posting.get("validThrough"),
        "city": address.get("addressLocality"),
        "state": address.get("addressRegion"),
        "country": address.get("addressCountry"),
        "url": listing["url"],
        "apply_url": listing["url"],
    }

for listing in listings[:3]:
    print(fetch_detail(session, listing))
    time.sleep(0.25)

def resolve_short_link(session, url: str) -> dict | None:
    """Turn https://jobs.apploi.com/view/531470 into a board + job identity."""
    resp = session.get(url, headers={"Accept": "text/html"}, timeout=30,
                       allow_redirects=True)
    if not resp.ok:
        return None

    parsed = parse_apploi(str(resp.url))
    if not parsed:
        return None
    company_token, job_id = parsed
    original_id = [s for s in url.split("/") if s][-1]
    return {
        "company_token": company_token,
        "job_id": job_id or original_id,
        "board_url": f"https://{HOST}/jobs/{company_token}",
    }

print(resolve_short_link(session, "https://jobs.apploi.com/view/531470"))