AppliTrack (Frontline Education) Jobs API.

import re
import requests
from urllib.parse import quote

HOST = "www.applitrack.com"

def tenant_from_url(url: str) -> str | None:
    # Matches /{tenant}/onlineapp in the path (e.g. /mcminnville/onlineapp).
    m = re.search(r"/([^/]+)/onlineapp(?:/|$)", url, re.IGNORECASE)
    return m.group(1) if m else None

def listings_url(tenant: str) -> str:
    return f"https://{HOST}/{tenant}/onlineapp/jobpostings/Output.asp?all=1"

tenant = tenant_from_url("https://www.applitrack.com/mcminnville/onlineapp/default.aspx?all=1")
print(listings_url(tenant))

DOC_WRITE = re.compile(r"document\.write\('((?:\\.|[^'\\])*)'\)", re.DOTALL)
UNESCAPE = {"n": "\n", "r": "\r", "t": "\t", "'": "'", '"': '"', "\\": "\\", "/": "/"}

def js_unescape(s: str) -> str:
    out, i = [], 0
    while i < len(s):
        if s[i] == "\\" and i + 1 < len(s):
            out.append(UNESCAPE.get(s[i + 1], s[i + 1]))
            i += 2
        else:
            out.append(s[i])
            i += 1
    return "".join(out)

resp = requests.get(listings_url(tenant), timeout=20)
resp.raise_for_status()
html = "".join(js_unescape(m.group(1)) for m in DOC_WRITE.finditer(resp.text))

POSTING = re.compile(
    r"<ul\s+class=['\"]postingsList['\"]\s+id=['\"]p(\d+)_['\"]\s*>",
    re.IGNORECASE,
)

matches = list(POSTING.finditer(html))
blocks = []
for i, m in enumerate(matches):
    job_id = m.group(1)  # numeric AppliTrackJobId
    if not job_id.isdigit():
        continue
    end = matches[i + 1].start() if i + 1 < len(matches) else len(html)
    blocks.append((job_id, html[m.start():end]))

print(f"{len(blocks)} open postings")

from bs4 import BeautifulSoup

APPLY_ARGS = re.compile(
    r"applyFor\(\s*'([^']*)'\s*,\s*'([^']*)'\s*,\s*'([^']*)'\s*\)"
)

def parse_block(tenant: str, job_id: str, chunk: str) -> dict:
    soup = BeautifulSoup(chunk, "html.parser")

    title_cell = soup.select_one("table.title td#wrapword")
    title = title_cell.get_text(" ", strip=True) if title_cell else None

    fields = {}
    for li in soup.select("li"):
        label = li.select_one("span.label")
        if not label:
            continue
        key = label.get_text(strip=True).rstrip(":").strip()
        value = "/".join(
            n.get_text(" ", strip=True)
            for n in li.select("span.normal")
            if n.get_text(strip=True)
        )
        fields[key] = value or None

    first_choice = specialty = ""
    apply_btn = soup.select_one("input.ApplyButton, input[onclick*='applyFor']")
    if apply_btn:
        args = APPLY_ARGS.search(apply_btn.get("onclick", ""))
        if args:
            first_choice, specialty = args.group(2), args.group(3)

    return {
        "external_id": job_id,
        "title": title,
        "position_type": fields.get("Position Type"),
        "date_posted": fields.get("Date Posted"),
        "location": fields.get("Location"),
        "description": soup.get_text(" ", strip=True),
        "listing_url": f"https://{HOST}/{tenant}/onlineapp/jobpostings/view.asp?AppliTrackJobId={job_id}",
        "apply_url": (
            f"https://{HOST}/{tenant}/onlineapp/_application.aspx"
            f"?posJobCodes={job_id}"
            f"&posFirstChoice={quote(first_choice)}"
            f"&posSpecialty={quote(specialty)}"
        ),
    }

for job_id, chunk in blocks:
    job = parse_block(tenant, job_id, chunk)
    print(job["external_id"], job["title"], job["location"])

import time

def fetch_postings(tenant: str) -> str:
    resp = requests.get(listings_url(tenant), timeout=20)
    if resp.status_code == 404:
        raise LookupError(f"Tenant '{tenant}' not found")
    if resp.status_code == 401:
        # Only the private /onlineapp/api/jobs endpoint requires auth;
        # the public Output.asp feed should not return 401.
        raise PermissionError(f"Tenant '{tenant}' requires authentication")
    if resp.status_code in (403, 429):
        raise RuntimeError(f"Tenant '{tenant}' throttled or blocked (HTTP {resp.status_code})")
    resp.raise_for_status()
    time.sleep(0.5)  # single connection, ~500ms between requests
    return resp.text