Paycor Jobs API.

from urllib.parse import urlparse, parse_qs
import re

url = "https://recruitingbypaycor.com/career/CareerHome.action?clientId=8a7883c67239c84401727af009b53231"

parsed = urlparse(url)
assert parsed.netloc == "recruitingbypaycor.com", "Not a Paycor recruiting host"

client_id = (parse_qs(parsed.query).get("clientId") or [""])[0]
assert re.fullmatch(r"[0-9a-fA-F]{16,}", client_id), "Missing or malformed clientId"

listings_url = f"https://recruitingbypaycor.com/career/CareerHome.action?clientId={client_id}"
print(listings_url)

import requests

resp = requests.get(
    listings_url,
    headers={"Accept": "text/html,application/xhtml+xml"},
    timeout=15,
)
resp.raise_for_status()
page_html = resp.text

from bs4 import BeautifulSoup
from urllib.parse import urlparse, parse_qs
import html

soup = BeautifulSoup(page_html, "html.parser")

listings = []
seen = set()
for a in soup.select('a[href*="JobIntroduction.action"]'):
    href = html.unescape(a.get("href", ""))
    qs = parse_qs(urlparse(href).query)
    href_client = (qs.get("clientId") or [""])[0]
    job_id = (qs.get("id") or [""])[0]

    # Skip cross-client links and repeated job IDs.
    if href_client.lower() != client_id.lower() or not job_id or job_id in seen:
        continue
    seen.add(job_id)

    listings.append({
        "external_id": f"{client_id}:{job_id}",
        "job_id": job_id,
        "title": a.get_text(strip=True),
        "detail_url": (
            "https://recruitingbypaycor.com/career/JobIntroduction.action"
            f"?clientId={client_id}&id={job_id}&source=&lang=en"
        ),
    })

print(f"Template A found {len(listings)} jobs")

import re

if not listings:
    names = {}
    for dep, idx, title in re.findall(
        r'jobName\["([0-9a-fA-F]{16,})"\]\[(\d+)\s*-\s*1\]\s*=\s*"([^"]*)"',
        page_html,
    ):
        names[(dep, idx)] = title

    for dep, idx, job_id in re.findall(
        r'jobId\["([0-9a-fA-F]{16,})"\]\[(\d+)\s*-\s*1\]\s*=\s*"([0-9a-fA-F]{16,})"',
        page_html,
    ):
        if any(l["job_id"] == job_id for l in listings):
            continue
        listings.append({
            "external_id": f"{client_id}:{job_id}",
            "job_id": job_id,
            "title": names.get((dep, idx), ""),
            "detail_url": (
                "https://recruitingbypaycor.com/career/JobIntroduction.action"
                f"?clientId={client_id}&id={job_id}&source=&lang=en"
            ),
        })

    print(f"Template B found {len(listings)} jobs")

import re
import requests
from bs4 import BeautifulSoup

def fetch_detail(detail_url: str) -> dict | None:
    resp = requests.get(
        detail_url,
        headers={"Accept": "text/html,application/xhtml+xml"},
        timeout=15,
    )
    resp.raise_for_status()

    # Skip stale pages that no longer describe a live job.
    if re.search(r"this\s+job\s+is\s+no\s+longer\s+active", resp.text, re.I):
        return None

    soup = BeautifulSoup(resp.text, "html.parser")

    def cell(selector: str, strip_label: bool = False) -> str | None:
        el = soup.select_one(selector)
        if el is None:
            return None
        text = el.get_text(" ", strip=True)
        if strip_label and ":" in text:
            text = text.split(":", 1)[1].strip()
        return text or None

    desc_el = soup.select_one("#gnewtonJobDescriptionText")
    return {
        "title": cell("#gnewtonJobPosition", strip_label=True),
        "description_html": desc_el.decode_contents().strip() if desc_el else None,
        "locations": [el.get_text(" ", strip=True) for el in soup.select("#gnewtonJobLocationInfo")],
        "client_job_id": cell("#gnewtonJobID", strip_label=True),
        "openings": cell("#gnewtonJobOpening", strip_label=True),
    }

for job in listings[:3]:
    print(fetch_detail(job["detail_url"]))

import re

if not listings:
    if re.search(r'id\s*=\s*["\']gnewtonNoActiveJobs["\']', page_html, re.I):
        print("Board explicitly reports no active jobs — safe to record as empty")
    else:
        raise RuntimeError(
            "No jobs parsed and no empty-state sentinel found — "
            "treat as incomplete and retry, do not record zero jobs"
        )