Manatal Jobs API.

import requests

company_slug = "instaswim-llc"
url = f"https://www.careers-page.com/api/v1.0/c/{company_slug}/"

resp = requests.get(url, timeout=10)
resp.raise_for_status()  # 404 here means the company slug is wrong
company = resp.json()

print(company.get("name"), company.get("website"))

import requests

def fetch_manatal_jobs(company_slug: str) -> list[dict]:
    jobs = []
    page = 1
    while True:
        url = f"https://www.careers-page.com/api/v1.0/c/{company_slug}/jobs/"
        params = {
            "page": page,
            "page_size": 20,  # server hard-caps page_size at 20
            "ordering": "-is_pinned_in_career_page,-last_published_at",
        }
        resp = requests.get(url, params=params, timeout=10)
        resp.raise_for_status()
        data = resp.json()
        jobs.extend(data.get("results", []))
        if not data.get("next"):  # paginate until 'next' is null
            break
        page += 1
    return jobs

all_jobs = fetch_manatal_jobs("instaswim-llc")
print(f"Found {len(all_jobs)} jobs")

def parse_job(company_slug: str, job: dict) -> dict:
    job_hash = job["hash"]
    return {
        "external_id": job_hash,
        "title": (job.get("position_name") or "").strip(),
        "description_html": job.get("description") or "",
        "city": job.get("city"),
        "state": job.get("state"),
        "country": job.get("country"),
        "location": job.get("location_display"),
        "salary_min": job.get("salary_min"),
        "salary_max": job.get("salary_max"),
        "currency": job.get("currency_code"),  # ISO code in the API
        "salary_visible": job.get("is_salary_visible"),
        "listing_url": f"https://www.careers-page.com/{company_slug}/job/{job_hash}",
        "apply_url": f"https://www.careers-page.com/{company_slug}/job/{job_hash}/apply",
    }

jobs = [parse_job("instaswim-llc", j) for j in all_jobs if j.get("hash")]

import json
import re
import requests

JSON_LD_RE = re.compile(
    r'<script[^>]*type="application/ld\+json"[^>]*>(.*?)</script>',
    re.IGNORECASE | re.DOTALL,
)

def fetch_detail(listing_url: str) -> dict:
    html = requests.get(listing_url, timeout=10).text
    match = JSON_LD_RE.search(html)
    if not match:
        return {}
    try:
        ld = json.loads(match.group(1))
    except json.JSONDecodeError:
        return {}  # malformed JSON-LD is non-fatal
    return {
        "posted_at": ld.get("datePosted"),
        "closes_at": ld.get("validThrough"),
        "employment_type": ld.get("employmentType"),
    }

print(fetch_detail(jobs[0]["listing_url"]))

import time
import requests

def safe_get(url, **kwargs):
    resp = requests.get(url, timeout=10, **kwargs)
    if resp.status_code == 404:
        raise LookupError("Company or job not found")
    if resp.status_code in (401, 403):
        raise PermissionError("Blocked or authentication required")
    if resp.status_code == 429:
        time.sleep(5)
        return safe_get(url, **kwargs)
    resp.raise_for_status()
    time.sleep(0.25)  # ~250ms between requests, max ~5 concurrent details
    return resp