Comeet Jobs API.

import requests
import re
import json
from urllib.parse import quote

# Canonical listings URL: /jobs/{tenant}/{board_code}
listings_url = "https://www.comeet.com/jobs/monday/41.00B"

response = requests.get(listings_url, timeout=30)
response.raise_for_status()
html = response.text

print(f"Fetched board page: {len(html)} bytes")

match = re.search(r"COMPANY_DATA\s*=\s*(\{.*?\});", html, re.DOTALL)
if not match:
    raise ValueError("Comeet bootstrap (COMPANY_DATA) not found — check the board URL")

company = json.loads(match.group(1))
company_uid = company.get("company_uid")
token = company.get("token")
company_name = company.get("name")

if not company_uid or not token:
    raise ValueError("COMPANY_DATA did not expose company_uid/token")

print(f"Bootstrapped {company_name}: uid={company_uid}")

api_url = (
    f"https://www.comeet.co/careers-api/2.0/company/{quote(company_uid)}/positions"
    f"?token={quote(token)}&details=true"
)

api_response = requests.get(
    api_url,
    headers={"Accept": "application/json", "Referer": listings_url},
    timeout=30,
)
api_response.raise_for_status()

positions = api_response.json()  # JSON array of position objects
print(f"Fetched {len(positions)} positions")

def build_description(position):
    # v2 exposes details[] at the top level; older payloads nest it under custom_fields.
    details = position.get("details") or (position.get("custom_fields") or {}).get("details") or []
    parts = [
        d["value"]
        for d in sorted(details, key=lambda d: d.get("order") or 0)
        if d.get("value")  # some entries ship a null value upstream
    ]
    return "\n\n".join(parts)

jobs = []
for p in positions:
    uid = p.get("uid")
    if not uid:
        continue  # scraper rejects positions with no uid

    loc = p.get("location") or {}
    jobs.append({
        "id": uid,
        "title": (p.get("name") or "").strip(),
        "department": p.get("department"),
        "location": loc.get("name"),
        "city": loc.get("city"),
        "state": loc.get("state"),
        "country": loc.get("country"),
        "is_remote": loc.get("is_remote"),
        "employment_type": p.get("employment_type"),
        "experience_level": p.get("experience_level"),
        "workplace_type": p.get("workplace_type"),
        "listing_url": p.get("url_comeet_hosted_page") or p.get("url_active_page") or listings_url,
        "apply_url": p.get("url_active_page") or p.get("url_comeet_hosted_page") or listings_url,
        "description": build_description(p),
        "updated_at": p.get("time_updated"),
    })

for job in jobs:
    print(f"  - {job['title']} ({job['location']})")

import time

def scrape_comeet(listings_url: str, delay: float = 0.2):
    resp = requests.get(listings_url, timeout=30)
    if resp.status_code == 404:
        raise LookupError("Company not found on Comeet (HTTP 404)")
    resp.raise_for_status()

    m = re.search(r"COMPANY_DATA\s*=\s*(\{.*?\});", resp.text, re.DOTALL)
    if not m:
        raise ValueError("Comeet bootstrap did not expose company UID/token")
    company = json.loads(m.group(1))
    uid, token = company.get("company_uid"), company.get("token")
    if not uid or not token:
        raise ValueError("Missing company_uid or token in COMPANY_DATA")

    time.sleep(delay)  # backend paces requests ~200ms apart
    api_url = (
        f"https://www.comeet.co/careers-api/2.0/company/{quote(uid)}/positions"
        f"?token={quote(token)}&details=true"
    )
    api = requests.get(
        api_url,
        headers={"Accept": "application/json", "Referer": listings_url},
        timeout=30,
    )
    if api.status_code in (403, 429):
        raise RuntimeError(f"Comeet blocked/rate-limited (HTTP {api.status_code}) — back off")
    api.raise_for_status()

    positions = api.json()
    if not positions:
        return []  # authoritative empty array — tenant may have paused hiring

    seen, out = set(), []
    for p in positions:
        uid = p.get("uid")
        if not uid or uid in seen:
            continue
        seen.add(uid)
        out.append(p)
    return out

# Scrape several boards
for url in [
    "https://www.comeet.com/jobs/plus500_bulgaria/89.006",
    "https://www.comeet.com/jobs/seekingalpha/46.006",
]:
    try:
        results = scrape_comeet(url)
        print(f"{url}: {len(results)} positions")
    except Exception as e:
        print(f"{url}: {e}")