Comeet Jobs API.

import requests
from bs4 import BeautifulSoup
import re
import json

company_slug = "monday"
company_uid = "41.00B"
url = f"https://www.comeet.com/jobs/{company_slug}/{company_uid}"

response = requests.get(url)
response.raise_for_status()
html = response.text

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

# Extract the embedded JSON data using regex
pattern = r'COMPANY_POSITIONS_DATA\s*=\s*(\[.*?\]);\s*</script>'
match = re.search(pattern, html, re.DOTALL)

if not match:
    raise ValueError("Could not find COMPANY_POSITIONS_DATA in HTML")

jobs_data = json.loads(match.group(1))
print(f"Found {len(jobs_data)} jobs")

for job in jobs_data:
    # Extract description from custom fields
    details = job.get("customFields", {}).get("details", [])

    description_parts = []
    for detail in details:
        field_name = detail.get("name", "").lower()
        field_value = detail.get("value", "")
        description_parts.append(f"**{detail.get('name')}**\n{field_value}")

    full_description = "\n\n".join(description_parts)

    parsed_job = {
        "id": job.get("uid"),
        "title": job.get("name"),
        "department": job.get("department"),
        "location": job.get("location", {}).get("name"),
        "city": job.get("location", {}).get("city"),
        "country": job.get("location", {}).get("country"),
        "is_remote": job.get("location", {}).get("isRemote", False),
        "employment_type": job.get("employmentType"),
        "experience_level": job.get("experienceLevel"),
        "workplace_type": job.get("workplaceType"),
        "url": job.get("urlComeetHostedPage"),
        "description": full_description,
        "updated_at": job.get("timeUpdated"),
    }

    print(f"  - {parsed_job['title']} ({parsed_job['location']})")

def discover_comeet_company(short_slug: str) -> dict:
    """Follow redirect to get full Comeet URL with company UID."""
    url = f"https://www.comeet.com/jobs/{short_slug}/"

    response = requests.get(url, allow_redirects=False)

    if response.status_code in (301, 302, 303, 307, 308):
        redirect_url = response.headers.get("Location", "")
        # Parse: https://www.comeet.com/jobs/monday/41.00B
        parts = redirect_url.rstrip("/").split("/")
        if len(parts) >= 2:
            return {
                "slug": parts[-2],
                "uid": parts[-1],
                "full_url": redirect_url
            }

    # No redirect, try fetching directly
    response = requests.get(url)
    soup = BeautifulSoup(response.text, "html.parser")

    # Look for COMPANY_DATA in the page
    company_pattern = r'COMPANY_DATA\s*=\s*(\{.*?\});'
    match = re.search(company_pattern, response.text, re.DOTALL)

    if match:
        company_data = json.loads(match.group(1))
        return {
            "slug": company_data.get("slug"),
            "uid": company_data.get("companyUid"),
            "name": company_data.get("name"),
        }

    return None

# Example usage
company_info = discover_comeet_company("monday")
print(f"Company: {company_info}")

import time
from typing import Optional, List, Dict, Any

def scrape_comeet_jobs(
    company_slug: str,
    company_uid: str,
    delay: float = 1.0
) -> List[Dict[str, Any]]:
    """Scrape all jobs from a Comeet company with error handling."""
    url = f"https://www.comeet.com/jobs/{company_slug}/{company_uid}"

    try:
        time.sleep(delay)  # Rate limiting
        response = requests.get(url, timeout=30)
        response.raise_for_status()
    except requests.RequestException as e:
        print(f"Error fetching {url}: {e}")
        return []

    # Extract embedded JSON
    pattern = r'COMPANY_POSITIONS_DATA\s*=\s*(\[.*?\]);\s*</script>'
    match = re.search(pattern, response.text, re.DOTALL)

    if not match:
        print(f"Could not find job data in {url}")
        return []

    try:
        jobs_data = json.loads(match.group(1))
    except json.JSONDecodeError as e:
        print(f"Error parsing JSON from {url}: {e}")
        return []

    # Process jobs
    jobs = []
    for job in jobs_data:
        jobs.append({
            "id": job.get("uid"),
            "title": job.get("name"),
            "department": job.get("department"),
            "location": job.get("location", {}).get("name", "Unknown"),
            "url": job.get("urlComeetHostedPage"),
        })

    return jobs

# Scrape multiple companies
companies = [
    ("monday", "41.00B"),
    ("fiverr", "60.002"),
    ("brightdata", "88.007"),
]

for slug, uid in companies:
    jobs = scrape_comeet_jobs(slug, uid)
    print(f"{slug}: {len(jobs)} jobs")