CareerPlug Jobs API.

import requests
from bs4 import BeautifulSoup

company_slug = "bemobile"
url = f"https://{company_slug}.careerplug.com/jobs"

headers = {
    "User-Agent": "Mozilla/5.0 (compatible; JobScraper/1.0)",
    "Accept": "text/html",
}

response = requests.get(url, headers=headers, timeout=10)
response.raise_for_status()
soup = BeautifulSoup(response.text, "html.parser")
print(f"Fetched page: {response.url}")

# Find the job container (supports both modern and legacy layouts)
job_container = soup.select_one("#job_table, #job-list")

if job_container:
    job_links = job_container.select("div > a[href^='/jobs/']")
    jobs = []

    for link in job_links:
        title_elem = link.select_one(".job-title .name")
        location_elem = link.select_one(".job-location")

        jobs.append({
            "title": title_elem.get_text(strip=True) if title_elem else None,
            "location": location_elem.get_text(strip=True) if location_elem else None,
            "url": f"https://{company_slug}.careerplug.com{link['href']}",
            "job_id": link['href'].split('/')[-1],
        })

    print(f"Found {len(jobs)} jobs")
    for job in jobs[:3]:
        print(f"  - {job['title']} @ {job['location']}")

def fetch_job_details(job_url: str) -> dict:
    """Fetch full job details from a CareerPlug job page."""
    response = requests.get(job_url, headers=headers, timeout=10)
    response.raise_for_status()
    soup = BeautifulSoup(response.text, "html.parser")

    # Extract job details
    title = soup.select_one("h1")
    description = soup.select_one(".trix-content, .job-description, [class*='description']")
    location_info = soup.select_one("h1 + p, [class*='location']")

    # Fall back to the application page when the description is missing
    if description is None:
        apply_url = job_url.rstrip("/") + "/apps/new"
        apply_soup = BeautifulSoup(requests.get(apply_url, headers=headers, timeout=10).text, "html.parser")
        description = apply_soup.select_one(".trix-content, .job-description, [class*='description']")

    return {
        "title": title.get_text(strip=True) if title else None,
        "description": description.get_text(strip=True) if description else None,
        "description_html": str(description) if description else None,
        "location": location_info.get_text(strip=True) if location_info else None,
        "url": job_url,
    }

# Fetch details for the first job
if jobs:
    details = fetch_job_details(jobs[0]["url"])
    print(f"Title: {details['title']}")
    print(f"Location: {details['location']}")
    print(f"Description length: {len(details['description'] or '')} chars")

import time

def fetch_all_jobs(company_slug: str, max_pages: int = 10) -> list:
    """Fetch all jobs from a CareerPlug company with pagination."""
    all_jobs = []
    base_url = f"https://{company_slug}.careerplug.com/jobs"

    for page in range(1, max_pages + 1):
        url = f"{base_url}?page={page}" if page > 1 else base_url
        response = requests.get(url, headers=headers, timeout=10)

        if response.status_code in (403, 404):
            break  # 404 = unknown company; 403 = AWS ELB throttling

        soup = BeautifulSoup(response.text, "html.parser")
        job_container = soup.select_one("#job_table, #job-list")

        if not job_container:
            break

        job_links = job_container.select("div > a[href^='/jobs/']")

        if not job_links:
            break

        for link in job_links:
            title_elem = link.select_one(".job-title .name")
            location_elem = link.select_one(".job-location")

            all_jobs.append({
                "title": title_elem.get_text(strip=True) if title_elem else None,
                "location": location_elem.get_text(strip=True) if location_elem else None,
                "url": f"https://{company_slug}.careerplug.com{link['href']}",
            })

        print(f"Page {page}: Found {len(job_links)} jobs (total: {len(all_jobs)})")
        time.sleep(1)  # Be respectful

    return all_jobs

jobs = fetch_all_jobs("bemobile")
print(f"Total jobs collected: {len(jobs)}")