Jobvite Jobs API.

import requests
from bs4 import BeautifulSoup

company_slug = "nutanix"
url = f"https://jobs.jobvite.com/{company_slug}"

response = requests.get(url, timeout=10)
response.raise_for_status()

soup = BeautifulSoup(response.text, "html.parser")
print(f"Page loaded: {len(response.text)} bytes")

import re

# Find all job links on the page
job_links = soup.find_all("a", href=re.compile(r"/job/[a-z0-9]{9}"))

jobs = []
for link in job_links:
    href = link.get("href", "")
    # Extract job ID from URL like "/nutanix/job/ow6lzfwg"
    match = re.search(r"/job/([a-z0-9]{9})", href)
    if match:
        job_id = match.group(1)
        jobs.append({
            "id": job_id,
            "title": link.get_text(strip=True),
            "url": f"https://jobs.jobvite.com{href}"
        })

print(f"Found {len(jobs)} jobs")
for job in jobs[:5]:
    print(f"  - {job['title']} ({job['id']})")

import time

def get_all_jobs(company_slug: str) -> list:
    base_url = f"https://jobs.jobvite.com/{company_slug}/search"
    all_jobs = []
    page = 0

    while True:
        url = f"{base_url}/?p={page}"
        response = requests.get(url, timeout=10)
        soup = BeautifulSoup(response.text, "html.parser")

        # Find job links on this page
        job_links = soup.find_all("a", href=re.compile(r"/job/[a-z0-9]{9}"))

        if not job_links:
            break

        for link in job_links:
            href = link.get("href", "")
            match = re.search(r"/job/([a-z0-9]{9})", href)
            if match:
                all_jobs.append({
                    "id": match.group(1),
                    "title": link.get_text(strip=True),
                    "url": f"https://jobs.jobvite.com{href}"
                })

        print(f"Page {page}: found {len(job_links)} jobs")
        page += 1
        time.sleep(0.5)  # Be respectful

    return all_jobs

def get_job_details(company_slug: str, job_id: str) -> dict:
    url = f"https://jobs.jobvite.com/{company_slug}/job/{job_id}"
    response = requests.get(url, timeout=10)
    soup = BeautifulSoup(response.text, "html.parser")

    # Extract structured data from known CSS classes
    title_elem = soup.find("h2", class_="jv-header")
    meta_elem = soup.find("p", class_="jv-job-detail-meta")
    desc_elem = soup.find("div", class_="jv-job-detail-description")

    job = {
        "id": job_id,
        "url": url,
        "title": title_elem.get_text(strip=True) if title_elem else None,
        "description_html": str(desc_elem) if desc_elem else None,
    }

    # Parse metadata (category, location, req number)
    if meta_elem:
        meta_text = meta_elem.get_text(separator="|", strip=True)
        parts = [p.strip() for p in meta_text.split("|") if p.strip()]
        if len(parts) >= 1:
            job["category"] = parts[0]
        if len(parts) >= 2:
            job["location"] = parts[1]
        if len(parts) >= 3:
            job["requisition_number"] = parts[2]

    return job

# Example usage
job = get_job_details("nutanix", "ow6lzfwg")
print(f"Title: {job['title']}")
print(f"Location: {job.get('location')}")

def get_facets(company_slug: str, location: str = None) -> dict:
    url = f"https://jobs.jobvite.com/{company_slug}/search/facets"
    params = {"nl": 1}

    if location:
        params["l"] = location

    response = requests.get(url, params=params, timeout=10)
    response.raise_for_status()

    data = response.json()
    return data.get("facets", {})

# Get all available filters
facets = get_facets("nutanix")
print("Available locations:", len(facets.get("locations", [])))
print("Available categories:", len(facets.get("categories", [])))
print("Available departments:", len(facets.get("departments", [])))