Eightfold Jobs API.

import requests

company = "aexp"  # American Express
domain = "aexp.com"
base_url = f"https://{company}.eightfold.ai"

# Try SmartApply API first
smartapply_url = f"{base_url}/api/apply/v2/jobs?domain={domain}&hl=en&start=0"
headers = {"Accept": "application/json", "Content-Type": "application/json"}

response = requests.get(smartapply_url, headers=headers)
if response.status_code == 200:
    data = response.json()
    jobs = data.get("positions", [])
    total = data.get("totalJobs", 0)
    print(f"SmartApply: Found {total} jobs, showing {len(jobs)}")
else:
    # Try PCSX API as fallback
    pcsx_url = f"{base_url}/api/pcsx/search?domain={domain}&query=&location=&start=0"
    response = requests.get(pcsx_url, headers=headers)
    if response.status_code == 200:
        data = response.json().get("data", {})
        jobs = data.get("positions", [])
        print(f"PCSX: Found {len(jobs)} jobs")

import requests
import re
import xml.etree.ElementTree as ET

company = "aexp"
domain = "aexp.com"
sitemap_url = f"https://{company}.eightfold.ai/careers/sitemap.xml?domain={domain}"

response = requests.get(sitemap_url)
root = ET.fromstring(response.content)

# Extract job IDs from URLs
job_ids = []
namespace = {"ns": "http://www.sitemaps.org/schemas/sitemap/0.9"}

for url in root.findall(".//ns:url/ns:loc", namespace):
    match = re.search(r"/careers/job/(d+)", url.text)
    if match:
        job_ids.append(match.group(1))

print(f"Found {len(job_ids)} job IDs in sitemap")

import requests
import time

company = "aexp"
domain = "aexp.com"
job_id = "39751247"
base_url = f"https://{company}.eightfold.ai"
headers = {"Accept": "application/json", "Content-Type": "application/json"}

# SmartApply details endpoint
details_url = f"{base_url}/api/apply/v2/jobs/{job_id}?domain={domain}&hl=en"
response = requests.get(details_url, headers=headers)

if response.status_code == 200:
    job = response.json()
    print({
        "id": job.get("id"),
        "title": job.get("name"),
        "location": job.get("location"),
        "department": job.get("department"),
        "description": job.get("job_description", "")[:200] + "...",
        "url": job.get("canonicalPositionUrl"),
    })

# For PCSX, use: /api/pcsx/position_details?position_id={job_id}&domain={domain}

import requests
import time

company = "aexp"
domain = "aexp.com"
base_url = f"https://{company}.eightfold.ai"
headers = {"Accept": "application/json", "Content-Type": "application/json"}

all_jobs = []
start = 0
batch_size = 10

while True:
    url = f"{base_url}/api/apply/v2/jobs?domain={domain}&hl=en&start={start}"
    response = requests.get(url, headers=headers)

    if response.status_code != 200:
        break

    data = response.json()
    positions = data.get("positions", [])

    if not positions:
        break

    all_jobs.extend(positions)
    print(f"Fetched {len(positions)} jobs (total: {len(all_jobs)})")

    start += batch_size
    time.sleep(0.5)  # Rate limiting

print(f"Total jobs collected: {len(all_jobs)}")

import re
import requests
from urllib.parse import urlparse

# Known company -> domain overrides where the subdomain differs from the domain
KNOWN_DOMAINS = {
    "aexp": "aexp.com",
    "americanexpress": "aexp.com",
    "starbucks": "starbucks.com",
    "paypal": "paypal.com",
    "siemens": "siemens.com",
}

def infer_domain(careers_url: str) -> str | None:
    """Best-effort domain guess from an eightfold.ai subdomain."""
    host = urlparse(careers_url).netloc.lower()
    if host.endswith(".eightfold.ai"):
        slug = host[: -len(".eightfold.ai")]
        return KNOWN_DOMAINS.get(slug, f"{slug}.com")
    return None  # custom/vanity host -> resolve from the page instead

def extract_embedded_domain(careers_url: str) -> str | None:
    """Vanity hosts embed the real domain param in the careers page HTML."""
    html = requests.get(careers_url).text
    match = re.search(r'"domain"s*:s*"([A-Za-z0-9.-]+)"', html)
    return match.group(1).lower() if match else None

def resolve_domain(careers_url: str) -> str | None:
    return infer_domain(careers_url) or extract_embedded_domain(careers_url)

# Standard subdomain
print(resolve_domain("https://aexp.eightfold.ai/careers"))   # aexp.com
# Custom / vanity host (e.g. talent.bayer.com) -> read from page HTML
print(resolve_domain("https://talent.bayer.com/careers"))