Phenom People Jobs API.

import requests
from bs4 import BeautifulSoup

def get_refnum(domain: str) -> str | None:
    url = f"https://{domain}/global/en/search-results"
    response = requests.get(url, timeout=10)
    soup = BeautifulSoup(response.text, "html.parser")

    # Look for refNum in script tags or data attributes
    for script in soup.find_all("script"):
        if script.string and "refNum" in script.string:
            # Extract refNum using string parsing
            import re
            match = re.search(r'"refNum":"([^"]+)"', script.string)
            if match:
                return match.group(1)
    return None

refnum = get_refnum("careers.geaerospace.com")
print(f"Found refNum: {refnum}")

import requests

def fetch_jobs(domain: str, refnum: str, page: int = 0, size: int = 20) -> dict:
    url = f"https://{domain}/widgets"
    payload = {
        "lang": "en_global",
        "deviceType": "desktop",
        "country": "global",
        "pageName": "search-results",
        "size": size,
        "from": page * size,
        "jobs": True,
        "counts": True,
        "all_fields": ["category", "country", "city", "type"],
        "clearAll": False,
        "jdsource": "facets",
        "isSliderEnable": False,
        "pageId": "page20",
        "siteType": "external",
        "keywords": "",
        "global": True,
        "selected_fields": {},
        "sort": {"order": "desc", "field": "postedDate"},
        "locationData": {},
        "refNum": refnum,
        "ddoKey": "refineSearch"
    }

    response = requests.post(
        url,
        json=payload,
        headers={"Content-Type": "application/json"},
        timeout=15
    )
    return response.json()

data = fetch_jobs("careers.geaerospace.com", "GAOGAYGLOBAL", page=0)
jobs = data.get("refineSearch", {}).get("data", {}).get("jobs", [])
total = data.get("refineSearch", {}).get("totalHits", 0)
print(f"Found {len(jobs)} jobs (total: {total})")

for job in jobs:
    parsed = {
        "job_id": job.get("jobId"),
        "req_id": job.get("reqId"),
        "title": job.get("title"),
        "location": job.get("location"),
        "category": job.get("category"),
        "type": job.get("type"),
        "posted_date": job.get("postedDate"),
        "apply_url": job.get("applyUrl"),
        "teaser": job.get("descriptionTeaser", "")[:200],
        "job_seq_no": job.get("jobSeqNo"),
        "is_multi_location": job.get("isMultiLocation", False),
    }
    print(f"{parsed['title']} - {parsed['location']}")

import requests
from bs4 import BeautifulSoup
from urllib.parse import quote

def fetch_job_details(domain: str, job_seq_no: str, title: str) -> dict:
    title_slug = quote(title.lower().replace(" ", "-"))
    url = f"https://{domain}/global/en/job/{job_seq_no}/{title_slug}"

    response = requests.get(url, timeout=10)
    soup = BeautifulSoup(response.text, "html.parser")

    # Extract job details from HTML
    title_elem = soup.select_one("h1.job-title, h1")
    location_elem = soup.select_one(".job-location, [class*='location']")
    desc_elem = soup.select_one(".job-description, [class*='description']")
    apply_elem = soup.select_one("a[href*='apply']")

    return {
        "title": title_elem.get_text(strip=True) if title_elem else None,
        "location": location_elem.get_text(strip=True) if location_elem else None,
        "description": desc_elem.get_text(strip=True) if desc_elem else None,
        "apply_url": apply_elem.get("href") if apply_elem else None,
        "url": url,
    }

# Fetch details for first job
if jobs:
    first_job = jobs[0]
    details = fetch_job_details(
        "careers.geaerospace.com",
        first_job["jobSeqNo"],
        first_job["title"]
    )
    print(f"Full description length: {len(details.get('description', ''))}")

import time
import requests

def fetch_all_jobs(domain: str, refnum: str, delay: float = 0.5) -> list:
    all_jobs = []
    page = 0
    size = 20

    while True:
        data = fetch_jobs(domain, refnum, page=page, size=size)
        result = data.get("refineSearch", {})
        jobs = result.get("data", {}).get("jobs", [])
        total = result.get("totalHits", 0)

        if not jobs:
            break

        all_jobs.extend(jobs)
        print(f"Page {page}: fetched {len(jobs)} jobs (total: {len(all_jobs)}/{total})")

        if len(all_jobs) >= total:
            break

        page += 1
        time.sleep(delay)  # Rate limiting

    return all_jobs

all_jobs = fetch_all_jobs("careers.geaerospace.com", "GAOGAYGLOBAL")
print(f"Total jobs collected: {len(all_jobs)}")

import requests
import xml.etree.ElementTree as ET

def discover_jobs_from_sitemap(domain: str) -> list:
    sitemap_url = f"https://{domain}/global/en/sitemap_index.xml"
    response = requests.get(sitemap_url, timeout=10)

    root = ET.fromstring(response.content)
    namespace = {"sm": "http://www.sitemaps.org/schemas/sitemap/0.9"}

    job_urls = []
    # Parse sitemap index for individual sitemaps
    for sitemap in root.findall(".//sm:loc", namespace):
        sitemap_response = requests.get(sitemap.text, timeout=10)
        sitemap_root = ET.fromstring(sitemap_response.content)

        # Extract job URLs from each sitemap
        for url in sitemap_root.findall(".//sm:loc", namespace):
            if "/job/" in url.text:
                job_urls.append(url.text)

    return job_urls

job_urls = discover_jobs_from_sitemap("careers.geaerospace.com")
print(f"Discovered {len(job_urls)} job URLs from sitemaps")