Taleo Jobs API.

import requests

# Company configuration
company = "hdr"
section = "ex"  # Common sections: ex, 1, 2, 10000
portal_id = "101430233"  # Found in network requests

base_url = f"https://{company}.taleo.net"
search_url = f"{base_url}/careersection/rest/jobboard/searchjobs?lang=en&portal={portal_id}"

print(f"Taleo instance: {base_url}")
print(f"Career section: {section}")

import requests

url = f"https://{company}.taleo.net/careersection/rest/jobboard/searchjobs?lang=en&portal={portal_id}"

headers = {
    "Content-Type": "application/json",
    "X-Requested-With": "XMLHttpRequest",
    "Accept": "application/json, text/javascript, */*; q=0.01",
    "Referer": f"https://{company}.taleo.net/careersection/{section}/jobsearch.ftl",
}

payload = {
    "multilineEnabled": False,
    "sortingSelection": {
        "sortBySelectionParam": "1",
        "ascendingSortingOrder": "false"
    },
    "fieldData": {
        "fields": {
            "KEYWORD": "",
            "LOCATION": "",
            "CATEGORY": ""
        },
        "valid": True
    },
    "pageNo": 1
}

response = requests.post(url, json=payload, headers=headers)
data = response.json()

jobs = data.get("requisitionList", [])
total_count = data.get("pagingData", {}).get("totalCount", 0)

print(f"Found {total_count} total jobs, fetched {len(jobs)} on page 1")

import json

for job in jobs:
    job_id = job.get("jobId")
    contest_no = job.get("contestNo")  # Use this for URLs
    columns = job.get("column", [])

    parsed_job = {
        "job_id": job_id,
        "contest_no": contest_no,
        "title": columns[0] if len(columns) > 0 else None,
        "location": json.loads(columns[1]) if len(columns) > 1 else [],
        "posted_date": columns[2] if len(columns) > 2 else None,
        "is_hot_job": job.get("hotJob", False),
        "detail_url": f"https://{company}.taleo.net/careersection/{section}/jobdetail.ftl?job={contest_no}"
    }

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

import requests
import time

all_jobs = []
page_no = 1
page_size = 25

while True:
    payload["pageNo"] = page_no

    response = requests.post(url, json=payload, headers=headers)
    data = response.json()

    jobs = data.get("requisitionList", [])
    if not jobs:
        break

    all_jobs.extend(jobs)

    paging = data.get("pagingData", {})
    total_count = paging.get("totalCount", 0)

    print(f"Page {page_no}: {len(jobs)} jobs (total: {len(all_jobs)}/{total_count})")

    if len(all_jobs) >= total_count:
        break

    page_no += 1
    time.sleep(0.5)  # Rate limiting

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

import requests
from bs4 import BeautifulSoup

def fetch_job_details(contest_no: str) -> dict:
    detail_url = f"https://{company}.taleo.net/careersection/{section}/jobdetail.ftl?job={contest_no}"

    response = requests.get(detail_url)
    soup = BeautifulSoup(response.text, "html.parser")

    # Extract job details from HTML
    # Note: Selectors may vary by Taleo instance
    title_elem = soup.find("h1") or soup.find(class_="title")
    location_elem = soup.find(class_="location")

    # Description is typically in main content area
    description_elem = soup.find(class_="jobdescription")
    if not description_elem:
        description_elem = soup.find(id="jobdescription")

    return {
        "contest_no": contest_no,
        "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": description_elem.get_text(strip=True) if description_elem else None,
        "url": detail_url
    }

# Fetch details for first job
if all_jobs:
    first_job = all_jobs[0]
    details = fetch_job_details(first_job["contestNo"])
    print(f"Title: {details['title']}")

import requests

def safe_fetch_jobs(company: str, section: str, portal_id: str) -> list:
    url = f"https://{company}.taleo.net/careersection/rest/jobboard/searchjobs"
    params = {"lang": "en", "portal": portal_id}

    try:
        response = requests.post(url, params=params, json=payload, headers=headers, timeout=30)
        response.raise_for_status()

        # Check for unavailable section
        if "Career Section Unavailable" in response.text:
            print(f"Career section '{section}' unavailable for {company}")
            return []

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

    except requests.exceptions.Timeout:
        print(f"Timeout fetching jobs for {company}")
        return []
    except requests.exceptions.RequestException as e:
        print(f"Error fetching jobs for {company}: {e}")
        return []
    except ValueError as e:
        print(f"JSON parse error for {company}: {e}")
        return []

# Test with known working instance
jobs = safe_fetch_jobs("hdr", "ex", "101430233")
print(f"Fetched {len(jobs)} jobs")