TalNet (Oleeo) Jobs API.

import requests
from bs4 import BeautifulSoup
import re

company = "fcdo"
base_url = f"https://{company}.tal.net/candidate"

response = requests.get(base_url, timeout=15)
soup = BeautifulSoup(response.text, "html.parser")

# Look for job board links
job_links = soup.find_all("a", href=re.compile(r"/jobboard/vacancy/\d+/adv"))
if job_links:
    print(f"Found job board: {job_links[0]['href']}")

import requests
from bs4 import BeautifulSoup
import xml.etree.ElementTree as ET

company = "royalvacancies"
base_url = f"https://{company}.tal.net"

# Preferred: read the advertised Atom feed link from the candidate page.
discovery = requests.get(f"{base_url}/vx/appcentre-ext/candidate/", timeout=15)
soup = BeautifulSoup(discovery.text, "html.parser")
link = soup.find("link", attrs={"type": "application/atom+xml"})

if link and link.get("href"):
    feed_url = requests.compat.urljoin(base_url, link["href"])
else:
    # Fallback: build the feed URL from the tenant's appcentre, brand and board
    # IDs. The mobile-0 and brand- segments are required.
    feed_url = f"{base_url}/vx/mobile-0/appcentre-1/brand-2/candidate/jobboard/vacancy/1/feed"

resp = requests.get(feed_url, timeout=10)
if resp.status_code == 200 and "<feed" in resp.text:
    root = ET.fromstring(resp.content)
    entries = root.findall(".//{http://www.w3.org/2005/Atom}entry")
    print(f"Found {len(entries)} jobs in feed")

import requests
from bs4 import BeautifulSoup
import re

job_board_url = "https://fcdo.tal.net/vx/appcentre-ext/candidate/jobboard/vacancy/1/adv/"
response = requests.get(job_board_url, timeout=15)
soup = BeautifulSoup(response.text, "html.parser")

# Extract job links using the /opp/ pattern
job_links = soup.find_all("a", href=re.compile(r"/opp/\d+"))

jobs = []
for link in job_links:
    href = link.get("href", "")
    # Extract job ID from URL pattern: /opp/{job_id}-{slug}
    match = re.search(r"/opp/(\d+)", href)
    if match:
        jobs.append({
            "id": match.group(1),
            "title": link.get_text(strip=True),
            "url": href if href.startswith("http") else f"https://fcdo.tal.net{href}"
        })

print(f"Found {len(jobs)} jobs")

import requests
from bs4 import BeautifulSoup
import re
import time

base_url = "https://fcdo.tal.net/vx/appcentre-ext/candidate/jobboard/vacancy/1/adv/"
all_jobs = []
offset = 0

while True:
    url = f"{base_url}?start={offset}"
    response = requests.get(url, timeout=15)
    soup = BeautifulSoup(response.text, "html.parser")

    job_links = soup.find_all("a", href=re.compile(r"/opp/\d+"))

    if not job_links:
        break

    for link in job_links:
        match = re.search(r"/opp/(\d+)", link.get("href", ""))
        if match:
            all_jobs.append({
                "id": match.group(1),
                "title": link.get_text(strip=True),
                "url": link.get("href")
            })

    offset += 50
    time.sleep(1)  # Be respectful

    if len(job_links) < 50:  # Last page
        break

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

import requests
from bs4 import BeautifulSoup
import re

def parse_job_details(job_url: str) -> dict:
    response = requests.get(job_url, timeout=15)
    soup = BeautifulSoup(response.text, "html.parser")

    details = {"url": job_url}

    # Extract title from h1
    h1 = soup.find("h1")
    if h1:
        title_text = h1.get_text(strip=True)
        details["title"] = title_text.replace("View Vacancy - ", "")

    # Extract sections by looking for label patterns
    page_text = soup.get_text()

    patterns = {
        "location": r"Location[^:]*:\s*([^\n]+)",
        "city": r"Location \(City\)[^:]*:\s*([^\n]+)",
        "salary": r"Salary[^:]*:\s*([^\n]+)",
        "deadline": r"(?:Application deadline|Closing Date)[^:]*:\s*([^\n]+)",
        "job_type": r"Type of Position[^:]*:\s*([^\n]+)",
        "region": r"Region[^:]*:\s*([^\n]+)",
        "grade": r"Grade[^:]*:\s*([^\n]+)",
    }

    for field, pattern in patterns.items():
        match = re.search(pattern, page_text, re.IGNORECASE)
        if match:
            details[field] = match.group(1).strip()

    # Extract full job description section
    desc_match = re.search(
        r"Job Description[^:]*:\s*(.+?)(?=Essential qualifications|Application deadline|$)",
        page_text,
        re.DOTALL | re.IGNORECASE
    )
    if desc_match:
        details["description"] = desc_match.group(1).strip()[:2000]

    return details

# Usage example with a real FCDO job URL
job = parse_job_details(
    "https://fcdo.tal.net/vx/lang-en-GB/mobile-0/appcentre-1/brand-2/"
    "candidate/so/pm/4/pl/1/opp/26301-example-job-title/en-GB"
)
print(job)

import requests
from bs4 import BeautifulSoup
import re
import json

def extract_config(company: str) -> dict:
    url = f"https://{company}.tal.net/candidate"
    response = requests.get(url, timeout=15)
    soup = BeautifulSoup(response.text, "html.parser")

    config = {}

    # Find embedded WCN configuration
    scripts = soup.find_all("script")
    for script in scripts:
        if script.string and "WCN.global_config" in script.string:
            # Extract baseUrl
            base_match = re.search(r'baseUrl:\s*["']([^"']+)["']', script.string)
            if base_match:
                config["baseUrl"] = base_match.group(1)

            # Extract rootPath
            root_match = re.search(r'rootPath:\s*["']([^"']+)["']', script.string)
            if root_match:
                config["rootPath"] = root_match.group(1)

            # Extract appcentre ID from rootPath
            appcentre_match = re.search(r'appcentre-(\d+)', script.string)
            if appcentre_match:
                config["appcentreId"] = appcentre_match.group(1)

            # Extract brand ID
            brand_match = re.search(r'brand-(\d+)', script.string)
            if brand_match:
                config["brandId"] = brand_match.group(1)

            break

    return config

# Usage
config = extract_config("fcdo")
print(f"Appcentre ID: {config.get('appcentreId')}")
print(f"Brand ID: {config.get('brandId')}")
print(f"Base URL: {config.get('baseUrl')}")