Zoho Recruit Jobs API.

import requests

def detect_zoho_pattern(company: str) -> str:
    """Detect which Zoho URL pattern a company uses."""
    patterns = [
        f"https://{company}.zohorecruit.com/jobs/Careers",  # Modern
        f"https://{company}.zohorecruit.in/jobs/Careers",   # India
        f"https://{company}.zohorecruit.com/careers",       # Legacy
    ]

    for pattern in patterns:
        try:
            resp = requests.head(pattern, timeout=10, allow_redirects=True)
            if resp.status_code == 200:
                return pattern
        except requests.RequestException:
            continue
    return None

# Usage
url = detect_zoho_pattern("algoleap")
print(f"Detected URL: {url}")

import requests
from bs4 import BeautifulSoup

def fetch_zoho_career_page(url: str) -> str:
    """Fetch HTML from a Zoho Recruit career page."""
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
    }

    response = requests.get(url, headers=headers, timeout=15)
    response.raise_for_status()

    return response.text

# Usage
html = fetch_zoho_career_page("https://algoleap.zohorecruit.com/jobs/Careers")
print(f"Fetched {len(html)} bytes")

from bs4 import BeautifulSoup
import re

def parse_zoho_jobs(html: str) -> list[dict]:
    """Extract job listings from Zoho career page HTML."""
    soup = BeautifulSoup(html, 'html.parser')
    jobs = []

    # Zoho-specific selectors from investigation
    job_elements = soup.select('.ziabot-job-listing-row, .cw-job-listing-container > div')

    for el in job_elements:
        link = el.select_one('h3 > a, a[href*="/jobs/Careers/"]')
        if not link:
            continue

        location_el = el.select_one('.cw-job-location')
        job_type_el = el.select_one('.cw-job-type')

        jobs.append({
            'title': link.get_text(strip=True),
            'url': link.get('href'),
            'location': location_el.get_text(strip=True) if location_el else None,
            'job_type': job_type_el.get_text(strip=True) if job_type_el else None,
        })

    return jobs

# Usage
jobs = parse_zoho_jobs(html)
print(f"Found {len(jobs)} jobs")
for job in jobs[:3]:
    print(f"  - {job['title']} ({job['location']})")

import re

def parse_zoho_job_url(url: str) -> dict | None:
    """Extract job ID and slug from a Zoho job URL."""
    # Pattern: /jobs/Careers/{jobId}/{job-title}
    match = re.search(r'/jobs/Careers/(\d+)/([^/?]+)', url)

    if not match:
        return None

    job_id = match.group(1)
    slug = match.group(2)

    return {
        'job_id': job_id,
        'slug': slug,
        'title': slug.replace('-', ' ').title(),
    }

def build_job_detail_url(base_url: str, job_id: str, slug: str) -> str:
    """Construct the full URL for a job detail page."""
    return f"{base_url}/{job_id}/{slug}?source=CareerSite"

# Usage
url = "https://algoleap.zohorecruit.com/jobs/Careers/660523000015041023/senior-software-engineer"
parsed = parse_zoho_job_url(url)
print(f"Job ID: {parsed['job_id']}, Title: {parsed['title']}")

import requests
from bs4 import BeautifulSoup
import re

def fetch_job_details(job_url: str) -> dict:
    """Fetch detailed information from a Zoho job detail page."""
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
    }

    response = requests.get(job_url, headers=headers, timeout=15)
    soup = BeautifulSoup(response.text, 'html.parser')

    # Extract from detail page selectors
    title_el = soup.select_one('h1')
    desc_el = soup.select_one('.cw-job-description, #spandesc')
    location_el = soup.select_one('.cw-job-detail-meta .cw-detail-value')

    return {
        'title': title_el.get_text(strip=True) if title_el else None,
        'description': desc_el.get_text(strip=True) if desc_el else None,
        'description_html': str(desc_el) if desc_el else None,
        'location': location_el.get_text(strip=True) if location_el else None,
        'url': job_url,
    }

# Usage
details = fetch_job_details("https://algoleap.zohorecruit.com/jobs/Careers/660523000015041023/senior-software-engineer?source=CareerSite")
print(f"Title: {details['title']}")

import json
from bs4 import BeautifulSoup

def extract_json_ld(html: str) -> list[dict]:
    """Extract JobPosting JSON-LD data from the page."""
    soup = BeautifulSoup(html, 'html.parser')
    jobs = []

    for script in soup.find_all('script', type='application/ld+json'):
        try:
            data = json.loads(script.string)

            # Handle both single object and array formats
            items = data if isinstance(data, list) else [data]

            for item in items:
                if item.get('@type') == 'JobPosting':
                    location = item.get('jobLocation', {})
                    address = location.get('address', {}) if isinstance(location, dict) else {}

                    jobs.append({
                        'title': item.get('title'),
                        'description': item.get('description'),
                        'location': address.get('addressLocality'),
                        'date_posted': item.get('datePosted'),
                        'employment_type': item.get('employmentType'),
                        'url': item.get('url'),
                    })
        except (json.JSONDecodeError, AttributeError, TypeError):
            continue

    return jobs

# Usage
json_jobs = extract_json_ld(html)
print(f"Found {len(json_jobs)} jobs via JSON-LD")