ApplicantPro Jobs API.

import requests
import re
from urllib.parse import urlparse

def get_site_id(subdomain: str) -> str | None:
    url = f"https://{subdomain}.applicantpro.com/jobs/"
    response = requests.get(url, timeout=10)
    response.raise_for_status()

    # Extract domain_id from embedded JavaScript
    match = re.search(r'"domain_id"\s*:\s*"(d+)"', response.text)
    if match:
        return match.group(1)
    return None

site_id = get_site_id("harvardbioscience")
print(f"Site ID: {site_id}")  # Output: Site ID: 11099

import requests
import json
from urllib.parse import quote

subdomain = "harvardbioscience"
site_id = "11099"

get_params = {
    "isInternal": 0,
    "showLocation": 1,
    "showEmploymentType": 1,
    "chatToApplyButton": "0"
}

# URL-encode the JSON params
encoded_params = quote(json.dumps(get_params))
listings_url = f"https://{subdomain}.applicantpro.com/core/jobs/{site_id}?getParams={encoded_params}"

headers = {
    "Accept": "application/json",
    "Referer": f"https://{subdomain}.applicantpro.com/jobs/"
}
response = requests.get(listings_url, headers=headers, timeout=10)
data = response.json()

jobs = data.get("data", {}).get("jobs", [])
job_count = data.get("data", {}).get("jobCount", 0)
print(f"Found {len(jobs)} jobs (API reports {job_count} total)")

for job in jobs:
    print({
        "id": job.get("id"),
        "title": job.get("title"),
        "location": job.get("jobLocation"),
        "city": job.get("city"),
        "state": job.get("stateName"),
        "country": job.get("iso3"),
        "department": job.get("orgTitle"),
        "classification": job.get("classification"),
        "employment_type": job.get("employmentType"),
        "workplace_type": job.get("workplaceType"),
        "pay_type": job.get("payType"),
        "pay_details": job.get("payDetails"),
        "min_salary": job.get("minSalary"),
        "max_salary": job.get("maxSalary"),
        "job_url": job.get("jobUrl"),
        "posted_date": job.get("startDateRef"),
        "expiry_date": job.get("endDateRef"),
    })

import time

def get_job_details(subdomain: str, site_id: str, job_id: int) -> dict:
    url = f"https://{subdomain}.applicantpro.com/core/jobs/{site_id}/{job_id}/job-details"
    headers = {
        "Accept": "application/json",
        "Referer": f"https://{subdomain}.applicantpro.com/jobs/{job_id}"
    }
    response = requests.get(url, headers=headers, timeout=10)
    response.raise_for_status()
    return response.json().get("data", {})

# Fetch details for first job with rate limiting
if jobs:
    details = get_job_details(subdomain, site_id, jobs[0]["id"])
    print({
        "id": details.get("id"),
        "title": details.get("title"),
        "city": details.get("city"),
        "description_html": details.get("advertisingDescriptionHtml", "")[:200],
        "description_plain": details.get("advertisingDescription", "")[:200],
        "benefits": details.get("benefits"),
        "zip_code": details.get("jobBoardZip"),
        "pay_details": details.get("payDetails"),
    })
    time.sleep(0.5)  # Be respectful with rate limiting

def safe_extract(subdomain: str) -> list[dict]:
    try:
        site_id = get_site_id(subdomain)
        if not site_id:
            print(f"Could not find site ID for {subdomain}")
            return []

        get_params = {"isInternal": 0, "showLocation": 1}
        encoded_params = quote(json.dumps(get_params))
        url = f"https://{subdomain}.applicantpro.com/core/jobs/{site_id}?getParams={encoded_params}"
        response = requests.get(url, headers={"Accept": "application/json"}, timeout=10)
        response.raise_for_status()

        data = response.json()
        if not data.get("success"):
            print(f"API returned error for {subdomain}")
            return []

        return data.get("data", {}).get("jobs", [])
    except requests.RequestException as e:
        print(f"Request failed for {subdomain}: {e}")
        return []

jobs = safe_extract("harvardbioscience")

import requests
import xml.etree.ElementTree as ET

# Global sitemap index lists all ApplicantPro companies
sitemap_index_url = "https://feeds.applicantpro.com/site_map_index.xml"
response = requests.get(sitemap_index_url, timeout=10)
root = ET.fromstring(response.content)

# Extract company sitemap URLs
namespaces = {"ns": "http://www.sitemaps.org/schemas/sitemap/0.9"}
company_sitemaps = []
for sitemap in root.findall("ns:sitemap", namespaces):
    loc = sitemap.find("ns:loc", namespaces)
    if loc is not None:
        company_sitemaps.append(loc.text)

print(f"Found {len(company_sitemaps)} company sitemaps")

# Parse individual company sitemap for job URLs
def parse_company_sitemap(sitemap_url: str) -> list[str]:
    response = requests.get(sitemap_url, timeout=10)
    root = ET.fromstring(response.content)
    job_urls = []
    for url in root.findall("ns:url", namespaces):
        loc = url.find("ns:loc", namespaces)
        if loc is not None and "/jobs/" in loc.text:
            job_urls.append(loc.text)
    return job_urls

# Example: Get jobs from first company sitemap
if company_sitemaps:
    jobs = parse_company_sitemap(company_sitemaps[0])
    print(f"Found {len(jobs)} job URLs in first sitemap")