Paylocity Jobs API.

import re

# Paylocity URL patterns
listing_url = "https://recruiting.paylocity.com/recruiting/jobs/All/b181f77f-0432-453f-b229-869d786bb46c/Available-Positions"
detail_url = "https://recruiting.paylocity.com/Recruiting/Jobs/Details/3898273"

# Extract tenant GUID from URL
guid_pattern = r'[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}'
guid_match = re.search(guid_pattern, listing_url)
tenant_guid = guid_match.group(0) if guid_match else None
print(f"Tenant GUID: {tenant_guid}")

import requests
import re
import json

tenant_guid = "b181f77f-0432-453f-b229-869d786bb46c"
listing_url = f"https://recruiting.paylocity.com/recruiting/jobs/All/{tenant_guid}/Available-Positions"

response = requests.get(listing_url, timeout=30)
html = response.text

# Extract window.pageData JSON from the HTML
pattern = r'window\.pageData\s*=\s*(\{.*?\});\s*</script>'
match = re.search(pattern, html, re.DOTALL)

if match:
    json_str = match.group(1)
    page_data = json.loads(json_str)
    jobs = page_data.get("Jobs", [])
    print(f"Found {len(jobs)} jobs in embedded JSON")
else:
    print("No embedded pageData found - may need HTML parsing fallback")

import json

# Assuming page_data was extracted from the previous step
jobs = page_data.get("Jobs", [])

for job in jobs[:3]:  # Show first 3 jobs
    job_info = {
        "job_id": job.get("JobId"),
        "title": job.get("JobTitle"),
        "location": job.get("LocationName"),
        "is_remote": job.get("IsRemote", False),
        "published_date": job.get("PublishedDate"),
        "department": job.get("HiringDepartment"),
    }

    # Full location details
    location = job.get("JobLocation", {})
    if location:
        job_info["address"] = location.get("Address")
        job_info["city"] = location.get("City")
        job_info["state"] = location.get("State")
        job_info["zip"] = location.get("Zip")
        job_info["country"] = location.get("Country")

    print(json.dumps(job_info, indent=2))

import requests
import json
from bs4 import BeautifulSoup

job_id = 3898273
tenant_guid = "b181f77f-0432-453f-b229-869d786bb46c"

# Detail URLs carry the tenant GUID in the listingId query param
detail_url = f"https://recruiting.paylocity.com/Recruiting/Jobs/Details/{job_id}?listingId={tenant_guid}"

response = requests.get(detail_url, timeout=30)
html = response.text

# Removed roles render "Job Not Found" in the body without a 404
if "Job Not Found" in html:
    raise ValueError(f"Job {job_id} has been removed")

soup = BeautifulSoup(html, "html.parser")

def text_or_none(selector):
    el = soup.select_one(selector)
    return el.get_text(strip=True) if el else None

job = {
    "job_id": job_id,
    "title": text_or_none("span.job-preview-title") or text_or_none("span.breadcrumb-title"),
    "description": text_or_none("div.job-preview-details"),
    "location": text_or_none("div.preview-location"),
    "apply_url": detail_url,
}

# Salary, dates, employment type, and company name live in the JSON-LD JobPosting
for script in soup.find_all("script", type="application/ld+json"):
    try:
        data = json.loads(script.string or "{}")
    except json.JSONDecodeError:
        continue
    if isinstance(data, dict) and data.get("@type") == "JobPosting":
        job["date_posted"] = data.get("datePosted")
        job["valid_through"] = data.get("validThrough")
        job["employment_type"] = data.get("employmentType")
        job["company_name"] = (data.get("hiringOrganization") or {}).get("name")
        base_salary = data.get("baseSalary") or {}
        salary_value = base_salary.get("value") or {}
        if salary_value:
            job["salary_min"] = salary_value.get("minValue")
            job["salary_max"] = salary_value.get("maxValue")
            job["salary_currency"] = base_salary.get("currency", "USD")
        if not job["description"]:
            job["description"] = data.get("description")
        break

print(json.dumps(job, indent=2))

import requests
import time
import json
import re

def fetch_paylocity_jobs(tenant_guid: str, max_retries: int = 3) -> list:
    listing_url = f"https://recruiting.paylocity.com/recruiting/jobs/All/{tenant_guid}/Available-Positions"

    for attempt in range(max_retries):
        try:
            response = requests.get(
                listing_url,
                timeout=30,
                headers={"User-Agent": "Mozilla/5.0 (compatible; JobBot/1.0)"}
            )
            response.raise_for_status()

            # Extract embedded JSON
            pattern = r'window\.pageData\s*=\s*(\{.*?\});\s*</script>'
            match = re.search(pattern, response.text, re.DOTALL)

            if match:
                page_data = json.loads(match.group(1))
                return page_data.get("Jobs", [])
            return []

        except requests.RequestException as e:
            print(f"Attempt {attempt + 1} failed: {e}")
            if attempt < max_retries - 1:
                time.sleep(2 ** attempt)  # Exponential backoff
            else:
                raise

    return []

# Usage with rate limiting
tenant_guids = ["b181f77f-0432-453f-b229-869d786bb46c"]
for guid in tenant_guids:
    jobs = fetch_paylocity_jobs(guid)
    print(f"Retrieved {len(jobs)} jobs for tenant {guid}")
    time.sleep(1.5)  # Conservative delay between requests