GoHire Jobs API.

import requests
from bs4 import BeautifulSoup
import re

company_slug = "dexerto-de5jlhjo"
url = f"https://jobs.gohire.io/{company_slug}"

response = requests.get(url, timeout=10)
soup = BeautifulSoup(response.text, 'html.parser')

print(f"Fetched listings page: {len(response.text)} bytes")

# Extract job IDs from anchor tags
job_ids = []
for link in soup.select('a.gohire-job'):
    href = link.get('href', '')
    # Job IDs are the numeric portion at the end of URLs like /job-slug-12345/
    match = re.search(r'/(\d{5,})/?$', href)
    if match:
        job_ids.append(match.group(1))

# Remove duplicates while preserving order
job_ids = list(dict.fromkeys(job_ids))
print(f"Found {len(job_ids)} job IDs: {job_ids[:5]}...")

import requests

def fetch_job_details(job_id: str) -> dict | None:
    url = "https://api.gohire.io/getJobId"

    # API expects form-data, not JSON
    data = {"jobId": job_id}

    response = requests.post(
        url,
        data=data,
        headers={"Content-Type": "application/x-www-form-urlencoded"},
        timeout=10
    )

    result = response.json()

    # API returns an array - get first element
    return result[0] if result else None

# Fetch details for first job
job = fetch_job_details(job_ids[0])
if job:
    print(f"Title: {job.get('jobTitle')}")
    print(f"Company: {job.get('companyName')}")

import base64

def transform_job(job: dict) -> dict:
    # Decode the base64 apply URL if present
    apply_url = None
    if job.get('applyUrl'):
        try:
            apply_url = base64.b64decode(job['applyUrl']).decode('utf-8')
        except:
            apply_url = job.get('applyUrl')

    # Build salary string if available
    salary = None
    if job.get('fromSalary') and job.get('toSalary'):
        currency = job.get('currencySymbol', '')
        salary = f"{currency}{job['fromSalary']} - {currency}{job['toSalary']} {job.get('salaryUnit', '')}"

    return {
        "id": job.get("jobId"),
        "title": job.get("jobTitle"),
        "company": job.get("companyName"),
        "location": f"{job.get('jobCounty', '')}, {job.get('countryName', '')}",
        "type": job.get("jobType"),
        "salary": salary,
        "description_html": job.get("jobDescr"),
        "apply_url": apply_url,
        "posted_timestamp": job.get("jobCreatedOn"),
        "client_hash": job.get("clientHash"),
    }

transformed = transform_job(job)
print(f"Transformed: {transformed['title']} at {transformed['company']}")

import time
from typing import List, Dict

def scrape_gohire_company(company_slug: str) -> List[Dict]:
    jobs = []

    # Step 1: Fetch listings page
    try:
        url = f"https://jobs.gohire.io/{company_slug}"
        response = requests.get(url, timeout=10)
        response.raise_for_status()
        soup = BeautifulSoup(response.text, 'html.parser')
    except requests.RequestException as e:
        print(f"Error fetching listings: {e}")
        return jobs

    # Step 2: Extract job IDs
    job_ids = []
    for link in soup.select('a.gohire-job'):
        href = link.get('href', '')
        match = re.search(r'/(\d{5,})/?$', href)
        if match:
            job_ids.append(match.group(1))
    job_ids = list(dict.fromkeys(job_ids))

    # Step 3: Fetch each job's details
    for i, job_id in enumerate(job_ids):
        try:
            time.sleep(0.5)  # Conservative rate limiting
            job = fetch_job_details(job_id)
            if job:
                jobs.append(transform_job(job))
                print(f"[{i+1}/{len(job_ids)}] Fetched: {job.get('jobTitle')}")
        except Exception as e:
            print(f"Error fetching job {job_id}: {e}")

    return jobs

# Run the scraper
all_jobs = scrape_gohire_company("dexerto-de5jlhjo")
print(f"\nTotal jobs scraped: {len(all_jobs)}")

import requests

def discover_gohire_companies() -> dict:
    """Fetch sitemap and extract unique company slugs with their job counts."""
    url = "https://jobs.gohire.io/sitemap.txt"
    response = requests.get(url, timeout=30)
    response.raise_for_status()

    companies = {}
    for line in response.text.strip().split('\n'):
        # URLs look like: https://jobs.gohire.io/company-slug/job-title-12345/
        parts = line.strip().split('/')
        if len(parts) >= 5:
            company_slug = parts[3]  # company-slug
            if company_slug not in companies:
                companies[company_slug] = {"slug": company_slug, "job_count": 0}
            companies[company_slug]["job_count"] += 1

    return companies

# Discover all GoHire companies
companies = discover_gohire_companies()
print(f"Found {len(companies)} companies")
for slug, data in list(companies.items())[:5]:
    print(f"  {slug}: {data['job_count']} jobs")