JOIN Jobs API.

import requests
import json
from bs4 import BeautifulSoup

company_slug = "marswalk"
url = f"https://join.com/companies/{company_slug}"

response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")

# Find the __NEXT_DATA__ script tag
script_tag = soup.find("script", id="__NEXT_DATA__")
next_data = json.loads(script_tag.string)

# Extract the company ID
company_id = next_data["props"]["pageProps"]["initialState"]["company"]["id"]
print(f"Company ID: {company_id}")

import requests

company_id = 98520  # From step 1
url = f"https://join.com/api/public/companies/{company_id}/jobs"

params = {
    "locale": "en-us",
    "page": 1,
    "pageSize": 100  # Max items per page
}

response = requests.get(url, params=params)
data = response.json()

jobs = data["items"]
pagination = data["pagination"]
print(f"Found {pagination['rowCount']} total jobs across {pagination['pageCount']} pages")

for job in jobs:
    # Convert salary from cents to actual amount
    salary_from = job.get("salaryAmountFrom", {}).get("amount", 0) / 100
    salary_to = job.get("salaryAmountTo", {}).get("amount", 0) / 100
    currency = job.get("salaryAmountFrom", {}).get("currency", "EUR")

    job_info = {
        "id": job["id"],
        "idParam": job.get("idParam"),
        "title": job["title"],
        "location": job.get("city", {}).get("cityName"),
        "country": job.get("city", {}).get("countryName"),
        "workplace_type": job.get("workplaceType"),  # ONSITE, REMOTE, HYBRID
        "category": job.get("category", {}).get("name"),
        "employment_type": job.get("employmentType", {}).get("name"),
        "salary_range": f"{salary_from:,.0f} - {salary_to:,.0f} {currency}" if salary_from else None,
        "created_at": job.get("createdAt"),
    }
    print(job_info)

import requests

job_id = 15565770  # From step 2
url = f"https://join.com/api/public/jobs/{job_id}"

response = requests.get(url)
job = response.json()

# Extract full job details
full_job = {
    "id": job["id"],
    "title": job["title"],
    "description": job.get("description"),  # Full markdown description
    "intro": job.get("intro"),
    "tasks": job.get("tasks"),
    "requirements": job.get("requirements"),
    "benefits": job.get("benefits"),
    "outro": job.get("outro"),
    "contact_name": job.get("contactName"),
    "contact_email": job.get("contactEmail"),
    "status": job.get("status"),  # ONLINE, OFFLINE, ARCHIVED
}

print(f"Job: {full_job['title']}")
print(f"Status: {full_job['status']}")

import requests

def fetch_all_jobs(company_id: int, page_size: int = 100) -> list:
    all_jobs = []
    page = 1

    while True:
        url = f"https://join.com/api/public/companies/{company_id}/jobs"
        params = {"locale": "en-us", "page": page, "pageSize": page_size}

        response = requests.get(url, params=params)
        data = response.json()

        all_jobs.extend(data["items"])

        # Check if we've fetched all pages
        if page >= data["pagination"]["pageCount"]:
            break

        page += 1

    return all_jobs

# Fetch all jobs for a company
jobs = fetch_all_jobs(98520)
print(f"Retrieved {len(jobs)} total jobs")