Lever Jobs API.

import re

# URL pattern: https://jobs.lever.co/{companySlug}
# Examples:
# - https://jobs.lever.co/netflix -> slug: "netflix"
# - https://jobs.lever.co/spotify -> slug: "spotify"

url = "https://jobs.lever.co/netflix"
match = re.search(r"jobs\.lever\.co/([^/?#]+)", url)

if match:
    company_slug = match.group(1)
    print(f"Company slug: {company_slug}")  # "netflix"
else:
    print("Invalid Lever URL")

import requests

def get_lever_jobs(company_slug: str) -> list:
    """Fetch all jobs from a Lever company job board."""
    url = f"https://api.lever.co/v0/postings/{company_slug}?mode=json"

    response = requests.get(url, timeout=10)

    if response.status_code == 404:
        raise ValueError(f'Company "{company_slug}" not found or API disabled')

    response.raise_for_status()
    jobs = response.json()
    return jobs

# Usage
jobs = get_lever_jobs("netflix")
print(f"Found {len(jobs)} jobs")

from datetime import datetime

def parse_lever_job(job: dict) -> dict:
    """Parse a Lever job posting into a structured format."""
    categories = job.get("categories", {})
    salary = job.get("salaryRange")

    return {
        "id": job.get("id"),
        "title": job.get("text"),
        "location": categories.get("location"),
        "all_locations": categories.get("allLocations", [categories.get("location")]),
        "department": categories.get("department"),
        "team": categories.get("team"),
        "employment_type": categories.get("commitment"),
        "workplace_type": job.get("workplaceType"),  # remote, hybrid, onsite
        "description_plain": job.get("descriptionPlain") or job.get("description"),
        "description_html": job.get("description"),
        "description_body": job.get("descriptionBody"),
        "opening": job.get("opening"),
        "benefits": job.get("additional"),
        "lists": job.get("lists", []),  # Structured requirements/responsibilities
        "salary": {
            "min": salary.get("min"),
            "max": salary.get("max"),
            "currency": salary.get("currency"),
            "interval": salary.get("interval")
        } if salary else None,
        "apply_url": job.get("applyUrl"),
        "view_url": job.get("hostedUrl"),
        "posted_at": datetime.fromtimestamp(job.get("createdAt", 0) / 1000),
        "country": job.get("country")
    }

# Parse all jobs
jobs = get_lever_jobs("netflix")
parsed_jobs = [parse_lever_job(job) for job in jobs]
print(parsed_jobs[0])

def build_full_description(job: dict) -> str:
    """Build a complete HTML description from all Lever content sections."""
    parts = []

    # Add opening/intro section
    if job.get("opening"):
        parts.append(job["opening"])

    # Add main description body
    if job.get("descriptionBody"):
        parts.append(job["descriptionBody"])

    # Add structured lists (requirements, responsibilities)
    for lst in job.get("lists", []):
        if lst.get("text"):
            parts.append(f"<h3>{lst['text']}</h3>")
        if lst.get("content"):
            parts.append(lst["content"])

    # Add benefits/additional info
    if job.get("additional"):
        parts.append("<h3>Benefits & Perks</h3>")
        parts.append(job["additional"])

    return "\n\n".join(parts)

# Build full description for each job
for job in jobs:
    full_html = build_full_description(job)
    print(f"{job.get('text')}: {len(full_html)} chars")

import time
import requests

def scrape_multiple_companies(slugs: list, delay_seconds: float = 1.0) -> dict:
    """Scrape jobs from multiple Lever companies with rate limiting."""
    results = {}

    for slug in slugs:
        try:
            url = f"https://api.lever.co/v0/postings/{slug}?mode=json"
            response = requests.get(url, timeout=10)

            if response.status_code == 404:
                print(f"[SKIP] {slug}: Company not found")
                results[slug] = {"jobs": [], "error": "not_found"}
            else:
                response.raise_for_status()
                jobs = response.json()
                results[slug] = {"jobs": jobs, "error": None}
                print(f"[OK] {slug}: {len(jobs)} jobs")

        except requests.RequestException as e:
            print(f"[ERROR] {slug}: {e}")
            results[slug] = {"jobs": [], "error": str(e)}

        # Respect robots.txt crawl-delay of 1 second
        time.sleep(delay_seconds)

    return results

# Scrape multiple companies
companies = ["netflix", "spotify", "twitch", "lyft", "coinbase"]
results = scrape_multiple_companies(companies, delay_seconds=1.0)

total_jobs = sum(len(r["jobs"]) for r in results.values())
print(f"\nTotal jobs found: {total_jobs}")