import os
import time
import sys
from scrapers.ats_ingestion import run_ats_direct_ingestion
from scrapers.art_and_design_ingestion import run_art_and_design_ingestion
from scrapers.expanded_categories_ingestion import run_expanded_categories_ingestion
from scrapers.major_ct_employers import run_major_ct_employers_scrape
from scrapers.jobaps_ct import run_ct_jobaps_scrape
from scrapers.jobspy_runner import run_jobspy_scrapes
from scrapers.smart_careers_crawler import SmartCareersCrawler
from db import upsert_jobs

# Targeted domains for smart careers auto-discovery across US
DOMAINS_TO_PROBE = [
    ("anthropic.com", "Anthropic"),
    ("openai.com", "OpenAI"),
    ("stripe.com", "Stripe"),
    ("ramp.com", "Ramp"),
    ("brex.com", "Brex"),
    ("plaid.com", "Plaid"),
    ("figma.com", "Figma"),
    ("linear.app", "Linear"),
    ("notion.so", "Notion"),
    ("cursor.com", "Cursor"),
    ("superhuman.com", "Superhuman"),
    ("vercel.com", "Vercel"),
    ("supabase.com", "Supabase"),
    ("datadoghq.com", "Datadog"),
    ("cloudflare.com", "Cloudflare"),
    ("posthog.com", "PostHog"),
    ("sentry.io", "Sentry"),
    ("resend.com", "Resend"),
    ("retool.com", "Retool"),
    ("duolingo.com", "Duolingo"),
    ("canva.com", "Canva"),
    ("roblox.com", "Roblox"),
    ("epicgames.com", "Epic Games"),
    ("flexport.com", "Flexport")
]

def run_smart_crawler_scrapes():
    print("[Smart Crawler] Probing company domains for live /careers, /jobs & ATS endpoints...")
    crawler = SmartCareersCrawler()
    discovered_jobs = []

    for domain, company_name in DOMAINS_TO_PROBE:
        try:
            provider, slug, careers_url = crawler.probe_domain_for_careers(domain)
            if provider and slug:
                print(f"[Smart Crawler] Discovered {company_name} ATS: {provider.upper()} -> '{slug}'")
                if provider == "greenhouse":
                    jobs = crawler.fetch_greenhouse_board(slug, company_name)
                    discovered_jobs.extend(jobs)
                elif provider == "lever":
                    jobs = crawler.fetch_lever_board(slug, company_name)
                    discovered_jobs.extend(jobs)
                elif provider == "ashby":
                    jobs = crawler.fetch_ashby_board(slug, company_name)
                    discovered_jobs.extend(jobs)
        except Exception as e:
            print(f"[Smart Crawler Warning] Probing {domain} failed: {e}")

    print(f"[Smart Crawler] Successfully gathered {len(discovered_jobs)} postings via smart domain probing.")
    return discovered_jobs

def execute_all_scrapes():
    print("\n==============================================")
    print("Starting Nationwide Multi-Source Ingestion Pipeline...")
    print("==============================================")

    all_jobs = []

    # 1. Smart Domain Careers Crawler (/careers, /jobs, Greenhouse/Lever/Ashby)
    try:
        crawler_jobs = run_smart_crawler_scrapes()
        all_jobs.extend(crawler_jobs)
    except Exception as e:
        print(f"[Error] Smart Careers Crawler error: {e}")

    # 2. Direct Public ATS Board Ingestion (Greenhouse, Lever, Ashby uncapped)
    try:
        ats_jobs = run_ats_direct_ingestion()
        all_jobs.extend(ats_jobs)
    except Exception as e:
        print(f"[Error] ATS Ingestion error: {e}")

    # 3. Dedicated Art, Creative, Gaming & Design Ingestion
    try:
        art_jobs = run_art_and_design_ingestion()
        all_jobs.extend(art_jobs)
    except Exception as e:
        print(f"[Error] Art & Design Ingestion error: {e}")

    # 4. Expanded Legal, Education, Trades, Logistics, HR, Biotech
    try:
        exp_jobs = run_expanded_categories_ingestion()
        all_jobs.extend(exp_jobs)
    except Exception as e:
        print(f"[Error] Expanded categories error: {e}")

    # 5. Major CT & Regional Enterprise Employers
    try:
        emp_jobs = run_major_ct_employers_scrape()
        all_jobs.extend(emp_jobs)
    except Exception as e:
        print(f"[Error] Major Employers error: {e}")

    # 6. CT State JobAps Government & Public Portal
    try:
        ct_jobs = run_ct_jobaps_scrape()
        all_jobs.extend(ct_jobs)
    except Exception as e:
        print(f"[Error] CT JobAps execution error: {e}")

    # 7. JobSpy Nationwide US Metros & Remote Broad Searches
    try:
        jobspy_jobs = run_jobspy_scrapes()
        all_jobs.extend(jobspy_jobs)
    except Exception as e:
        print(f"[Error] JobSpy execution error: {e}")

    print(f"\n==============================================")
    print(f"Total job postings ingested: {len(all_jobs)}")
    print("==============================================")

    if all_jobs:
        count = upsert_jobs(all_jobs)
        print(f"✅ Successfully written/updated {count} jobs into database.")
    else:
        print("No job records were collected in this run.")

if __name__ == "__main__":
    if len(sys.argv) > 1 and sys.argv[1] == "--once":
        execute_all_scrapes()
        sys.exit(0)

    try:
        from apscheduler.schedulers.blocking import BlockingScheduler
        interval = int(os.getenv("SCRAPE_INTERVAL_MINUTES", "30"))
        print(f"Scraper worker starting. Scheduled to run every {interval} minutes.")

        execute_all_scrapes()

        scheduler = BlockingScheduler()
        scheduler.add_job(execute_all_scrapes, 'interval', minutes=interval)
        scheduler.start()
    except ImportError:
        print("[Warning] APScheduler not found. Executing single scrape run.")
        execute_all_scrapes()
    except (KeyboardInterrupt, SystemExit):
        print("Scraper worker stopped.")