Orchestrated Lead Generation Campaigns

{
  "campaign_id": "camp_lu_restaurants_20251223_abc123",
  "status": "active",
  "query": "restaurants",
  "country_code": "LU",
  "total_locations": 14,
  "has_workflow": true,
  "workflow_config": {
    "spidersite": {
      "enabled": true,
      "max_pages": 5,
      "extract_company_info": true
    },
    "spiderverify": {
      "enabled": true,
      "max_emails_per_business": 5
    }
  }
}

{
  "campaign_id": "camp_lu_restaurants_20251223_abc123",
  "status": "active",
  "progress": {
    "completed": 5,
    "failed": 0,
    "pending": 9,
    "total": 14,
    "percentage": 35.7
  },
  "workflow_progress": {
    "businesses_total": 150,
    "sites_queued": 5,
    "sites_completed": 120,
    "sites_failed": 2,
    "verifies_queued": 10,
    "verifies_completed": 80,
    "verifies_failed": 1,
    "emails_found": 350,
    "emails_verified": 280
  },
  "has_workflow": true
}

{
  "campaign_id": "camp_lu_restaurants_20251223_abc123",
  "status": "active",
  "query": "restaurants",
  "country_code": "LU",
  "workflow_progress": {
    "businesses_total": 69,
    "sites_completed": 69,
    "emails_found": 201,
    "emails_verified": 84
  },
  "total_businesses": 69,
  "total_with_domains": 69,
  "total_emails_found": 201,
  "total_valid_emails": 8,
  "locations": [
    {
      "location_id": 843,
      "search_string": "Luxembourg, Luxembourg",
      "status": "completed",
      "businesses_count": 69,
      "businesses": [
        {
          "business_name": "Café des Tramways",
          "business_place_id": "0x47954f2add89aa79:0x74c726ae28575bec",
          "business_address": "79 Av. Pasteur, 2311 Luxembourg",
          "business_phone": "35226201136",
          "business_rating": 4.4,
          "business_reviews_count": 706,
          "business_categories": ["Bar", "Coffee shop"],
          "original_website": "http://www.cafedestramways.lu/",
          "domain": "cafedestramways.lu",
          "domain_filtered": false,
          "spidersite_status": "completed",
          "pages_crawled": 2,
          "emails_found": ["info@cafedestramways.lu"],
          "company_info": {
            "industry": "Restaurant/Bar",
            "key_services": ["Flammekueches", "Burgers", "Cocktails"],
            "target_audience": "Locals and tourists in Luxembourg",
            "one_sentence_summary": "Cozy bar offering drinks and homemade food"
          },
          "spiderverify_status": "completed",
          "emails_verified": [
            {
              "email": "info@cafedestramways.lu",
              "status": "risky",
              "score": 90,
              "is_deliverable": true,
              "is_role_account": true
            }
          ],
          "valid_emails_count": 0,
          "workflow_stage": "complete"
        }
      ]
    }
  ]
}

import requests
import time
import csv

# Configuration
API_URL = "https://spideriq.di-atomic.com/api/v1"
TOKEN = "your_token_here"
HEADERS = {"Authorization": f"Bearer {TOKEN}"}

# 1. Create Campaign with Workflow
campaign_response = requests.post(
    f"{API_URL}/jobs/spiderMaps/campaigns/submit",
    headers=HEADERS,
    json={
        "query": "restaurants",
        "country_code": "LU",
        "name": "Luxembourg Restaurant Leads",
        "workflow": {
            "spidersite": {
                "enabled": True,
                "max_pages": 5,
                "extract_company_info": True
            },
            "spiderverify": {
                "enabled": True,
                "max_emails_per_business": 3
            }
        }
    }
)
campaign = campaign_response.json()
campaign_id = campaign['campaign_id']
print(f"Created campaign: {campaign_id}")
print(f"Total locations: {campaign['total_locations']}")

# 2. Process all locations
while True:
    next_response = requests.post(
        f"{API_URL}/jobs/spiderMaps/campaigns/{campaign_id}/next",
        headers=HEADERS
    )
    next_data = next_response.json()

    if next_data.get('current_task'):
        task = next_data['current_task']
        print(f"Processing: {task['search_string']} (job: {task['job_id']})")

    progress = next_data['progress']
    print(f"Progress: {progress['completed']}/{progress['total']} ({progress['percentage']:.1f}%)")

    if not next_data['has_more']:
        print("All locations processed!")
        break

    time.sleep(2)  # Rate limit between calls

# 3. Wait for workflow jobs to complete
print("\nWaiting for SpiderSite and SpiderVerify jobs to complete...")
while True:
    status_response = requests.get(
        f"{API_URL}/jobs/spiderMaps/campaigns/{campaign_id}/status",
        headers=HEADERS
    )
    status = status_response.json()
    wp = status.get('workflow_progress', {})

    sites_done = wp.get('sites_completed', 0) + wp.get('sites_failed', 0)
    sites_total = wp.get('businesses_total', 0)
    verifies_done = wp.get('verifies_completed', 0) + wp.get('verifies_failed', 0)

    print(f"Sites: {sites_done}/{sites_total} | Verifies: {verifies_done} | Emails: {wp.get('emails_found', 0)}")

    # Check if workflow is complete (all sites done and verifies caught up)
    if sites_done >= sites_total and wp.get('verifies_queued', 0) == 0:
        break

    time.sleep(5)

# 4. Get aggregated results
results_response = requests.get(
    f"{API_URL}/jobs/spiderMaps/campaigns/{campaign_id}/workflow-results",
    headers=HEADERS
)
results = results_response.json()

# 5. Export to CSV
with open('leads.csv', 'w', newline='', encoding='utf-8') as f:
    writer = csv.writer(f)
    writer.writerow([
        'Business Name', 'Address', 'Phone', 'Website', 'Rating',
        'Industry', 'Email', 'Email Status', 'Email Score'
    ])

    for location in results['locations']:
        for biz in location['businesses']:
            for email in biz.get('emails_verified', []):
                writer.writerow([
                    biz['business_name'],
                    biz.get('business_address', ''),
                    biz.get('business_phone', ''),
                    biz.get('domain', ''),
                    biz.get('business_rating', ''),
                    biz.get('company_info', {}).get('industry', ''),
                    email['email'],
                    email['status'],
                    email['score']
                ])

print(f"\nExported {results['total_valid_emails']} valid emails to leads.csv")
print(f"Total businesses: {results['total_businesses']}")
print(f"Total emails found: {results['total_emails_found']}")

{
  "workflow": {
    "spidersite": {
      "enabled": true,
      "max_pages": 5,
      "crawl_strategy": "bestfirst",
      "extract_company_info": true,
      "compendium": {
        "enabled": false
      }
    },
    "spiderverify": {
      "enabled": true,
      "max_emails_per_business": 3
    }
  }
}