scrapercity 1.0.4 → 1.0.6

package/AGENT_DOCS.txt

@@ -18,6 +18,14 @@ apollo
   Cost: $0.0039/lead | Min 500, max 50000
   DELIVERY: UP TO 4 DAYS. Use webhook, not polling.
 
+apollo-filters
+  Body: { seniorityLevel, functionDept, companyIndustry, personCountry, personState,
+          companyCountry, companyState, companySize, personTitles:[], companyDomains:[],
+          companyKeywords:[], personCities:[], companyCities:[], hasPhone, count, fileName }
+  At least one filter required.
+  Returns: { runId, message }
+  Cost: $0.0039/lead | DELIVERY: UP TO 4 DAYS.
+
 maps
   Body: { searchStringsArray: ["plumbers"], locationQuery: "Denver, CO", maxCrawledPlacesPerSearch: 500 }
   Returns: { runId, datasetId, priceMicro }
@@ -149,9 +157,7 @@ GET /api/v1/apollo-status
   Returns: { useApify, message } - check if Apollo URL endpoint is available
 
 ────────────────────────────────────────
-DATABASES (GET, $149+ plans, 100k/day)
-This is the recommended path for filter-based B2B people search (by title,
-industry, location, seniority, etc). Returns instantly from a cached dataset.
+DATABASES (GET, $649 plan only, 100k/day)
 ────────────────────────────────────────
 
 GET /api/v1/database/leads?title=CTO&country=United States&hasEmail=true&page=1&limit=100
@@ -178,20 +184,19 @@ ERROR CODES
 WORKFLOW EXAMPLES
 ────────────────────────────────────────
 
-1. LEAD DATABASE (instant, recommended for B2B people search):
-   GET /api/v1/database/leads?title=CTO&industry=computer+software&hasEmail=true&page=1
-   Loop pages until page > totalPages.
-   This is the supported path for filter-based B2B contact search ($149+ plans).
-
-2. MAPS SCRAPE (fast):
+1. MAPS SCRAPE (fast):
    POST /api/v1/scrape/maps → get runId → poll status every 15s → download CSV
 
-3. APOLLO SCRAPE (slow, only when user provides an apollo.io URL):
+2. APOLLO SCRAPE (slow):
    POST /api/v1/scrape/apollo → get runId → configure webhook → wait for callback
    Do NOT poll Apollo in a tight loop. Check once per hour at most.
 
-4. ENRICH PIPELINE:
-   Database/Maps → download CSV → extract emails → POST email-validator → download validated CSV
+3. ENRICH PIPELINE:
+   Apollo/Maps → download CSV → extract emails → POST email-validator → download validated CSV
+
+4. LEAD DATABASE (instant):
+   GET /api/v1/database/leads?title=CTO&industry=computer+software&hasEmail=true&page=1
+   Loop pages until page > totalPages
 
 5. LOCAL BUSINESS PIPELINE:
    Yelp/Angi/Maps → download CSV → POST email-finder with names+domains → POST mobile-finder

package/SKILL.md

@@ -20,6 +20,7 @@ Auth: `Authorization: Bearer $SCRAPERCITY_API_KEY` on all requests.
 | Slug | Input | Cost | Speed |
 |------|-------|------|-------|
 | `apollo` | `{url, count, fileName}` | $0.0039/lead | ~4 DAYS (use webhook) |
+| `apollo-filters` | `{seniorityLevel, functionDept, companyIndustry, personCountry, personState, companySize, personTitles[], companyDomains[], count}` | $0.0039/lead | ~4 DAYS |
 | `maps` | `{searchStringsArray:["query"], locationQuery, maxCrawledPlacesPerSearch}` | $0.01/place | 5-30 min |
 | `email-validator` | `{emails:["a@b.com"]}` | $0.0036/email | 1-10 min |
 | `email-finder` | `{contacts:[{first_name,last_name,domain}], autoValidateEmails, autoFindMobiles}` | $0.05/contact | 1-10 min |

package/bin/cli.mjs

@@ -97,6 +97,40 @@ async function main() {
         break
       }
 
+      // ── Apollo Filters ────────────────────────────────────
+      case 'apollo-filters': {
+        const filters = {}
+        for (const f of ['--seniority', '--function', '--industry', '--country', '--state',
+                         '--company-country', '--company-state', '--company-size', '--count', '--name', '--has-phone']) {
+          const v = flag(f)
+          if (v === undefined) continue
+          const key = {
+            '--seniority': 'seniorityLevel', '--function': 'functionDept',
+            '--industry': 'companyIndustry', '--country': 'personCountry',
+            '--state': 'personState', '--company-country': 'companyCountry',
+            '--company-state': 'companyState', '--company-size': 'companySize',
+            '--count': 'count', '--name': 'fileName', '--has-phone': 'hasPhone'
+          }[f]
+          filters[key] = f === '--has-phone' ? true : (f === '--count' ? +v : v)
+        }
+        // Array flags
+        for (const f of ['--titles', '--domains', '--keywords', '--person-cities', '--company-cities']) {
+          const v = flag(f)
+          if (!v) continue
+          const key = { '--titles': 'personTitles', '--domains': 'companyDomains',
+                        '--keywords': 'companyKeywords', '--person-cities': 'personCities',
+                        '--company-cities': 'companyCities' }[f]
+          filters[key] = v.split(',').map(s => s.trim())
+        }
+        if (!Object.keys(filters).length) die('At least one filter required. Example: scrapercity apollo-filters --industry "computer software" --country "United States" --count 1000')
+        const r = await sc.apolloFilters(filters)
+        console.log(`✓ Apollo filter search started`)
+        console.log(`  Run ID: ${r.runId}`)
+        console.log(`  ${r.message || ''}`)
+        console.log(`  Note: Apollo takes up to 4 days. Set up a webhook to get notified.`)
+        break
+      }
+
       // ── Maps ──────────────────────────────────────────────
       case 'maps': {
         const query = flag('--query') || flag('-q')
@@ -432,6 +466,7 @@ ScraperCity CLI - B2B lead generation from your terminal
 
   Scrapers:
     scrapercity apollo <url> [--count N]     Apollo scrape (URL-based, ~4 day delivery)
+    scrapercity apollo-filters [filters]     Apollo scrape (filter-based)
     scrapercity maps -q <query> -l <loc>     Google Maps scrape
     scrapercity email-validate <emails>      Validate email addresses
     scrapercity email-find --first X --last Y --domain Z    Find business emails

package/bin/mcp.mjs

@@ -42,6 +42,31 @@ const TOOLS = [
       required: ['url']
     }
   },
+  {
+    name: 'scrape_apollo_filters',
+    description: 'Scrape leads from Apollo.io using filter parameters instead of a URL. Same 4-day delivery - use webhooks. At least one filter required.',
+    inputSchema: {
+      type: 'object',
+      properties: {
+        seniorityLevel: { type: 'string', description: 'e.g. "director", "vp", "c_suite", "manager", "senior"' },
+        functionDept: { type: 'string', description: 'e.g. "sales", "marketing", "engineering", "finance"' },
+        companyIndustry: { type: 'string', description: 'e.g. "computer software", "financial services"' },
+        personCountry: { type: 'string', description: 'e.g. "United States", "United Kingdom"' },
+        personState: { type: 'string', description: 'e.g. "California", "New York"' },
+        companyCountry: { type: 'string', description: 'Company HQ country' },
+        companyState: { type: 'string', description: 'Company HQ state' },
+        companySize: { type: 'string', description: 'e.g. "11-50", "51-200", "201-500", "501-1000", "1001-5000"' },
+        personTitles: { type: 'array', items: { type: 'string' }, description: 'Specific job titles to target' },
+        companyDomains: { type: 'array', items: { type: 'string' }, description: 'Specific company domains' },
+        companyKeywords: { type: 'array', items: { type: 'string' }, description: 'Company description keywords' },
+        personCities: { type: 'array', items: { type: 'string' }, description: 'Person city filter' },
+        companyCities: { type: 'array', items: { type: 'string' }, description: 'Company city filter' },
+        hasPhone: { type: 'boolean', description: 'Only return contacts with phone numbers', default: false },
+        count: { type: 'number', description: 'Number of leads (min 500, max 50000)', default: 1000 },
+        fileName: { type: 'string', description: 'Export name', default: 'Apollo Export' }
+      }
+    }
+  },
   {
     name: 'scrape_maps',
     description: 'Scrape businesses from Google Maps. Returns businesses with names, addresses, phone numbers, websites, emails, ratings. Typically completes in 5-30 minutes.',
@@ -358,6 +383,10 @@ server.setRequestHandler(CallToolRequestSchema, async (request) => {
         result = await sc.apollo(args.url, args.count || 1000, args.fileName || '')
         result._note = 'Apollo takes 11-48+ hours. Configure webhook at app.scrapercity.com/dashboard/webhooks instead of polling.'
         break
+      case 'scrape_apollo_filters':
+        result = await sc.apolloFilters(args)
+        result._note = 'Apollo takes 11-48+ hours. Configure webhook at app.scrapercity.com/dashboard/webhooks instead of polling.'
+        break
       case 'scrape_maps':
         result = await sc.maps(args.query, args.location, args.limit || 500)
         break

package/lib/client.mjs

@@ -83,12 +83,8 @@ export async function download(runId, outputPath) {
 export const apollo = (url, count = 1000, fileName = '') =>
   post('/api/v1/scrape/apollo', { url, count, fileName })
 
-// apolloFilters was the filter-based Apollo endpoint. It has been retired.
-// For B2B people search by filter, use the Lead Database (GET /api/v1/database/leads,
-// included on the $149/mo plan and above).
-export const apolloFilters = () => {
-  throw new Error('apolloFilters is no longer available. Use the Lead Database (GET /api/v1/database/leads) instead - included on the $149/mo plan and above.')
-}
+export const apolloFilters = (filters) =>
+  post('/api/v1/scrape/apollo-filters', filters)
 
 export const apolloStatus = () => get('/api/v1/apollo-status')
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "scrapercity",
-  "version": "1.0.4",
+  "version": "1.0.6",
   "description": "ScraperCity CLI & MCP Server - B2B lead generation for AI agents",
   "type": "module",
   "bin": {