scrapercity 1.0.13 → 1.0.15

package/AGENT_DOCS.txt

@@ -40,17 +40,13 @@ SCRAPE ENDPOINTS (POST /api/v1/scrape/{slug})
 
 apollo
   Body: { url: "https://app.apollo.io/#/people?...", count: 1000, fileName: "My Export" }
-  Returns: { runId, message }
+  Returns: { runId, message, lead_database? }
+    lead_database (when there are matches): { matches, url, api } - leads with the same
+    filters already in the Lead Database (ones you don't have), a dashboard link, and the
+    /api/v1/database/leads call that returns them now.
   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.
+  To filter by title/location/industry without a URL, use the Lead Database (below).
 
 maps
   Body: { searchStringsArray: ["plumbers"], locationQuery: "Denver, CO", maxCrawledPlacesPerSearch: 500 }
@@ -180,7 +176,8 @@ GET /api/v1/runs?hours=24&limit=50
   Returns: { runs: [{ run_id, status, handled, url, file_name, created_at }] }
 
 GET /api/v1/apollo-status
-  Returns: { useApify, message } - check if Apollo URL endpoint is available
+  Returns: { status: "url-based" | "legacy", message, timestamp } - "url-based" means the
+  Apollo URL endpoint is available
 
 ────────────────────────────────────────
 DATABASES (GET, $149/mo plan and up, 100k new records/day)
@@ -189,7 +186,17 @@ DATABASES (GET, $149/mo plan and up, 100k new records/day)
 GET /api/v1/database/leads?title=CTO&country=United States&hasEmail=true&page=1&limit=100
   Filters: title, industry, country, state, city, companyName, companyDomain,
            seniority, department, hasEmail, hasPhone, minEmployees, maxEmployees, socialUrl
+  Company filters: keywords (company tags, whole-word, any match), revenueMin, revenueMax (USD),
+           companyCountry, companyState, companyCity (company HQ, not the person)
+  Exclusions: notTitle, notKeywords, notIndustry
+  url=<people-search URL>: use that search's filters (other params override).
+           The response adds search_translation: { applied, approximated, not_supported }.
+           A URL with no filters the database can use returns 400.
+  POST /api/v1/database/leads with a JSON body takes the same parameters (arrays as JSON
+           arrays). Use it for a long url or long lists: a query string over ~16KB is refused.
+  Country: full name ("United States"); US, USA, UK, UAE also work.
   Array params use repeated keys: ?seniority=vp&seniority=director
+  (keywords / notKeywords also accept commas: ?keywords=saas,fintech)
   Optional:
     excludeDelivered=true  skip leads this account already has (from the API or the
                            dashboard). For daily pulls. Keep page=1 (or use after).
@@ -197,7 +204,15 @@ GET /api/v1/database/leads?title=CTO&country=United States&hasEmail=true&page=1&
                            pagination.next_after from each response until it is null.
   Every lead returned is saved to your account. Only NEW leads count toward the
   100k/day limit; fetching a lead you already have again is free.
-  Returns: { data: [...leads], pagination: { page, limit, total, totalPages, has_more, next_after }, rate_limit }
+  Returns: { data: [...leads], pagination: { page, limit, total, totalPages, has_more, next_after }, rate_limit,
+             search_translation? }
+  Lead fields include company_industry, company_size, employees_count, company_website,
+  company_annual_revenue, company_city, company_state, company_country, keywords.
+  409 with filters_not_applied_yet: the company filters listed can't be used yet (company
+  data still being prepared right after launch). Nothing is returned or counted; retry later
+  or drop those filters.
+  503: the search took too long to run. Narrow it (fewer titles or keywords, add a location
+  or company size) and retry.
 
 GET /api/v1/database/local-businesses?...
 GET /api/v1/database/ecommerce?...

package/SKILL.md

@@ -45,7 +45,6 @@ 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 |
@@ -78,8 +77,8 @@ Apollo scrapes take **up to 4 days** to deliver. Do NOT poll in a loop.
 | GET | `/api/v1/runs?hours=24&limit=50` | Recent runs |
 | POST | `/api/v1/scrape/cancel/{runId}` | Cancel running job |
 | GET | `/api/v1/scrape/logs/{runId}` | Run logs |
-| GET | `/api/v1/apollo-status` | Apollo service health |
-| GET | `/api/v1/database/leads?title=CTO&country=United%20States&hasEmail=true&limit=100` | Lead DB ($149/mo plan and up, 100k new leads/day). Optional: `excludeDelivered=true` (only leads you don't have yet), `after=0` then `pagination.next_after` (cursor paging) |
+| GET | `/api/v1/apollo-status` | Apollo service health: `{status: "url-based" or "legacy", message, timestamp}` |
+| GET | `/api/v1/database/leads?title=CTO&country=United%20States&hasEmail=true&limit=100` | Lead DB ($149/mo plan and up, 100k new leads/day). Optional: `excludeDelivered=true` (only leads you don't have yet), `after=0` then `pagination.next_after` (cursor paging). Company filters: `keywords`, `revenueMin`/`revenueMax`, `companyCountry`/`companyState`/`companyCity`. Exclusions: `notTitle`, `notKeywords`, `notIndustry`. `url=<people-search URL>` searches with that URL's filters. POST with a JSON body takes the same parameters (use it for a long `url`) |
 | GET | `/api/v1/database/local-businesses?...` | Local biz DB ($149/mo plan and up). Same optional `excludeDelivered` / `after` |
 | GET | `/api/v1/database/ecommerce?...` | Ecommerce DB ($149/mo plan and up). Same optional `excludeDelivered` / `after` |
 

package/bin/cli.mjs

@@ -5,7 +5,9 @@ import fs from 'fs'
 import readline from 'readline'
 
 const [,, cmd, ...args] = process.argv
-const flag = (name) => { const i = args.indexOf(name); return i !== -1 ? (args.splice(i, 2), args[i] || true) : undefined }
+// Read "--name value" and remove both from args. (It used to splice first and then read
+// args[i], which by then was the NEXT flag, so every value flag got the wrong value.)
+const flag = (name) => { const i = args.indexOf(name); if (i === -1) return undefined; const v = args[i + 1]; args.splice(i, 2); return v ?? true }
 const flagBool = (name) => { const i = args.indexOf(name); if (i !== -1) { args.splice(i, 1); return true } return false }
 const json = (d) => JSON.stringify(d, null, 2)
 
@@ -368,19 +370,24 @@ async function main() {
       // ── Database: Leads ($149/mo plan and up) ─────────────
       case 'db-leads': {
         const params = {}
-        for (const f of ['--title', '--industry', '--country', '--state', '--city',
-                         '--company', '--domain', '--company-size', '--seniority',
-                         '--department', '--page', '--limit', '--min-employees', '--max-employees', '--after']) {
-          const v = flag(f)
-          if (v === undefined) continue
-          const key = { '--title': 'title', '--industry': 'industry', '--country': 'country',
+        const keyFor = { '--title': 'title', '--industry': 'industry', '--country': 'country',
                         '--state': 'state', '--city': 'city', '--company': 'companyName',
-                        '--domain': 'companyDomain', '--company-size': 'companySize',
+                        '--domain': 'companyDomain',
                         '--seniority': 'seniority', '--department': 'department',
                         '--page': 'page', '--limit': 'limit',
                         '--min-employees': 'minEmployees', '--max-employees': 'maxEmployees',
-                        '--after': 'after' }[f]
-          params[key] = v
+                        '--after': 'after', '--url': 'url', '--apollo-url': 'apolloUrl',
+                        '--keywords': 'keywords', '--revenue-min': 'revenueMin', '--revenue-max': 'revenueMax',
+                        '--company-country': 'companyCountry', '--company-state': 'companyState',
+                        '--company-city': 'companyCity', '--not-title': 'notTitle',
+                        '--not-keywords': 'notKeywords', '--not-industry': 'notIndustry' }
+        // List filters take commas: --country "United States,Canada" sends both.
+        const lists = new Set(['--industry', '--country', '--state', '--seniority', '--department',
+                               '--company-country', '--company-state', '--not-industry'])
+        for (const f of Object.keys(keyFor)) {
+          const v = flag(f)
+          if (v === undefined) continue
+          params[keyFor[f]] = lists.has(f) ? v.split(',').map(s => s.trim()).filter(Boolean) : v
         }
         if (flagBool('--has-email')) params.hasEmail = 'true'
         if (flagBool('--has-phone')) params.hasPhone = 'true'
@@ -388,6 +395,8 @@ async function main() {
         const r = await sc.dbLeads(params)
         console.log(`${r.pagination?.total || '?'} total leads, page ${r.pagination?.page || 1} of ${r.pagination?.totalPages || '?'}`)
         if (r.pagination?.next_after) console.log(`Next page: --after ${r.pagination.next_after}`)
+        const tr = r.search_translation || r.apollo_translation
+        if (tr?.not_supported?.length) console.log(`Not supported from the search URL: ${tr.not_supported.join(', ')}`)
         console.log(json(r.data?.slice(0, 3) || r))
         if (r.data?.length > 3) console.log(`... and ${r.data.length - 3} more`)
         break
@@ -445,6 +454,11 @@ ScraperCity CLI - B2B lead generation from your terminal
 
   Database ($149/mo plan and up):
     scrapercity db-leads [filters]           Query lead database
+      --title --industry --country --state --city --company --domain --seniority --department
+      --min-employees --max-employees --has-email --has-phone
+      --keywords --revenue-min --revenue-max --company-country --company-state --company-city
+      --not-title --not-keywords --not-industry
+      --url "<people-search URL>"  Search with that URL's filters
       --exclude-delivered                    Only leads you don't already have
       --after <id>                           Cursor paging (start with 0, then use the printed next id)
 

package/bin/mcp.mjs

@@ -50,17 +50,30 @@ const UTILITY_TOOLS = [
   },
   {
     name: 'query_lead_database',
-    description: 'Query the B2B lead database directly. Returns contacts with names, emails, phones, titles, companies. Up to 100 per request. Included with the $149/mo plan (100,000 new leads a day; leads you already have do not count again). For a daily pull of only new leads set excludeDelivered=true. For big pulls page with after: send after="0" first, then the pagination.next_after from each response until it is null.',
+    description: 'Query the B2B lead database directly. Returns contacts with names, emails, phones, titles, companies (plus company website, revenue, HQ location and keywords). Up to 100 per request. Included with the $149/mo plan (100,000 new leads a day; leads you already have do not count again). For a daily pull of only new leads set excludeDelivered=true. For big pulls page with after: send after="0" first, then the pagination.next_after from each response until it is null. Have a saved people-search URL? Pass it as url to search with its filters right away (search_translation in the response says what was applied).',
     inputSchema: { type: 'object', properties: {
-      title: { type: 'string', description: 'Job title filter' },
-      industry: { type: 'string', description: 'Company industry' },
-      country: { type: 'string', description: 'Person country' },
-      state: { type: 'string', description: 'Person state' },
-      city: { type: 'string', description: 'Person city' },
+      url: { type: 'string', description: 'A people-search URL (the address of a people search with its filters). Its filters become the search; any other filter you pass overrides the matching one.' },
+      title: { type: 'string', description: 'Job title filter, comma separated for several (partial match, e.g. "CEO, Founder")' },
+      industry: { type: 'array', items: { type: 'string' }, description: 'Company industries (any match)' },
+      country: { type: 'array', items: { type: 'string' }, description: 'Person countries, full names like "United States" (US, USA, UK, UAE also work)' },
+      state: { type: 'array', items: { type: 'string' }, description: 'Person states' },
+      city: { type: 'string', description: 'Person city, comma separated for several' },
       companyName: { type: 'string', description: 'Company name' },
-      companyDomain: { type: 'string', description: 'Company domain' },
-      seniority: { type: 'string', description: 'e.g. "vp", "director", "c_suite"' },
-      department: { type: 'string', description: 'e.g. "sales", "engineering"' },
+      companyDomain: { type: 'string', description: 'Company domain(s), comma separated' },
+      seniority: { type: 'array', items: { type: 'string' }, description: 'e.g. ["vp", "director", "c_suite"]' },
+      department: { type: 'array', items: { type: 'string' }, description: 'e.g. ["sales", "engineering"]' },
+      minEmployees: { type: 'number', description: 'Minimum company employee count' },
+      maxEmployees: { type: 'number', description: 'Maximum company employee count' },
+      keywords: { type: 'array', items: { type: 'string' }, description: 'Company keywords/tags, any match (e.g. ["saas", "fintech"])' },
+      revenueMin: { type: 'number', description: 'Minimum company annual revenue, USD' },
+      revenueMax: { type: 'number', description: 'Maximum company annual revenue, USD' },
+      companyCountry: { type: 'array', items: { type: 'string' }, description: 'Company HQ countries (not where the person is)' },
+      companyState: { type: 'array', items: { type: 'string' }, description: 'Company HQ states' },
+      companyCity: { type: 'string', description: 'Company HQ city' },
+      notTitle: { type: 'string', description: 'Exclude titles containing any of these (comma separated)' },
+      notKeywords: { type: 'array', items: { type: 'string' }, description: 'Exclude companies with any of these keywords' },
+      notIndustry: { type: 'array', items: { type: 'string' }, description: 'Exclude these industries' },
+      socialUrl: { type: 'string', description: 'Match a social profile URL' },
       hasEmail: { type: 'boolean', description: 'Only contacts with email' },
       hasPhone: { type: 'boolean', description: 'Only contacts with phone' },
       page: { type: 'number', description: 'Page number (default 1)', default: 1 },

package/lib/catalog.generated.mjs

@@ -1,6 +1,6 @@
 // AUTO-GENERATED by scripts/generate.mjs — DO NOT EDIT BY HAND.
 // Source of truth: scraperConfigs.ts (+ src/config/scrapers.ts). Regenerate: npm run generate
-// Generated: 2026-09-28T13:03:17.780Z
+// Generated: 2026-10-02T14:29:37.617Z
 export const TOOLS = [
   {
     "name": "scrape_apollo",

package/lib/client.mjs

@@ -166,14 +166,21 @@ export const scrape = (slug, body) =>
 export const postEndpoint = (endpoint, body) => post(endpoint, body)
 
 // ── Databases ($649 plan) ─────────────────────────────────────
+// A long request (a big Apollo URL, a long title or keyword list) goes as a POST with a JSON body:
+// a query string past ~16KB is refused by the server before the search runs.
+const LONG_QUERY = 6000
 export const dbLeads = (params) => {
   const qs = new URLSearchParams()
+  const body = {}
   for (const [k, v] of Object.entries(params)) {
     if (v === undefined || v === null || v === '') continue
     if (Array.isArray(v)) v.forEach(x => qs.append(k, x))
     else qs.append(k, String(v))
+    body[k] = v
   }
-  return get(`${ENDPOINTS['database-leads']}?${qs}`)
+  const qstr = qs.toString()
+  if (qstr.length > LONG_QUERY) return post(ENDPOINTS['database-leads'], body)
+  return get(`${ENDPOINTS['database-leads']}?${qstr}`)
 }
 
 export const dbLocalBusinesses = (params) => {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "scrapercity",
-  "version": "1.0.13",
+  "version": "1.0.15",
   "description": "ScraperCity CLI & MCP Server - B2B lead generation for AI agents",
   "type": "module",
   "bin": {