enrich-companies 1.0.0

package/README.md

@@ -0,0 +1,111 @@
+# enrich-csv
+
+Enrich a CSV of companies with revenue, credit score, employees, and financial data. Powered by the [Score API](https://score.get-scala.com/api) — 272M+ companies from 265 countries.
+
+**The Clearbit / ZoomInfo / D&B alternative that costs €0 to start.**
+
+## Quick Start
+
+```bash
+npx enrich-csv leads.csv -o enriched.csv
+```
+
+That's it. No signup needed. Free tier: 50 lookups/month.
+
+## Installation
+
+```bash
+npm install -g enrich-csv
+```
+
+Or use directly with `npx` (no install needed):
+
+```bash
+npx enrich-csv input.csv -o output.csv
+```
+
+## Usage
+
+```bash
+# Basic: enrich a CSV file
+enrich-csv companies.csv -o enriched.csv
+
+# Filter by country
+enrich-csv leads.csv --country IT -o italian-leads.csv
+
+# Specify which column contains company names
+enrich-csv data.csv --column "Company Name" -o enriched.csv
+
+# Choose which fields to add
+enrich-csv leads.csv --fields revenue,score,grade,employees -o enriched.csv
+
+# Use with API key for higher limits
+enrich-csv leads.csv -k sk_live_your_key -o enriched.csv
+
+# Pipe from stdin
+cat companies.txt | enrich-csv - -o results.csv
+
+# Dry run (see what would be enriched)
+enrich-csv leads.csv --dry-run
+```
+
+## What Gets Added
+
+For each company in your CSV, enrich-csv adds:
+
+| Field | Description |
+|-------|-------------|
+| `score_revenue` | Annual revenue (EUR) |
+| `score_employees` | Employee count |
+| `score_score` | Credit score 0-100 |
+| `score_grade` | Letter grade (AA to E) |
+| `score_country` | ISO country code |
+| `score_city` | City |
+| `score_sector_desc` | Industry description |
+
+## Example
+
+**Input (leads.csv):**
+```csv
+Company,Contact,Email
+Tesla,John,john@tesla.com
+Ferrero,Maria,maria@ferrero.com
+SAP,Hans,hans@sap.com
+```
+
+**Output (enriched.csv):**
+```csv
+Company,Contact,Email,score_revenue,score_employees,score_score,score_grade,score_country,score_city,score_sector_desc
+Tesla,John,john@tesla.com,96773000000,140000,85,A,US,Austin,Motor Vehicle Manufacturing
+Ferrero,Maria,maria@ferrero.com,19300000000,48697,75,BBB,IT,Alba,Food Manufacturing
+SAP,Hans,hans@sap.com,35000000000,107000,88,A,DE,Walldorf,Software Publishing
+```
+
+## API Pricing
+
+| Plan | Lookups/month | Price |
+|------|--------------|-------|
+| Free | 50 | €0 |
+| Starter | 500 | €19/mo |
+| Growth | 5,000 | €49/mo |
+| Enterprise | 50,000 | €149/mo |
+
+Get your free API key: https://score.get-scala.com/api/free-key
+
+## Data Coverage
+
+272,116,630 companies across 265 countries. Top coverage:
+
+🇧🇷 Brazil 47M · 🇺🇸 USA 39M · 🇦🇺 Australia 20M · 🇫🇷 France 17M · 🇬🇧 UK 14M · 🇩🇪 Germany 10M · 🇮🇳 India 8M · 🇯🇵 Japan 7M · 🇮🇹 Italy 6M · 🇪🇸 Spain 5M
+
+## Related
+
+- [Score API](https://score.get-scala.com/api) — Full REST API
+- [scala-score](https://www.npmjs.com/package/scala-score) — Node.js SDK
+- [scala-mcp-server](https://www.npmjs.com/package/scala-mcp-server) — MCP server for AI agents
+- [Dataset on Kaggle](https://www.kaggle.com/datasets/yorkiealfbroth/global-company-data-994k) — Free 994K sample
+- [Dataset on HuggingFace](https://huggingface.co/datasets/alf1990mi/global-company-database-1m) — Free 1M sample
+
+## License
+
+MIT — Built by [SCALA AI](https://get-scala.com)

package/index.js

@@ -0,0 +1,279 @@
+#!/usr/bin/env node
+
+const fs = require('fs');
+const https = require('https');
+const path = require('path');
+
+const VERSION = '1.0.0';
+const API_BASE = 'https://score.get-scala.com/api/search';
+const RATE_LIMIT_MS = 200;
+
+function usage() {
+  console.log(`
+enrich-csv v${VERSION} — Enrich company data from 272M+ businesses
+
+USAGE:
+  enrich-csv input.csv [options]
+  cat companies.csv | enrich-csv - [options]
+
+OPTIONS:
+  -o, --output FILE    Output file (default: stdout)
+  -k, --key KEY        Score API key (or set SCORE_API_KEY env var)
+  -c, --column NAME    Column name containing company names (default: auto-detect)
+  --country CC         Filter by ISO country code (e.g., IT, US, DE)
+  --delimiter CHAR     CSV delimiter (default: auto-detect , or ;)
+  --limit N            Max results per lookup (default: 1)
+  --fields FIELDS      Fields to add (default: revenue,employees,score,grade,country,city,sector_desc)
+  --dry-run            Show what would be enriched without calling API
+  -h, --help           Show this help
+  -v, --version        Show version
+
+EXAMPLES:
+  enrich-csv leads.csv -o enriched.csv
+  enrich-csv leads.csv --country IT --key sk_live_xxx
+  enrich-csv leads.csv --column "Company Name" --fields revenue,score,grade
+  cat names.txt | enrich-csv - -o results.csv
+
+FREE TIER: 50 lookups/month (no key needed)
+Get API key: https://score.get-scala.com/api/free-key
+
+PRICING:
+  Free       50 lookups/month    €0
+  Starter   500 lookups/month   €19/mo
+  Growth  5,000 lookups/month   €49/mo
+  Enterprise 50,000 lookups/mo  €149/mo
+
+More info: https://score.get-scala.com/api
+`);
+}
+
+function parseArgs() {
+  const args = process.argv.slice(2);
+  const opts = {
+    input: null,
+    output: null,
+    key: process.env.SCORE_API_KEY || null,
+    column: null,
+    country: null,
+    delimiter: null,
+    limit: 1,
+    fields: ['revenue', 'employees', 'score', 'grade', 'country', 'city', 'sector_desc'],
+    dryRun: false,
+  };
+
+  for (let i = 0; i < args.length; i++) {
+    const a = args[i];
+    if (a === '-h' || a === '--help') { usage(); process.exit(0); }
+    if (a === '-v' || a === '--version') { console.log(VERSION); process.exit(0); }
+    if (a === '-o' || a === '--output') { opts.output = args[++i]; continue; }
+    if (a === '-k' || a === '--key') { opts.key = args[++i]; continue; }
+    if (a === '-c' || a === '--column') { opts.column = args[++i]; continue; }
+    if (a === '--country') { opts.country = args[++i]; continue; }
+    if (a === '--delimiter') { opts.delimiter = args[++i]; continue; }
+    if (a === '--limit') { opts.limit = parseInt(args[++i], 10); continue; }
+    if (a === '--fields') { opts.fields = args[++i].split(','); continue; }
+    if (a === '--dry-run') { opts.dryRun = true; continue; }
+    if (!opts.input) { opts.input = a; continue; }
+  }
+
+  return opts;
+}
+
+function detectDelimiter(line) {
+  const semicolons = (line.match(/;/g) || []).length;
+  const commas = (line.match(/,/g) || []).length;
+  const tabs = (line.match(/\t/g) || []).length;
+  if (tabs > commas && tabs > semicolons) return '\t';
+  if (semicolons > commas) return ';';
+  return ',';
+}
+
+function parseCSVLine(line, delimiter) {
+  const fields = [];
+  let current = '';
+  let inQuotes = false;
+
+  for (let i = 0; i < line.length; i++) {
+    const c = line[i];
+    if (c === '"') {
+      if (inQuotes && line[i + 1] === '"') { current += '"'; i++; }
+      else { inQuotes = !inQuotes; }
+    } else if (c === delimiter && !inQuotes) {
+      fields.push(current.trim());
+      current = '';
+    } else {
+      current += c;
+    }
+  }
+  fields.push(current.trim());
+  return fields;
+}
+
+function escapeCSV(val, delimiter) {
+  if (val == null) return '';
+  const s = String(val);
+  if (s.includes(delimiter) || s.includes('"') || s.includes('\n')) {
+    return '"' + s.replace(/"/g, '""') + '"';
+  }
+  return s;
+}
+
+function detectNameColumn(headers) {
+  const patterns = [
+    /^company$/i, /^company.?name$/i, /^name$/i, /^business$/i,
+    /^business.?name$/i, /^organization$/i, /^org$/i, /^azienda$/i,
+    /^ragione.?sociale$/i, /^empresa$/i, /^entreprise$/i, /^firma$/i,
+    /^unternehmen$/i, /^nome$/i, /^denominazione$/i,
+  ];
+
+  for (const p of patterns) {
+    const idx = headers.findIndex(h => p.test(h));
+    if (idx >= 0) return idx;
+  }
+  return 0;
+}
+
+function apiSearch(query, country, key, limit) {
+  return new Promise((resolve, reject) => {
+    let url = `${API_BASE}?q=${encodeURIComponent(query)}&limit=${limit}`;
+    if (country) url += `&country=${country}`;
+    if (key) url += `&key=${key}`;
+
+    https.get(url, { headers: { 'User-Agent': `enrich-csv/${VERSION}` } }, (res) => {
+      let data = '';
+      res.on('data', c => data += c);
+      res.on('end', () => {
+        try {
+          const json = JSON.parse(data);
+          if (json.results && json.results.length > 0) {
+            resolve(json.results[0]);
+          } else {
+            resolve(null);
+          }
+        } catch {
+          resolve(null);
+        }
+      });
+    }).on('error', () => resolve(null));
+  });
+}
+
+function sleep(ms) { return new Promise(r => setTimeout(r, ms)); }
+
+function formatRevenue(val) {
+  if (!val || val === 0) return '';
+  if (val >= 1e9) return `€${(val / 1e9).toFixed(1)}B`;
+  if (val >= 1e6) return `€${(val / 1e6).toFixed(1)}M`;
+  if (val >= 1e3) return `€${(val / 1e3).toFixed(0)}K`;
+  return `€${val}`;
+}
+
+async function main() {
+  const opts = parseArgs();
+
+  if (!opts.input) {
+    console.error('Error: no input file specified. Use --help for usage.');
+    process.exit(1);
+  }
+
+  let inputData;
+  if (opts.input === '-') {
+    const chunks = [];
+    for await (const chunk of process.stdin) chunks.push(chunk);
+    inputData = Buffer.concat(chunks).toString('utf-8');
+  } else {
+    if (!fs.existsSync(opts.input)) {
+      console.error(`Error: file not found: ${opts.input}`);
+      process.exit(1);
+    }
+    inputData = fs.readFileSync(opts.input, 'utf-8');
+  }
+
+  const lines = inputData.split('\n').filter(l => l.trim());
+  if (lines.length < 2) {
+    console.error('Error: CSV must have a header row and at least one data row.');
+    process.exit(1);
+  }
+
+  const delimiter = opts.delimiter || detectDelimiter(lines[0]);
+  const headers = parseCSVLine(lines[0], delimiter);
+  const nameColIdx = opts.column
+    ? headers.findIndex(h => h.toLowerCase() === opts.column.toLowerCase())
+    : detectNameColumn(headers);
+
+  if (nameColIdx < 0) {
+    console.error(`Error: column "${opts.column}" not found. Available: ${headers.join(', ')}`);
+    process.exit(1);
+  }
+
+  const enrichedHeaders = [...headers, ...opts.fields.map(f => `score_${f}`)];
+  const outputLines = [enrichedHeaders.map(h => escapeCSV(h, delimiter)).join(delimiter)];
+
+  const total = lines.length - 1;
+  let enriched = 0;
+  let notFound = 0;
+
+  process.stderr.write(`\nEnriching ${total} companies from column "${headers[nameColIdx]}"...\n`);
+  if (!opts.key) {
+    process.stderr.write('No API key — using free tier (50 lookups/month)\n');
+    process.stderr.write('Get unlimited: https://score.get-scala.com/api/free-key\n');
+  }
+  process.stderr.write('\n');
+
+  for (let i = 1; i < lines.length; i++) {
+    const row = parseCSVLine(lines[i], delimiter);
+    const companyName = row[nameColIdx];
+
+    if (!companyName || !companyName.trim()) {
+      const emptyRow = [...row, ...opts.fields.map(() => '')];
+      outputLines.push(emptyRow.map(v => escapeCSV(v, delimiter)).join(delimiter));
+      continue;
+    }
+
+    process.stderr.write(`  [${i}/${total}] ${companyName.substring(0, 40).padEnd(40)} `);
+
+    if (opts.dryRun) {
+      process.stderr.write('(dry run)\n');
+      const emptyRow = [...row, ...opts.fields.map(() => '')];
+      outputLines.push(emptyRow.map(v => escapeCSV(v, delimiter)).join(delimiter));
+      continue;
+    }
+
+    const result = await apiSearch(companyName, opts.country, opts.key, opts.limit);
+
+    if (result) {
+      enriched++;
+      const enrichedValues = opts.fields.map(f => {
+        if (f === 'revenue') return result.revenue || '';
+        return result[f] != null ? result[f] : '';
+      });
+      const enrichedRow = [...row, ...enrichedValues];
+      outputLines.push(enrichedRow.map(v => escapeCSV(v, delimiter)).join(delimiter));
+      process.stderr.write(`✓ ${result.name} (${result.country}) rev=${formatRevenue(result.revenue)}\n`);
+    } else {
+      notFound++;
+      const emptyRow = [...row, ...opts.fields.map(() => '')];
+      outputLines.push(emptyRow.map(v => escapeCSV(v, delimiter)).join(delimiter));
+      process.stderr.write('✗ not found\n');
+    }
+
+    await sleep(RATE_LIMIT_MS);
+  }
+
+  const output = outputLines.join('\n') + '\n';
+
+  if (opts.output) {
+    fs.writeFileSync(opts.output, output, 'utf-8');
+    process.stderr.write(`\nDone! ${enriched}/${total} enriched, ${notFound} not found.\n`);
+    process.stderr.write(`Output: ${opts.output}\n`);
+  } else {
+    process.stdout.write(output);
+    process.stderr.write(`\n${enriched}/${total} enriched, ${notFound} not found.\n`);
+  }
+
+  process.stderr.write(`\n--- Score API by SCALA AI ---\n`);
+  process.stderr.write(`272M+ companies | 265 countries | Free tier available\n`);
+  process.stderr.write(`https://score.get-scala.com/api\n\n`);
+}
+
+main().catch(e => { console.error(`Fatal: ${e.message}`); process.exit(1); });

package/package.json

@@ -0,0 +1,36 @@
+{
+  "name": "enrich-companies",
+  "version": "1.0.0",
+  "description": "Enrich a CSV of companies with revenue, credit score, employees, and financial data from 272M+ companies. Free tier: 50 lookups/month.",
+  "main": "index.js",
+  "bin": {
+    "enrich-companies": "./index.js"
+  },
+  "keywords": [
+    "csv",
+    "enrichment",
+    "company data",
+    "business intelligence",
+    "lead enrichment",
+    "crm",
+    "revenue data",
+    "credit score",
+    "dun and bradstreet alternative",
+    "zoominfo alternative",
+    "clearbit alternative",
+    "data enrichment",
+    "b2b data",
+    "company lookup",
+    "sales intelligence"
+  ],
+  "author": "SCALA AI <ale@get-scala.com>",
+  "license": "MIT",
+  "homepage": "https://score.get-scala.com/api",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/Alessandro114/enrich-csv"
+  },
+  "engines": {
+    "node": ">=16"
+  }
+}