Build a Tech Stack Lead Enrichment Pipeline in Under 50 Lines of Python

#webdev #api #sales #python

Knowing a prospect runs Shopify vs Magento changes your entire pitch. Here's how to enrich your entire lead list with tech stack data in minutes.

Why tech stack data matters for sales

Before you send that outreach email, you should know:

Is this company a Shopify store or a custom-built platform? (Different pitch entirely)
Are they already using HubSpot, or do they need CRM tooling too?
Running WordPress or Webflow? That changes what integrations you can offer
Is their site on AWS, Vercel, or Heroku? Signals engineering maturity

This data used to require a Wappalyzer enterprise license ($250+/mo) or manual inspection for each lead. Now you can enrich an entire lead list in one batch API call.

The setup: TechStackDetect API

TechStackDetect is a REST API that analyzes any public website and returns the full technology stack:

5,000+ technology signatures across 48 categories
Batch mode — analyze up to 50 URLs in one request
Confidence scores — know when a detection is definitive vs likely
Free tier — 100 requests/day, no credit card required

Step 1: Single URL test

import requests

API_KEY = "YOUR_RAPIDAPI_KEY"
HEADERS = {
    "X-RapidAPI-Key": API_KEY,
    "X-RapidAPI-Host": "techstackdetect1.p.rapidapi.com",
}

def detect(url: str) -> list[dict]:
    r = requests.post(
        "https://techstackdetect1.p.rapidapi.com/detect",
        json={"url": url},
        headers=HEADERS,
        timeout=30,
    )
    r.raise_for_status()
    return r.json().get("technologies", [])

techs = detect("https://woocommerce.com")
for t in techs[:5]:
    print(f"{t['name']} ({t['category']}) {t['confidence']:.0%}")

Output:

WordPress (cms) 95%
WooCommerce (ecommerce) 95%
Nginx (server) 95%
jQuery (javascript) 95%
Yoast SEO Premium (seo) 75%

Step 2: Batch enrichment — 50 URLs at once

def detect_batch(urls: list[str]) -> list[dict]:
    r = requests.post(
        "https://techstackdetect1.p.rapidapi.com/batch",
        json={"urls": urls},
        headers=HEADERS,
        timeout=60,
    )
    r.raise_for_status()
    return r.json()["results"]

lead_urls = [
    "https://woocommerce.com",
    "https://shopify.com",
    "https://bigcommerce.com",
]

results = detect_batch(lead_urls)
for r in results:
    ecom = [t["name"] for t in r["technologies"] if t["category"] == "ecommerce"]
    print(f"{r['url']}: {ecom[0] if ecom else 'Unknown'}")

Step 3: Full CSV enrichment pipeline

import csv, time

def enrich_leads(input_csv: str, output_csv: str):
    with open(input_csv) as f:
        rows = list(csv.DictReader(f))

    urls = [row["website"] for row in rows]
    results_map = {}

    for i in range(0, len(urls), 50):
        chunk = urls[i:i + 50]
        results = detect_batch(chunk)
        for r in results:
            results_map[r["url"]] = r.get("technologies", [])
        if i + 50 < len(urls):
            time.sleep(1)

    fieldnames = list(rows[0].keys()) + [
        "detected_cms", "detected_hosting", "detected_analytics",
        "detected_ecommerce", "tech_count"
    ]

    with open(output_csv, "w", newline="") as f:
        writer = csv.DictWriter(f, fieldnames=fieldnames)
        writer.writeheader()
        for row in rows:
            techs = results_map.get(row["website"], [])
            by_cat = {}
            for t in techs:
                by_cat.setdefault(t["category"], t["name"])
            row.update({
                "detected_cms": by_cat.get("cms", ""),
                "detected_hosting": by_cat.get("hosting", ""),
                "detected_analytics": by_cat.get("analytics", ""),
                "detected_ecommerce": by_cat.get("ecommerce", ""),
                "tech_count": len(techs),
            })
            writer.writerow(row)

    print(f"Enriched {len(rows)} leads → {output_csv}")

enrich_leads("leads.csv", "leads_enriched.csv")

Before:

name,company,website
Acme Corp,acme.com,https://acme.com

After:

name,company,website,detected_cms,detected_hosting,detected_analytics,detected_ecommerce,tech_count
Acme Corp,acme.com,https://acme.com,WordPress,WP Engine,Google Analytics,,8

Step 4: Filter by confidence

def get_high_confidence(url: str, min_confidence: float = 0.90) -> list[str]:
    return [
        t["name"] for t in detect(url)
        if t["confidence"] >= min_confidence
    ]

print(get_high_confidence("https://stripe.com"))
# ['AWS', 'Nginx', 'HSTS', 'Next.js']

Score thresholds: 0.95+ definitive · 0.90 strong · 0.75 probable. Use 0.85+ for lead scoring.

Step 5: Segment by platform for personalized outreach

def segment_leads(results):
    segments = {"shopify": [], "woocommerce": [], "magento": [], "custom": []}
    for r in results:
        ecom = next(
            (t["name"].lower() for t in r["technologies"] if t["category"] == "ecommerce"),
            None
        )
        key = ecom if ecom in segments else "custom"
        segments[key].append(r["url"])
    return segments