Keyword Clusters → Focus Group Validation

import os, requests, csv, io, time
from collections import defaultdict

SR, MV = os.environ["SEMRUSH_API_KEY"], os.environ["MAVERA_API_KEY"]
MB = "https://app.mavera.io/api/v1"
MH = {"Authorization": f"Bearer {MV}", "Content-Type": "application/json"}
SEED = "content marketing automation"

resp = requests.get("https://api.semrush.com/", params={
    "type": "phrase_related", "key": SR, "phrase": SEED,
    "database": "us", "display_limit": 100, "export_columns": "Ph,Nq,Kd,Co",
})
reader = csv.reader(io.StringIO(resp.text), delimiter=";")
next(reader)
kws = [{"keyword": r[0], "volume": int(r[1] or 0), "difficulty": int(r[2] or 0)}
       for r in reader if len(r) >= 4]

intent_map = {"how": "info", "best": "commercial", "tool": "transactional", "software": "transactional"}
stops = {"how", "to", "what", "is", "the", "a", "for", "and", "best", "top"}
clusters = defaultdict(list)
for kw in kws:
    words = kw["keyword"].lower().split()
    intent = next((intent_map[w] for w in words if w in intent_map), "info")
    topic = next((w for w in words if w not in stops), words[0])
    clusters[f"{intent}:{topic}"].append(kw)

top = sorted(clusters.items(), key=lambda c: sum(k["volume"] for k in c[1]), reverse=True)[:4]

pids = []
for key, group in top:
    intent, topic = key.split(":", 1)
    p = requests.post(f"{MB}/personas", headers=MH, json={
        "name": f"Reader: {intent} — {topic}",
        "description": f"Searches for {intent} content about '{topic}'. "
                       f"{len(group)} kws, {sum(k['volume'] for k in group)} vol.",
    }).json()
    pids.append(p["id"])
    time.sleep(0.3)

concepts = [f"{k.split(':')[0]} about '{k.split(':')[1]}': "
            + ", ".join(kw["keyword"] for kw in sorted(v, key=lambda x: -x["volume"])[:5])
            for k, v in top]

fg = requests.post(f"{MB}/focus-groups", headers=MH, json={
    "name": f"Cluster Validation: {SEED}", "persona_ids": pids,
    "questions": [
        "Which concept would you click first?\n" + "\n".join(f"{i+1}. {c}" for i, c in enumerate(concepts)),
        "What question must a blog post answer for you to read it fully?",
        "Comprehensive guide (3000+ words) or quick checklist? Why?",
    ], "responses_per_persona": 2,
}).json()

for _ in range(24):
    time.sleep(5)
    data = requests.get(f"{MB}/focus-groups/{fg['id']}", headers=MH).json()
    if data.get("status") == "completed": break
for r in data.get("responses", [])[:8]:
    print(f"[{r.get('persona_id','?')}] {r.get('answer','')[:250]}\n")

const SR = process.env.SEMRUSH_API_KEY, MV = process.env.MAVERA_API_KEY;
const MB = "https://app.mavera.io/api/v1";
const MH = { Authorization: `Bearer ${MV}`, "Content-Type": "application/json" };
const SEED = "content marketing automation";

const params = new URLSearchParams({
  type: "phrase_related", key: SR, phrase: SEED,
  database: "us", display_limit: "100", export_columns: "Ph,Nq,Kd,Co",
});
const text = await fetch(`https://api.semrush.com/?${params}`).then((r) => r.text());
const kws = text.trim().split("\n").slice(1).map((line) => {
  const c = line.split(";");
  return c.length >= 4 ? { keyword: c[0], volume: parseInt(c[1]) || 0, difficulty: parseInt(c[2]) || 0 } : null;
}).filter(Boolean);

const iMap = { how: "info", best: "commercial", tool: "transactional", software: "transactional" };
const stops = new Set(["how","to","what","is","the","a","for","and","best","top"]);
const clusters = {};
for (const kw of kws) {
  const w = kw.keyword.toLowerCase().split(" ");
  const intent = w.find((x) => iMap[x]) ? iMap[w.find((x) => iMap[x])] : "info";
  const topic = w.find((x) => !stops.has(x)) || w[0];
  (clusters[`${intent}:${topic}`] ??= []).push(kw);
}
const top = Object.entries(clusters)
  .map(([k, g]) => ({ k, g, vol: g.reduce((s, x) => s + x.volume, 0) }))
  .sort((a, b) => b.vol - a.vol).slice(0, 4);

const pids = [];
for (const { k, g, vol } of top) {
  const [intent, topic] = k.split(":");
  const p = await fetch(`${MB}/personas`, { method: "POST", headers: MH,
    body: JSON.stringify({ name: `Reader: ${intent} — ${topic}`,
      description: `${intent} searcher, '${topic}'. ${g.length} kws, ${vol} vol.` }),
  }).then((r) => r.json());
  pids.push(p.id);
  await new Promise((r) => setTimeout(r, 300));
}

const concepts = top.map(({ k, g }) => {
  const [i, t] = k.split(":");
  return `${i} about '${t}': ${g.sort((a, b) => b.volume - a.volume).slice(0, 5).map((x) => x.keyword).join(", ")}`;
});
const fg = await fetch(`${MB}/focus-groups`, { method: "POST", headers: MH,
  body: JSON.stringify({
    name: `Cluster: ${SEED}`, persona_ids: pids,
    questions: ["Which first?\n" + concepts.map((c, i) => `${i+1}. ${c}`).join("\n"),
      "What question must a post answer for you to finish it?",
      "Long guide or quick checklist? Why?"],
    responses_per_persona: 2,
  }),
}).then((r) => r.json());

let data;
for (let i = 0; i < 24; i++) {
  await new Promise((r) => setTimeout(r, 5000));
  data = await fetch(`${MB}/focus-groups/${fg.id}`, { headers: MH }).then((r) => r.json());
  if (data.status === "completed") break;
}
for (const r of (data.responses || []).slice(0, 8))
  console.log(`[${r.persona_id}] ${(r.answer || "").slice(0, 250)}\n`);