4ventures-client-portal/scripts/gap_report_connections.py

#!/usr/bin/env python3
"""Exact gap report: visible assets vs tenant matches + name candidates."""
from __future__ import annotations

import json
import re
import urllib.error
import urllib.parse
import urllib.request
from collections import defaultdict
from datetime import datetime, timezone, timedelta
from pathlib import Path

ROOT = Path(__file__).resolve().parents[1]
META = "https://graph.facebook.com/v21.0"


def load_env() -> dict[str, str]:
    vals: dict[str, str] = {}
    for line in (ROOT / ".env.local").read_text(encoding="utf-8").splitlines():
        if not line.strip() or line.strip().startswith("#") or "=" not in line:
            continue
        k, v = line.split("=", 1)
        vals[k.strip()] = v.strip().strip('"').strip("'")
    return vals


ENV = load_env()
BASE = ENV["NEXT_PUBLIC_SUPABASE_URL"].rstrip("/")
KEY = ENV["SUPABASE_SERVICE_ROLE_KEY"]
SH = {"apikey": KEY, "Authorization": f"Bearer {KEY}"}


def sb(path: str):
    req = urllib.request.Request(BASE + path, headers=SH)
    with urllib.request.urlopen(req, timeout=90) as r:
        return json.loads(r.read().decode())


def norm(s: str) -> str:
    s = s.lower()
    for a, b in (
        ("á", "a"),
        ("é", "e"),
        ("í", "i"),
        ("ó", "o"),
        ("ú", "u"),
        ("ñ", "n"),
    ):
        s = s.replace(a, b)
    return re.sub(r"[^a-z0-9]+", " ", s).strip()


def score_name(tenant_name: str, tenant_slug: str, account_name: str) -> int:
    t = norm(tenant_name)
    s = norm(tenant_slug.replace("-", " "))
    a = norm(account_name)
    if not a:
        return 0
    if a == t or a == s:
        return 100
    if t and (t in a or a in t):
        return 85
    if s and (s in a or a in s):
        return 80
    tt = {x for x in t.split() if len(x) > 2}
    aa = {x for x in a.split() if len(x) > 2}
    if not tt or not aa:
        return 0
    hit = len(tt & aa) / len(tt)
    if hit >= 0.8:
        return 70
    if hit >= 0.5:
        return 55
    return int(hit * 50)


def top_candidates(tenants, account_name, n=3):
    scored = []
    for t in tenants:
        sc = score_name(t["name"], t["slug"], account_name)
        if sc > 0:
            scored.append((sc, t["name"]))
    scored.sort(key=lambda x: -x[0])
    return scored[:n]


def meta_paginate(token: str, path: str):
    out = []
    url = f"{META}/{path}"
    sep = "&" if "?" in path else "?"
    url = url + sep + "access_token=" + urllib.parse.quote(token)
    while url:
        req = urllib.request.Request(url)
        with urllib.request.urlopen(req, timeout=90) as r:
            j = json.loads(r.read().decode())
        out.extend(j.get("data") or [])
        url = (j.get("paging") or {}).get("next")
    return out


def google_refresh(refresh: str) -> str:
    body = urllib.parse.urlencode(
        {
            "refresh_token": refresh,
            "client_id": ENV["GOOGLE_OAUTH_CLIENT_ID"],
            "client_secret": ENV["GOOGLE_OAUTH_CLIENT_SECRET"],
            "grant_type": "refresh_token",
        }
    ).encode()
    req = urllib.request.Request(
        "https://oauth2.googleapis.com/token",
        data=body,
        headers={"Content-Type": "application/x-www-form-urlencoded"},
    )
    with urllib.request.urlopen(req, timeout=60) as r:
        return json.loads(r.read().decode())["access_token"]


def main() -> int:
    tenants = sb("/rest/v1/tenants?select=id,name,slug&order=name.asc")
    integs = sb(
        "/rest/v1/integrations?provider=in.(ga4,search_console,google_drive,google_ads,meta_ads,facebook,instagram)"
        "&select=tenant_id,provider,status,external_account_id,meta,error_message"
    )
    by = defaultdict(dict)
    for i in integs:
        by[i["tenant_id"]][i["provider"]] = i

    grow = sb(
        "/rest/v1/agency_oauth?provider=eq.google_drive&select=access_token,refresh_token,account_email"
    )[0]
    mrow = sb(
        "/rest/v1/agency_oauth?provider=eq.meta_ads&select=access_token,account_email,scopes"
    )[0]
    gtoken = google_refresh(grow["refresh_token"])
    mtoken = mrow["access_token"]

    print("=== TOKENS ===")
    print("Google:", grow.get("account_email"))
    print("Meta:", mrow.get("account_email"))

    # Meta inventory
    ads = []
    for row in meta_paginate(
        mtoken, "me/adaccounts?fields=id,account_id,name&limit=200"
    ):
        aid = row.get("account_id") or row["id"].replace("act_", "")
        ads.append({"id": f"act_{aid}", "name": row.get("name") or aid})
    pages = []
    igs = []
    for page in meta_paginate(
        mtoken,
        "me/accounts?fields=id,name,instagram_business_account{id,username,name}&limit=100",
    ):
        pages.append({"id": page["id"], "name": page.get("name") or page["id"]})
        ig = page.get("instagram_business_account") or {}
        if ig.get("id"):
            igs.append(
                {
                    "id": ig["id"],
                    "name": f"@{ig['username']}"
                    if ig.get("username")
                    else (ig.get("name") or page.get("name") or ig["id"]),
                    "page": page.get("name"),
                }
            )

    print(f"\n=== META VISIBLE === ads={len(ads)} pages={len(pages)} ig={len(igs)}")
    print("Ad accounts:")
    for a in ads:
        cands = top_candidates(tenants, a["name"])
        linked = next(
            (
                t["name"]
                for t in tenants
                if (by[t["id"]].get("meta_ads") or {}).get("external_account_id")
                == a["id"]
            ),
            None,
        )
        print(
            f"  {a['name']!r} ({a['id']}) → linked={linked or 'NO'} best={cands}"
        )
    print("Pages:")
    for a in pages:
        cands = top_candidates(tenants, a["name"])
        linked = next(
            (
                t["name"]
                for t in tenants
                if (by[t["id"]].get("facebook") or {}).get("external_account_id")
                == a["id"]
            ),
            None,
        )
        print(
            f"  {a['name']!r} ({a['id']}) → linked={linked or 'NO'} best={cands}"
        )
    print("Instagram:")
    for a in igs:
        cands = top_candidates(tenants, a["name"]) + top_candidates(
            tenants, a.get("page") or ""
        )
        # dedupe keep best
        seen = {}
        for sc, name in cands:
            seen[name] = max(sc, seen.get(name, 0))
        cands = sorted(((v, k) for k, v in seen.items()), reverse=True)[:3]
        linked = next(
            (
                t["name"]
                for t in tenants
                if (by[t["id"]].get("instagram") or {}).get("external_account_id")
                == a["id"]
            ),
            None,
        )
        print(
            f"  {a['name']!r} page={a.get('page')!r} ({a['id']}) → linked={linked or 'NO'} best={cands}"
        )

    # GA4 / GSC inventory
    req = urllib.request.Request(
        "https://analyticsadmin.googleapis.com/v1beta/accountSummaries",
        headers={"Authorization": f"Bearer {gtoken}"},
    )
    with urllib.request.urlopen(req, timeout=90) as r:
        summaries = json.loads(r.read().decode())
    ga4 = []
    for acc in summaries.get("accountSummaries") or []:
        for p in acc.get("propertySummaries") or []:
            if p.get("property"):
                ga4.append(
                    {
                        "id": p["property"],
                        "name": p.get("displayName") or p["property"],
                        "account": acc.get("displayName"),
                    }
                )

    req = urllib.request.Request(
        "https://www.googleapis.com/webmasters/v3/sites",
        headers={"Authorization": f"Bearer {gtoken}"},
    )
    with urllib.request.urlopen(req, timeout=90) as r:
        sites_j = json.loads(r.read().decode())
    gsc = [
        {"id": s["siteUrl"], "name": s["siteUrl"]}
        for s in (sites_j.get("siteEntry") or [])
        if s.get("siteUrl")
    ]

    print(f"\n=== GOOGLE VISIBLE === ga4={len(ga4)} gsc={len(gsc)}")

    # Test Data API on first property
    if ga4:
        prop = ga4[0]["id"].replace("properties/", "")
        end = (datetime.now(timezone.utc) - timedelta(days=1)).date()
        start = end - timedelta(days=2)
        body = json.dumps(
            {
                "dateRanges": [{"startDate": str(start), "endDate": str(end)}],
                "dimensions": [{"name": "date"}],
                "metrics": [{"name": "sessions"}],
            }
        ).encode()
        req = urllib.request.Request(
            f"https://analyticsdata.googleapis.com/v1beta/properties/{prop}:runReport",
            data=body,
            headers={
                "Authorization": f"Bearer {gtoken}",
                "Content-Type": "application/json",
            },
            method="POST",
        )
        try:
            with urllib.request.urlopen(req, timeout=60) as r:
                print("Data API test: OK on", ga4[0]["name"], prop)
        except urllib.error.HTTPError as e:
            print("Data API test: FAIL", e.read().decode()[:250])

    # Unmatched GA4 with best candidates (only those not linked)
    linked_ga4_ids = {
        (by[t["id"]].get("ga4") or {}).get("external_account_id")
        for t in tenants
    }
    linked_ga4_props = set()
    for t in tenants:
        meta = (by[t["id"]].get("ga4") or {}).get("meta") or {}
        if meta.get("property_id"):
            linked_ga4_props.add(meta["property_id"])

    print("\n=== GA4 sin ficha clara (score<50 o no enlazado) — top candidatos ===")
    for a in ga4:
        linked = next(
            (
                t["name"]
                for t in tenants
                if (by[t["id"]].get("ga4") or {}).get("meta", {}).get("property_id")
                == a["id"]
                or (by[t["id"]].get("ga4") or {}).get("external_account_id")
                in (a["id"], a["name"])
            ),
            None,
        )
        cands = top_candidates(tenants, a["name"])
        best = cands[0][0] if cands else 0
        if linked and best >= 50:
            continue
        if linked:
            continue
        print(f"  GA4 {a['name']!r} ({a['id']}) acct={a.get('account')!r} best={cands}")

    print("\n=== GSC sin ficha clara ===")
    for a in gsc:
        linked = next(
            (
                t["name"]
                for t in tenants
                if (by[t["id"]].get("search_console") or {}).get("external_account_id")
                == a["id"]
            ),
            None,
        )
        if linked:
            continue
        cands = top_candidates(tenants, a["name"])
        # also try domain without sc-domain
        bare = a["name"].replace("sc-domain:", "").replace("https://", "").replace("http://", "").strip("/")
        cands2 = top_candidates(tenants, bare)
        merged = {}
        for sc, name in cands + cands2:
            merged[name] = max(sc, merged.get(name, 0))
        cands = sorted(((v, k) for k, v in merged.items()), reverse=True)[:3]
        print(f"  GSC {a['name']!r} best={cands}")

    # Per-tenant gaps with why
    print("\n=== POR CLIENTE: qué falta y por qué ===")
    providers = [
        "google_ads",
        "meta_ads",
        "ga4",
        "search_console",
        "google_drive",
        "facebook",
        "instagram",
    ]

    def ok(i):
        return bool(i and i.get("status") == "connected" and i.get("external_account_id"))

    for t in tenants:
        m = by[t["id"]]
        gaps = []
        for p in providers:
            if ok(m.get(p)):
                continue
            if p == "meta_ads":
                cands = [(score_name(t["name"], t["slug"], a["name"]), a["name"], a["id"]) for a in ads]
                cands = [c for c in sorted(cands, reverse=True) if c[0] > 0][:2]
                if not ads:
                    gaps.append("meta_ads: token no ve ad accounts")
                elif not cands:
                    gaps.append("meta_ads: no hay ad account cuyo nombre se parezca (¿no está en las 9 visibles?)")
                else:
                    gaps.append(f"meta_ads: no auto-match; candidatos {cands}")
            elif p == "facebook":
                cands = [(score_name(t["name"], t["slug"], a["name"]), a["name"], a["id"]) for a in pages]
                cands = [c for c in sorted(cands, reverse=True) if c[0] > 0][:2]
                if not cands:
                    gaps.append("facebook: ninguna Page visible se parece al nombre")
                else:
                    gaps.append(f"facebook: no auto-match; candidatos {cands}")
            elif p == "instagram":
                cands = []
                for a in igs:
                    sc = max(
                        score_name(t["name"], t["slug"], a["name"]),
                        score_name(t["name"], t["slug"], a.get("page") or ""),
                    )
                    if sc > 0:
                        cands.append((sc, a["name"], a.get("page"), a["id"]))
                cands = sorted(cands, reverse=True)[:2]
                if not cands:
                    gaps.append("instagram: ningún @ / page visible se parece")
                else:
                    gaps.append(f"instagram: no auto-match; candidatos {cands}")
            elif p == "ga4":
                cands = [(score_name(t["name"], t["slug"], a["name"]), a["name"], a["id"]) for a in ga4]
                cands = [c for c in sorted(cands, reverse=True) if c[0] > 0][:2]
                if not cands:
                    gaps.append("ga4: ninguna propiedad visible se parece al nombre")
                else:
                    gaps.append(f"ga4: no auto-match (umbral 50); candidatos {cands}")
            elif p == "search_console":
                cands = []
                for a in gsc:
                    bare = a["name"].replace("sc-domain:", "").replace("https://", "").replace("http://", "").strip("/")
                    sc = max(
                        score_name(t["name"], t["slug"], a["name"]),
                        score_name(t["name"], t["slug"], bare),
                    )
                    if sc > 0:
                        cands.append((sc, a["name"]))
                cands = sorted(cands, reverse=True)[:2]
                if not cands:
                    gaps.append("gsc: ningún site visible se parece")
                else:
                    gaps.append(f"gsc: no auto-match (umbral 40); candidatos {cands}")
            elif p == "google_drive":
                gaps.append("drive: sin carpeta auto-matched (revisar nombre carpeta Drive)")
            elif p == "google_ads":
                gaps.append("google_ads: sin cuenta enlazada (MCC / nombre)")
        if gaps:
            print(f"\n{t['name']}:")
            for g in gaps:
                print(f"  - {g}")
        else:
            print(f"\n{t['name']}: COMPLETO (todos los canales con ID)")

    # BPS GSC permission probe
    bps = next(t for t in tenants if t["name"] == "BPS")
    gsc_id = (by[bps["id"]].get("search_console") or {}).get("external_account_id")
    if gsc_id:
        end = (datetime.now(timezone.utc) - timedelta(days=1)).date()
        start = end - timedelta(days=3)
        body = json.dumps(
            {"startDate": str(start), "endDate": str(end), "dimensions": ["date"]}
        ).encode()
        req = urllib.request.Request(
            f"https://www.googleapis.com/webmasters/v3/sites/{urllib.parse.quote(gsc_id, safe='')}/searchAnalytics/query",
            data=body,
            headers={
                "Authorization": f"Bearer {gtoken}",
                "Content-Type": "application/json",
            },
            method="POST",
        )
        try:
            with urllib.request.urlopen(req, timeout=60) as r:
                print("\nBPS GSC probe: OK")
        except urllib.error.HTTPError as e:
            print("\nBPS GSC probe: FAIL", e.read().decode()[:220])

    return 0


if __name__ == "__main__":
    raise SystemExit(main())