feat: 5 fixes — dead site scoring, Kit Digital precision, social icons, GMB detection, social/GMB weighting

1. scorer: dead sites capped at 5 (was scoring HOT from SSL/CMS signals)
2. Kit Digital: require explicit kit-digital/agente-digitalizador signals;
   generic EU logo patterns (fondos-europeos, logo-ue, cofinanciado) removed.
   Gemini kit_digital_confirmed now overwrites heuristic in DB.
3. Browse table: social links replaced with compact coloured icon badges
   (fb/ig/in/x/tt/yt) linked to the profile URLs
4. site_analyzer: added has_gmb / gmb_url detection (Maps embed, Place links,
   LocalBusiness schema); fed to Gemini prompt
5. scorer: +5 no-social, +3 reachable contact; Gemini prompt includes GMB and
   social media management as sellable services; modal shows GMB/social status

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-04-14 07:21:02 +02:00
parent 793aea8a5f
commit dad910b6b0
6 changed files with 159 additions and 63 deletions

View File

@@ -1,15 +1,16 @@
import os
import json
import aiosqlite
from app.db import SQLITE_PATH
KNOWN_CMS = {"wordpress", "joomla", "drupal", "wix", "squarespace", "shopify", "prestashop", "magento", "typo3", "opencart"}
TARGET_COUNTRIES = set(os.getenv("TARGET_COUNTRIES", "ES,GB,DE,FR").split(","))
TARGET_COUNTRIES = set(os.getenv("TARGET_COUNTRIES", "ES,GB,DE,FR,RO,PT,AD,IT").split(","))
LOCAL_BIZ_KEYWORDS = {
"restaurant", "cafe", "shop", "store", "salon", "plumber", "electrician",
"dentist", "clinic", "garage", "hotel", "bakery", "bar", "gym", "spa",
"fontanero", "electricista", "dentista", "clínica", "taller", "hotel",
"panadería", "peluquería", "tienda",
"fontanero", "electricista", "dentista", "clínica", "taller",
"panadería", "peluquería", "tienda", "abogado", "gestor", "inmobili",
}
@@ -21,29 +22,53 @@ def local_biz_keywords(title: str | None) -> bool:
def score(domain_row: dict) -> int:
s = 0
if domain_row.get("is_live"):
s += 20
# Dead sites are unreachable — cap at 5 regardless of other signals
if not domain_row.get("is_live") and not domain_row.get("reachable"):
return 5
s = 20 # Live site base
ssl_days = domain_row.get("ssl_expiry_days")
if ssl_days is not None and ssl_days < 30:
s += 15
s += 15 # SSL expiring / expired — urgent upsell
if not domain_row.get("ssl_valid"):
s += 15
s += 15 # No valid SSL
cms = (domain_row.get("cms") or "").lower()
if cms in KNOWN_CMS:
s += 15
s += 15 # Known CMS — maintenance / migration opportunity
if not domain_row.get("has_mx"):
s += 10
s += 10 # No email = needs professional email setup
if domain_row.get("ip_country") in TARGET_COUNTRIES:
s += 10
server = (domain_row.get("server") or "").lower()
if "shared" in server:
s += 10
s += 5
if local_biz_keywords(domain_row.get("page_title")):
s += 5
# Kit Digital: proven buyer of IT services
# Kit Digital: proven buyer of IT services (Gemini-confirmed takes precedence)
if domain_row.get("kit_digital"):
s += 20
# Social media / GMB presence signals
try:
ci = json.loads(domain_row.get("contact_info") or "{}")
has_social = bool(ci.get("social"))
has_contact = bool(ci.get("emails") or ci.get("phones") or ci.get("whatsapp"))
except Exception:
has_social = False
has_contact = False
if not has_social:
s += 5 # No social = opportunity to build presence
if has_contact:
s += 3 # Reachable lead — we can actually pitch them
return min(s, 100)