Malin/DomGod
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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:
Malin
2026-04-14 07:21:02 +02:00
parent 793aea8a5f
commit dad910b6b0
6 changed files with 159 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
app/enricher.py
View File

@@ -62,44 +62,34 @@ def detect_cms(html: str, headers: dict) -> Optional[str]:
# ── Kit Digital detection ────────────────────────────────────────────────────
KIT_IMG_PATS = [
"digitalizadores", "kit-digital", "kitdigital", "kit_digital",
"fondos-europeos", "fondos_europeos", "nextgeneration", "next-generation",
"prtr", "plan-recuperacion", "planderecuperacion",
"acelerapyme", "logo-ue", "recovery-eu", "cofinanciado",
]
KIT_TEXT_PATS = [
"kit digital", "agente digitalizador", "agentes digitalizadores",
"fondos europeos", "next generation eu", "nextgenerationeu",
"plan de recuperación", "plan de recuperacion",
"plan de digitalización", "digitalización pymes",
"prtr", "financiado por la unión europea",
"red.es/kit-digital", "acelerapyme.es",
]
KIT_LINK_PATS = ["acelerapyme", "red.es", "kit-digital", "kitdigital"]
KIT_STRONG_IMG = ["kit-digital", "kitdigital", "kit_digital", "agente-digitalizador", "agente_digitalizador"]
KIT_STRONG_TEXT = ["kit digital", "agente digitalizador", "agentes digitalizadores"]
KIT_STRONG_LINK = ["acelerapyme.es", "red.es/kit-digital", "kit-digital.red.es"]
def detect_kit_digital(soup, html: str) -> tuple[bool, list]:
signals = []
hl = html.lower()
vl = soup.get_text().lower()
for img in soup.find_all("img"):
combined = ((img.get("src") or "") + (img.get("alt") or "") + (img.get("srcset") or "")).lower()
for p in KIT_IMG_PATS:
for p in KIT_STRONG_IMG:
if p in combined:
signals.append(f"img:{p}")
break
for p in KIT_TEXT_PATS:
if p in hl:
for p in KIT_STRONG_TEXT:
if p in vl:
signals.append(f"text:{p}")
for a in soup.find_all("a", href=True):
href = a["href"].lower()
if any(p in href for p in KIT_LINK_PATS):
signals.append(f"link:{href[:60]}")
for p in KIT_STRONG_LINK:
if p in href:
signals.append(f"link:{href[:60]}")
break
signals = list(dict.fromkeys(signals))[:15]
signals = list(dict.fromkeys(signals))[:10]
return len(signals) > 0, signals