diff --git a/app/beauty_ai.py b/app/beauty_ai.py
index 01b2eb0..9c1839e 100644
--- a/app/beauty_ai.py
+++ b/app/beauty_ai.py
@@ -19,6 +19,18 @@ REPLICATE_TOKEN = os.getenv("REPLICATE_API_TOKEN", "r8_7I7Feai78f9PzMOs20y5GVFKi
REPLICATE_MODEL = "https://api.replicate.com/v1/models/google/gemini-3-pro/predictions"
AI_CONCURRENCY = int(os.getenv("AI_CONCURRENCY", "3"))
+# Contact extraction regexes (same patterns as site_analyzer)
+_EMAIL_RE = re.compile(r"[a-zA-Z0-9._%+\-]+@[a-zA-Z0-9.\-]+\.[a-zA-Z]{2,}")
+_PHONE_RE = re.compile(r"(?:\+\d{1,3}[\s\-]?)?(?:6|7|8|9)\d{2}[\s\-]?\d{3}[\s\-]?\d{3}")
+
+# Pages that often contain company registration info (CIF/NIF, registered address,
+# legal email) — not fetched by site_analyzer, but rich sources for B2B contact data
+_LEGAL_PATHS = [
+ "/aviso-legal", "/aviso_legal", "/legal",
+ "/politica-de-privacidad", "/politica_privacidad", "/privacidad",
+ "/quienes-somos", "/quienes_somos", "/nosotros",
+]
+
_ai_sem: Optional[asyncio.Semaphore] = None
def _sem() -> asyncio.Semaphore:
@@ -182,91 +194,214 @@ async def _ddg_search(query: str) -> str:
return ""
+# ── Legal / about page scraper ────────────────────────────────────────────────
+
+async def _scrape_legal_pages(domain: str) -> dict:
+ """Fetch legal and about pages not covered by site_analyzer.
+
+ Spanish Aviso Legal pages legally must contain: company name (razón social),
+ CIF/NIF, registered address, and a contact email — making them the richest
+ source of verified B2B contact data.
+
+ Returns:
+ emails: all unique emails found across all pages
+ phones: all unique phones found across all pages
+ legal_snippet: first 800 chars of the aviso legal page (company registration
+ info: razón social, CIF, domicilio, etc.)
+ """
+ result: dict = {"emails": [], "phones": [], "legal_snippet": ""}
+
+ async def _fetch(path: str) -> tuple[str, str | None]:
+ try:
+ async with httpx.AsyncClient(
+ timeout=8, follow_redirects=True, verify=False,
+ headers={"User-Agent": "Mozilla/5.0"},
+ ) as c:
+ r = await c.get(f"https://{domain}{path}")
+ if r.status_code == 200:
+ return path, r.text
+ except Exception:
+ pass
+ return path, None
+
+ pages = await asyncio.gather(*[_fetch(p) for p in _LEGAL_PATHS])
+
+ for path, html in pages:
+ if not html:
+ continue
+ try:
+ soup = BeautifulSoup(html, "html.parser")
+ # Extract from anchor tags
+ for a in soup.find_all("a", href=True):
+ href = a["href"]
+ if href.startswith("mailto:"):
+ em = href[7:].split("?")[0].strip().lower()
+ if em and em not in result["emails"]:
+ result["emails"].append(em)
+ elif href.startswith("tel:"):
+ ph = re.sub(r"[^\d+]", "", href[4:])
+ if ph and ph not in result["phones"]:
+ result["phones"].append(ph)
+ # Regex scan full HTML for emails
+ for em in _EMAIL_RE.findall(html[:60000]):
+ em = em.lower()
+ if em not in result["emails"] and not any(
+ em.endswith(x) for x in (".png", ".jpg", ".css", ".js", ".svg")
+ ):
+ result["emails"].append(em)
+ # Regex scan visible text for phones
+ visible = soup.get_text(separator=" ", strip=True)
+ for ph in _PHONE_RE.findall(visible):
+ ph_c = re.sub(r"[\s\-]", "", ph)
+ if ph_c and ph_c not in result["phones"]:
+ result["phones"].append(ph_c)
+ # Capture legal snippet from the first legal page that resolves
+ if not result["legal_snippet"] and any(
+ k in path for k in ("aviso", "legal", "privacidad")
+ ):
+ result["legal_snippet"] = " ".join(visible.split()[:150])
+ except Exception:
+ pass
+
+ result["emails"] = list(dict.fromkeys(result["emails"]))[:8]
+ result["phones"] = list(dict.fromkeys(result["phones"]))[:6]
+ return result
+
+
# ── Prompt builder ─────────────────────────────────────────────────────────────
def _build_beauty_prompt(a: dict, detected_brands: list, dist_matches: list,
- search_results: str = "") -> str:
- contacts_block = []
- if a.get("emails"): contacts_block.append(f" Emails: {', '.join(a['emails'][:3])}")
- if a.get("phones"): contacts_block.append(f" Phones: {', '.join(a['phones'][:3])}")
- if a.get("social_links"): contacts_block.append(f" Social: {', '.join(a['social_links'][:4])}")
- contacts_str = "\n".join(contacts_block) or " Not found"
+ search_results: str = "",
+ extra_contacts: dict | None = None) -> str:
+ """Build the Gemini assessment prompt.
- snippet = (a.get("visible_text_snippet") or "")[:1200]
- title = a.get("page_title") or ""
- meta = a.get("meta_description") or ""
- country = a.get("ip_country") or "unknown"
- cms = a.get("cms") or "unknown"
- detected_str = ", ".join(detected_brands) if detected_brands else "none detected"
- dist_str = ", ".join(dist_matches) if dist_matches else "none"
+ extra_contacts comes from _scrape_legal_pages() and adds emails/phones/company
+ info found in the aviso legal, privacy policy, and about pages.
+ """
+ ec = extra_contacts or {}
- return f"""You are a senior B2B sales analyst for a cosmetics distribution company operating in Europe.
-Your task: evaluate whether this website is a viable B2B customer (retailer, multi-brand store,
-e-commerce, distributor or chain that buys beauty products wholesale) and generate an outreach plan.
+ # Merge contact sources: site_analyzer (main page + contact pages) + legal pages
+ all_emails = list(dict.fromkeys((a.get("emails") or []) + (ec.get("emails") or [])))[:8]
+ all_phones = list(dict.fromkeys((a.get("phones") or []) + (ec.get("phones") or [])))[:6]
+ all_whatsapp = list(dict.fromkeys(a.get("whatsapp") or []))[:4]
+ all_social = list(dict.fromkeys(a.get("social_links") or []))[:6]
-=== SITE DATA ===
-Domain: {a.get("domain")}
-Country (IP): {country}
-Title: {title}
-Meta desc: {meta}
-CMS: {cms}
-Contact info:
-{contacts_str}
+ def _fmt(lst: list) -> str:
+ return ", ".join(lst) if lst else "—"
+
+ # Site technical signals
+ ssl_info = ("✓ valid" if a.get("ssl_valid") else "✗ invalid/missing")
+ analytics = ", ".join(a.get("analytics_present") or []) or "none detected"
+ word_count = a.get("word_count", 0)
+ load_ms = a.get("load_time_ms", 0)
+ copyright = a.get("copyright_year") or a.get("last_modified") or "unknown"
+
+ snippet = (a.get("visible_text_snippet") or "")[:1600]
+ legal_snippet = (ec.get("legal_snippet") or "")[:800]
+ detected_str = ", ".join(detected_brands) if detected_brands else "none detected"
+ dist_str = ", ".join(dist_matches) if dist_matches else "none"
+
+ return f"""You are a senior B2B sales analyst for a cosmetics distribution company
+operating across Europe. Your task: thoroughly evaluate this website as a potential
+wholesale B2B customer and produce a complete outreach dossier.
+
+=== BUSINESS PROFILE ===
+Domain: {a.get("domain")}
+Country (IP): {a.get("ip_country") or "unknown"}
+Region: {a.get("ip_region") or "unknown"}
+Hosting (EU?): {a.get("eu_hosted")} | ISP/Org: {a.get("org") or a.get("isp") or "unknown"}
+Page title: {a.get("page_title") or "—"}
+H1: {a.get("h1_text") or "—"}
+Meta desc: {(a.get("meta_description") or "—")[:200]}
+CMS: {a.get("cms") or "unknown"}
+Last updated: {copyright}
+
+=== TECHNICAL SIGNALS ===
+SSL: {ssl_info}
+Load time: {load_ms}ms
+Word count: {word_count}
+Analytics: {analytics}
+Mobile: {"yes" if a.get("has_mobile_viewport") else "no"}
+Sitemap/Robots: sitemap={"yes" if a.get("has_sitemap") else "no"}, robots={"yes" if a.get("has_robots") else "no"}
+GDPR/Privacy: cookie_tool={a.get("cookie_tool") or "none"}, privacy_policy={"yes" if a.get("has_privacy_policy") else "no"}
+
+=== ALL CONTACT CHANNELS ===
+Emails: {_fmt(all_emails)}
+Phones: {_fmt(all_phones)}
+WhatsApp: {_fmt(all_whatsapp)}
+Social media: {_fmt(all_social)}
+
+=== LEGAL / COMPANY REGISTRATION INFO ===
+(extracted from aviso legal / política de privacidad — may contain razón social, CIF, address)
+{legal_snippet or "Not found or page not accessible"}
=== PAGE CONTENT SAMPLE ===
{snippet}
-=== BRANDS ALREADY DETECTED ON SITE ===
+=== BRANDS DETECTED ON SITE ===
{detected_str}
=== OUR PORTFOLIO BRANDS FOUND ON THEIR SITE ===
-(These brands we distribute — finding them means we're already in their market)
+(brands we distribute that appear on their site — confirms shared market)
{dist_str}
=== WEB SEARCH RESULTS ===
-{(search_results or "No results.")[:500]}
+{(search_results or "No results available.")[:700]}
-=== OUR DISTRIBUTION PORTFOLIO ===
+=== OUR FULL DISTRIBUTION PORTFOLIO ===
{', '.join(OUR_BRANDS)}
=== BEAUTY CATEGORIES WE COVER ===
{', '.join(BEAUTY_CATEGORIES)}
=== ASSESSMENT RULES ===
-1. Determine if this is a B2B prospect: retailer, pharmacy, parafarmacia,
- perfumería, multi-brand beauty ecommerce, salon chain, supermarket beauty section,
- or beauty products distributor based in Europe.
-2. Identify which categories from our list they cover.
-3. From the page content (even if brands list is empty), identify any beauty brands mentioned.
-4. Match detected brands against our portfolio — this drives lead quality:
- - HOT: 3+ of our portfolio brands detected, OR a large EU retailer clearly in our niche
- - WARM: 1-2 portfolio brand matches, OR clear beauty retailer with good potential
- - COLD: beauty-adjacent but weak match, OR can't confirm they buy wholesale
- - NOT_RELEVANT: not a beauty business or not in Europe
-5. Write all human text (proposal, email) in Spanish.
-6. Keep JSON values concise (≤ 25 words each).
+1. TARGET PROFILE: retailer, pharmacy, parafarmacia, perfumería, multi-brand beauty
+ ecommerce, salon chain, beauty distributor, or supermarket beauty section in Europe.
+2. Identify ALL beauty brands mentioned anywhere on the page — go beyond the pre-detected
+ list above. Use product names, brand references in body text, alt text, etc.
+3. Match brands against our portfolio. Lead quality is driven by portfolio overlap:
+ - HOT: 3+ portfolio brands detected, OR major EU beauty retailer clearly in our niche
+ - WARM: 1-2 portfolio brand matches, OR clear beauty multi-brand retailer with good reach
+ - COLD: beauty-adjacent but weak portfolio overlap, OR single-brand, OR unclear wholesale
+ - NOT_RELEVANT: not a beauty business, not in Europe, or clearly a consumer-only brand
+4. Extract the BEST contact for outreach:
+ - Prefer business/commercial emails (info@, ventas@, compras@, admin@) over personal
+ - If WhatsApp exists, flag it — it's often the fastest channel in Spain/LatAm
+ - Check social media for direct messaging channels
+5. Use the legal/company info to identify the official business name (razón social),
+ and if a CIF/NIF is visible, mention it in outreach_notes as it confirms legitimacy.
+6. Write summary, pitch_angle, b2b_proposal, outreach_subject, and outreach_email in Spanish.
+7. The outreach_email must be a complete ready-to-send email: greeting, 2-3 body sentences
+ (reference their specific range, 1-2 matching portfolio brands, add value), clear CTA.
-Respond ONLY with valid JSON, no markdown, no text outside JSON:
+Respond ONLY with valid JSON, no markdown fences, no text outside the JSON object:
{{
- "is_relevant": true/false,
+ "is_relevant": true,
"lead_quality": "HOT|WARM|COLD|NOT_RELEVANT",
- "lead_reasoning": "1-2 sentences why",
- "business_type": "retailer|ecommerce|distributor|pharmacy|salon_chain|other",
- "business_name": "name from title or domain",
- "country_fiscal": "2-letter ISO or full name",
- "countries_active": ["ES","FR"],
+ "summary": "2-3 sentence executive summary: what this business does, their product range, who their customers are, and their apparent scale",
+ "lead_reasoning": "2-3 sentences explaining the lead quality rating — reference specific brands found, categories covered, and portfolio overlap",
+ "business_type": "retailer|ecommerce|distributor|pharmacy|parafarmacia|salon_chain|perfumeria|other",
+ "business_name": "official business name from title, H1, or aviso legal",
+ "country_fiscal": "2-letter ISO",
+ "countries_active": ["ES"],
"categories": ["Hair Care","Makeup"],
- "detected_brands": ["brand1","brand2"],
- "dist_matches": ["OurBrand1","OurBrand2"],
- "contact_email": "email or empty string",
- "contact_phone": "phone or empty string",
- "contact_whatsapp": "whatsapp link or empty string",
- "contact_social": "primary social profile URL or empty string",
- "b2b_proposal": "1-2 sentence value proposition in Spanish referencing their categories and our matching brands",
- "outreach_subject": "short Spanish subject line referencing their business name",
- "outreach_email": "3-4 sentence ready-to-send email in Spanish. Mention their business, 1-2 specific brands from our portfolio that match their range, and a clear call to action (catálogo, muestra, llamada).",
- "revenue_estimate": "unknown",
- "outreach_notes": "brief context for sales rep"
+ "detected_brands": ["all beauty brands found on site — be thorough"],
+ "dist_matches": ["our portfolio brands found on their site"],
+ "partnership_signals": ["carries multi-brand","has wholesale section","stockist page","B2B portal"],
+ "pitch_angle": "1 punchy sentence in Spanish: the specific angle for this business (reference their range, a gap you fill, or the portfolio brands that match)",
+ "b2b_proposal": "2-3 sentence value proposition in Spanish: what we offer, why it fits their range, what differentiates our brands",
+ "outreach_subject": "specific Spanish subject line mentioning their business name and 1 relevant brand",
+ "outreach_email": "complete ready-to-send Spanish email: greeting + 3-4 body sentences referencing their specific product range and 1-2 portfolio brands that match + clear CTA (catálogo, muestra, llamada, pedido mínimo) + valediction. Do not use placeholders.",
+ "best_contact_channel": "email|phone|whatsapp|social|web_form|unknown",
+ "best_contact_value": "the actual email/phone/URL to use — prefer commercial emails, then phone, then social",
+ "all_contacts": {{
+ "emails": {json.dumps(all_emails)},
+ "phones": {json.dumps(all_phones)},
+ "whatsapp": {json.dumps(all_whatsapp)},
+ "social": {json.dumps(all_social)}
+ }},
+ "revenue_estimate": "unknown|<100k€|100k-500k€|500k-2M€|>2M€",
+ "outreach_notes": "2-3 sentences for the sales rep: timing, approach, red flags, CIF if found, any urgency signals"
}}"""
@@ -309,21 +444,31 @@ async def assess_beauty_domain(analysis: dict) -> dict:
detected = detect_brands_in_text(text)
dist_match = get_dist_matches(detected)
- # Also search for company context
+ # Run DDG search and legal page scraping in parallel
title = analysis.get("page_title") or ""
biz_name = title.split("|")[0].split("-")[0].strip() or domain
- search_results = await _ddg_search(f'"{biz_name}" {domain} beauty cosmetics wholesale contact')
- logger.info("Beauty assess %s: %d brands detected, %d portfolio matches",
- domain, len(detected), len(dist_match))
+ search_results, extra_contacts = await asyncio.gather(
+ _ddg_search(f'"{biz_name}" {domain} cosmetics beauty wholesale B2B contacto'),
+ _scrape_legal_pages(domain),
+ )
+
+ logger.info(
+ "Beauty assess %s: %d brands, %d portfolio matches, "
+ "%d extra emails from legal pages",
+ domain, len(detected), len(dist_match),
+ len(extra_contacts.get("emails", [])),
+ )
payload = {
"input": {
- "prompt": _build_beauty_prompt(analysis, detected, dist_match, search_results),
+ "prompt": _build_beauty_prompt(
+ analysis, detected, dist_match, search_results, extra_contacts
+ ),
"images": [], "videos": [],
"top_p": 0.9,
- "temperature": 0.15,
+ "temperature": 0.2,
"thinking_level": "low",
- "max_output_tokens": 2000,
+ "max_output_tokens": 4000,
}
}
try:
@@ -351,17 +496,45 @@ async def assess_beauty_domain(analysis: dict) -> dict:
if not result.get("detected_brands") and detected:
result["detected_brands"] = detected
- # Always merge contact data directly from site_analyzer — more reliable
- # than AI extraction since it uses regex against raw HTML
- phones = analysis.get("phones", [])
- whatsapp = analysis.get("whatsapp", [])
- social_links = analysis.get("social_links", [])
- if phones and not result.get("contact_phone"):
- result["contact_phone"] = phones[0]
- if whatsapp:
- result["contact_whatsapp"] = "; ".join(whatsapp[:2])
- if social_links:
- result["contact_social"] = "; ".join(social_links[:3])
+ # Merge contact data directly from site_analyzer + legal pages —
+ # more reliable than AI extraction since it's regex against raw HTML.
+ # The AI's all_contacts field may already have the right data if it
+ # followed the schema; fill gaps from our own extraction.
+ all_emails = list(dict.fromkeys(
+ (analysis.get("emails") or []) + (extra_contacts.get("emails") or [])
+ ))[:8]
+ all_phones = list(dict.fromkeys(
+ (analysis.get("phones") or []) + (extra_contacts.get("phones") or [])
+ ))[:6]
+ all_whatsapp = list(dict.fromkeys(analysis.get("whatsapp") or []))[:4]
+ all_social = list(dict.fromkeys(analysis.get("social_links") or []))[:6]
+
+ # Ensure all_contacts in result is always populated from our own data
+ if not result.get("all_contacts") or not isinstance(result.get("all_contacts"), dict):
+ result["all_contacts"] = {}
+ result["all_contacts"].setdefault("emails", [])
+ result["all_contacts"].setdefault("phones", [])
+ result["all_contacts"].setdefault("whatsapp", [])
+ result["all_contacts"].setdefault("social", [])
+ # Merge our extracted data into the AI's all_contacts
+ result["all_contacts"]["emails"] = list(dict.fromkeys(
+ result["all_contacts"]["emails"] + all_emails))[:8]
+ result["all_contacts"]["phones"] = list(dict.fromkeys(
+ result["all_contacts"]["phones"] + all_phones))[:6]
+ result["all_contacts"]["whatsapp"] = list(dict.fromkeys(
+ result["all_contacts"]["whatsapp"] + all_whatsapp))[:4]
+ result["all_contacts"]["social"] = list(dict.fromkeys(
+ result["all_contacts"]["social"] + all_social))[:6]
+
+ # Fill top-level contact fields from merged data if AI left them blank
+ if not result.get("contact_email") and all_emails:
+ result["contact_email"] = all_emails[0]
+ if not result.get("contact_phone") and all_phones:
+ result["contact_phone"] = all_phones[0]
+ if not result.get("contact_whatsapp") and all_whatsapp:
+ result["contact_whatsapp"] = all_whatsapp[0]
+ if not result.get("contact_social") and all_social:
+ result["contact_social"] = all_social[0]
logger.info("Beauty AI %s → quality=%s, dist_matches=%s",
domain, result.get("lead_quality"), result.get("dist_matches"))
@@ -369,17 +542,24 @@ async def assess_beauty_domain(analysis: dict) -> dict:
except Exception as e:
logger.error("Beauty AI error %s: %s", domain, e)
- phones = analysis.get("phones", [])
- whatsapp = analysis.get("whatsapp", [])
- social = analysis.get("social_links", [])
+ all_emails = list(dict.fromkeys(
+ (analysis.get("emails") or []) + (extra_contacts.get("emails") or [])))[:8]
+ all_phones = list(dict.fromkeys(
+ (analysis.get("phones") or []) + (extra_contacts.get("phones") or [])))[:6]
+ all_whatsapp = list(dict.fromkeys(analysis.get("whatsapp") or []))[:4]
+ all_social = list(dict.fromkeys(analysis.get("social_links") or []))[:6]
return {
"error": str(e)[:300],
"is_relevant": False,
"lead_quality": "COLD",
"dist_matches": dist_match,
"detected_brands": detected,
- "contact_email": "",
- "contact_phone": phones[0] if phones else "",
- "contact_whatsapp": "; ".join(whatsapp[:2]) if whatsapp else "",
- "contact_social": "; ".join(social[:3]) if social else "",
+ "contact_email": all_emails[0] if all_emails else "",
+ "contact_phone": all_phones[0] if all_phones else "",
+ "contact_whatsapp": all_whatsapp[0] if all_whatsapp else "",
+ "contact_social": all_social[0] if all_social else "",
+ "all_contacts": {
+ "emails": all_emails, "phones": all_phones,
+ "whatsapp": all_whatsapp, "social": all_social,
+ },
}
diff --git a/app/static/beauty/index.html b/app/static/beauty/index.html
index b32771f..ba0c541 100644
--- a/app/static/beauty/index.html
+++ b/app/static/beauty/index.html
@@ -340,7 +340,7 @@ textarea{width:100%;resize:vertical;font-family:monospace;font-size:12px}
—