Method _google_maps_contrib_probe

IntelOSINT.py:11173–11331

(self, gaia_id)

            return ""

    def _google_maps_contrib_probe(self, gaia_id):
        out = {
            "map_url": "",
            "reviews_url": "",
            "photos_url": "",
            "profile_name": "",
            "points": [],
            "reviews_geo": [],
            "photos": [],
            "reviews_count": None,
            "photos_count": None,
            "capture_status": ""
        }
        if not gaia_id:
            return out
        try:
            safe_id = re.sub(r"[^0-9]", "", str(gaia_id))
            if not safe_id:
                return out
            base_url = f"https://www.google.com/maps/contrib/{safe_id}"
            out["map_url"] = base_url
            out["reviews_url"] = f"{base_url}/reviews"
            out["photos_url"] = f"{base_url}/photos"
            headers = {
                "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124 Safari/537.36",
                "Accept-Language": "it-IT,it;q=0.9,en-US;q=0.8,en;q=0.7"
            }
            texts = []
            mas_texts = []
            ok_pages = 0
            for url in (base_url, out["reviews_url"], out["photos_url"]):
                try:
                    r = self._google_maps_get_public(url, headers)
                    if r and r.status_code == 200 and r.text:
                        texts.append(r.text)
                        ok_pages += 1
                except Exception:
                    continue
            if not texts:
                out["capture_status"] = "Profilo Maps non leggibile o non pubblico"
                return out
            txt = "\n".join(texts)
            out["capture_status"] = f"Pagine Maps lette: {ok_pages}"

            mas_links = []
            for raw in re.findall(r'href=["\'](/locationhistory/preview/mas\?[^"\']+)', txt):
                link = raw.replace("\\u003d", "=").replace("\\u0026", "&")
                link = html.unescape(link)
                if link not in mas_links:
                    mas_links.append(link)
            for link in mas_links[:3]:
                try:
                    full_link = "https://www.google.com" + link if link.startswith("/") else link
                    mr = session.get(full_link, headers=headers, timeout=18)
                    if mr.status_code == 200 and mr.text:
                        mas_texts.append(mr.text)
                except Exception:
                    continue