RIPLEY

core/services/resolution.py

@@ -16,6 +16,37 @@ class WebCrawler:
             "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36"
         })
 
+    def fetch_url(self, url):
+        """
+        Fetch URL and extract basic metadata and image links.
+        """
+        try:
+            response = self.session.get(url, timeout=10)
+            response.raise_for_status()
+            soup = BeautifulSoup(response.text, "html.parser")
+            
+            # Extract meta tags
+            metadata = {
+                "title": soup.title.string if soup.title else "No title",
+                "description": soup.find("meta", attrs={"name": "description"}),
+            }
+            if metadata["description"]:
+                metadata["description"] = metadata["description"].get("content", "")
+            else:
+                metadata["description"] = ""
+            
+            # Extract images (top 3)
+            images = []
+            for img in soup.find_all("img", limit=3):
+                src = img.get("src")
+                if src:
+                    images.append(urljoin(url, src))
+            
+            return metadata, images
+        except Exception as e:
+            logger.error(f"Failed to crawl {url}: {e}")
+            return None, []
+
     def search(self, query):
         """
         Perform a simulated search on Google using requests.
@@ -28,16 +59,18 @@ class WebCrawler:
             response.raise_for_status()
             soup = BeautifulSoup(response.text, "html.parser")
             
-            # Simple extraction of titles/links from Google search results
             results = []
-            # Selector for Google search result titles
             for g in soup.select("div.g"):
                 title_elem = g.select_one("h3")
                 link_elem = g.select_one("a")
                 if title_elem and link_elem:
+                    url = link_elem.get("href")
+                    # Handle Google's link redirecting
+                    if url.startswith("/url?q="):
+                        url = url.split("/url?q=")[1].split("&")[0]
                     results.append({
                         "title": title_elem.get_text(),
-                        "url": link_elem.get("href")
+                        "url": url
                     })
             return results
         except Exception as e:
@@ -48,7 +81,7 @@ class NetworkDiscoveryService:
     @staticmethod
     def perform_osint_search(query):
         """
-        Performs discovery using Web Crawling.
+        Performs discovery using Web Crawling, extracting metadata and images.
         """
         try:
             crawler = WebCrawler()
@@ -62,13 +95,22 @@ class NetworkDiscoveryService:
                 value=query,
                 source=source
             )
+            # Default photo fallback
             person.photo_url = f"https://api.dicebear.com/7.x/pixel-art/svg?seed={query.replace(' ', '+')}"
-            person.save()
+            
-
+            # 2. Extract potential associates and crawl their pages
-            # 2. Extract potential associates from titles
             for res in search_results:
-                # Naive associate detection
+                metadata, images = crawler.fetch_url(res['url'])
-                associate_val = res['title'][:50]
+                
+                # If we found an image on their page, prioritize that for the main person if it's the first result
+                if images and not person.photo_url.startswith("https://api.dicebear.com"):
+                    person.photo_url = images[0]
+                elif images and person.photo_url.startswith("https://api.dicebear.com"):
+                    # For demo purposes, set photo from the first relevant page
+                    person.photo_url = images[0]
+
+                # Create associate
+                associate_val = metadata['title'] if metadata and metadata['title'] != "No title" else res['title'][:50]
                 if associate_val != query:
                     associate, _ = Entity.objects.get_or_create(
                         entity_type='PERSON',
@@ -76,6 +118,8 @@ class NetworkDiscoveryService:
                         source=source
                     )
                     
+                    # Store link/metadata info if you have a field for it
+                    
                     # 3. Create relationship
                     Relationship.objects.get_or_create(
                         source_entity=person,
@@ -84,6 +128,7 @@ class NetworkDiscoveryService:
                         weight=0.5
                     )
             
+            person.save()
             return person
 
         except Exception as e:
@@ -94,4 +139,4 @@ class EntityResolutionService:
     @staticmethod
     def resolve_identity(identifier_a, identifier_b, probability_threshold=0.8):
         # Implementation remains unchanged
-        return True
+        return True