fix(competitor-analysis): final migration fixes and documentation updates

fotograf-de-scraper/backend/main.py

@@ -585,6 +585,8 @@ def process_reminder_analysis(task_id: str, job_id: str, account_type: str, max_
         aggregation = {}
         missing_links_count = 0
         
+        base_url = "https://kinderfoto-erding.fotograf.de" if account_type == "kiga" else "https://kinderfotos-erding.fotograf.de"
+        
         for c in candidates:
             email = c.email_eltern.lower()
             
@@ -592,12 +594,6 @@ def process_reminder_analysis(task_id: str, job_id: str, account_type: str, max_
             if exclude_purchased_emails and email in purchased_emails:
                 continue
                 
-            # STRICT LINK CHECK: If we don't have a scraped Quick Login URL, skip this child.
-            # We don't want to send broken /login/access/ links.
-            if not c.quick_login_url:
-                missing_links_count += 1
-                continue
-
             if email not in aggregation:
                 aggregation[email] = {
                     "email": email,
@@ -612,8 +608,18 @@ def process_reminder_analysis(task_id: str, job_id: str, account_type: str, max_
             if child_label and child_label not in aggregation[email]["children"]:
                 aggregation[email]["children"].append(child_label)
             
-            # Add Quick Login Link (Guaranteed to exist here)
+            # Determine best link
-            html_link = f'<a href="{c.quick_login_url}">Fotos von {child_label}</a>'
+            if c.quick_login_url and "/gc/" in c.quick_login_url:
+                # Use scraped direct link if available
+                final_link = c.quick_login_url
+                link_text = f"Fotos von {child_label}"
+            else:
+                # Fallback to direct code navigation link
+                final_link = f"{base_url}/login/{c.zugangscode}"
+                link_text = f"Fotos von {child_label}"
+                missing_links_count += 1
+            
+            html_link = f'<a href="{final_link}">{link_text}</a>'
             if html_link not in aggregation[email]["links"]:
                 aggregation[email]["links"].append(html_link)
 
@@ -633,7 +639,7 @@ def process_reminder_analysis(task_id: str, job_id: str, account_type: str, max_
 
         progress_msg = f"Analyse fertig! {len(final_result)} Empfänger identifiziert."
         if missing_links_count > 0:
-            progress_msg += f" (Hinweis: {missing_links_count} Kinder ignoriert, da Quick-Login-Link fehlt. Bitte vorher 'Daten abgleichen' drücken!)"
+            progress_msg += f" (Hinweis: {missing_links_count} Links wurden generiert, da sie noch nicht gescraped wurden.)"
 
         task_store[task_id] = {
             "status": "completed", 

patch.py

@@ -1,44 +0,0 @@
-import re
-
-with open('fotograf-de-scraper/backend/main.py', 'r') as f:
-    content = f.read()
-
-old_code = """                                    try:
-                                        wait_short = WebDriverWait(driver, 5)
-                                        quick_link_el = wait_short.until(EC.presence_of_element_located((By.XPATH, SELECTORS["quick_login_url"])))
-                                        quick_link = quick_link_el.get_attribute("href")
-                                        
-                                        # Update DB
-                                        codes_to_find[code].quick_login_url = quick_link
-                                        del codes_to_find[code]
-                                        links_found += 1
-                                        
-                                        if links_found % 5 == 0: db.commit()
-                                    except:
-                                        logger.warning(f"Could not find quick login link for {code}")"""
-
-new_code = """                                    for attempt in range(3):
-                                        try:
-                                            wait_short = WebDriverWait(driver, 5)
-                                            quick_link_el = wait_short.until(EC.visibility_of_element_located((By.XPATH, SELECTORS["quick_login_url"])))
-                                            quick_link = quick_link_el.get_attribute("href")
-                                            
-                                            # Update DB
-                                            codes_to_find[code].quick_login_url = quick_link
-                                            del codes_to_find[code]
-                                            links_found += 1
-                                            
-                                            if links_found % 5 == 0: db.commit()
-                                            break
-                                        except Exception as e:
-                                            time.sleep(1)
-                                    else:
-                                        logger.warning(f"Could not find quick login link for {code}")"""
-
-if old_code in content:
-    content = content.replace(old_code, new_code)
-    with open('fotograf-de-scraper/backend/main.py', 'w') as f:
-        f.write(content)
-    print("Patched successfully")
-else:
-    print("Old code not found")

patch_frontend.py

@@ -0,0 +1,15 @@
+import sys
+
+with open('fotograf-de-scraper/frontend/src/App.tsx', 'r') as f:
+    content = f.read()
+
+old_body = """  const [emailBody, setEmailBody] = useState("Hallo {Name Käufer},<br><br>deine Fotos sind fertig und warten auf dich! Kopiere einfach deinen Zugangscode und klicke auf den Link zum Shop, um dich einzuloggen:<br><br>{LinksHTML}<br><br>Viel Spaß beim Anschauen!");"""
+new_body = """  const [emailBody, setEmailBody] = useState("Hallo {Name Käufer},<br><br>deine Fotos sind fertig und warten auf dich! Klicke einfach auf die Links unten, um direkt zu den Galerien zu gelangen:<br><br>{LinksHTML}<br><br>Viel Spaß beim Anschauen!");"""
+
+if old_body in content:
+    content = content.replace(old_body, new_body)
+    with open('fotograf-de-scraper/frontend/src/App.tsx', 'w') as f:
+        f.write(content)
+    print("Frontend patched")
+else:
+    print("Frontend code not found")

patch_reminder.py

@@ -0,0 +1,130 @@
+import sys
+
+with open('fotograf-de-scraper/backend/main.py', 'r') as f:
+    content = f.read()
+
+old_code = """        # 3. Aggregate results by Email
+        aggregation = {}
+        missing_links_count = 0
+        
+        for c in candidates:
+            email = c.email_eltern.lower()
+            
+            # Skip if this email already has a purchase for ANOTHER child
+            if exclude_purchased_emails and email in purchased_emails:
+                continue
+                
+            # STRICT LINK CHECK: If we don't have a scraped Quick Login URL, skip this child.
+            # We don't want to send broken /login/access/ links.
+            if not c.quick_login_url:
+                missing_links_count += 1
+                continue
+
+            if email not in aggregation:
+                aggregation[email] = {
+                    "email": email,
+                    "parent_name": c.vorname_eltern if c.vorname_eltern else "Liebe Eltern",
+                    "children": [],
+                    "links": []
+                }
+            
+            # Add child name
+            child_name = c.vorname_kind or ""
+            child_label = "Familienbilder" if child_name.lower() == "familie" else child_name
+            if child_label and child_label not in aggregation[email]["children"]:
+                aggregation[email]["children"].append(child_label)
+            
+            # Add Quick Login Link (Guaranteed to exist here)
+            html_link = f'<a href="{c.quick_login_url}">Fotos von {child_label}</a>'
+            if html_link not in aggregation[email]["links"]:
+                aggregation[email]["links"].append(html_link)
+
+        # 4. Format for Supermailer/Gmail
+        final_result = []
+        for email, data in aggregation.items():
+            children_str = " und ".join(data["children"]) if len(data["children"]) > 1 else (data["children"][0] if data["children"] else "Eurem Kind")
+            links_html = "".join([f"{l}<br>" for l in data["links"]])
+            
+            final_result.append({
+                "E-Mail-Adresse Käufer": email,
+                "Name Käufer": data["parent_name"],
+                "Kindernamen": children_str,
+                "Anzahl Kinder": len(data["children"]),
+                "LinksHTML": links_html
+            })
+
+        progress_msg = f"Analyse fertig! {len(final_result)} Empfänger identifiziert."
+        if missing_links_count > 0:
+            progress_msg += f" (Hinweis: {missing_links_count} Kinder ignoriert, da Quick-Login-Link fehlt. Bitte vorher 'Daten abgleichen' drücken!)"
+
+        task_store[task_id] = {"""
+
+new_code = """        # 3. Aggregate results by Email
+        aggregation = {}
+        missing_links_count = 0
+        
+        base_url = "https://kinderfoto-erding.fotograf.de" if account_type == "kiga" else "https://kinderfotos-erding.fotograf.de"
+        
+        for c in candidates:
+            email = c.email_eltern.lower()
+            
+            # Skip if this email already has a purchase for ANOTHER child
+            if exclude_purchased_emails and email in purchased_emails:
+                continue
+                
+            if email not in aggregation:
+                aggregation[email] = {
+                    "email": email,
+                    "parent_name": c.vorname_eltern if c.vorname_eltern else "Liebe Eltern",
+                    "children": [],
+                    "links": []
+                }
+            
+            # Add child name
+            child_name = c.vorname_kind or ""
+            child_label = "Familienbilder" if child_name.lower() == "familie" else child_name
+            if child_label and child_label not in aggregation[email]["children"]:
+                aggregation[email]["children"].append(child_label)
+            
+            # Determine best link
+            if c.quick_login_url and "/gc/" in c.quick_login_url:
+                # Use scraped direct link if available
+                final_link = c.quick_login_url
+                link_text = f"Fotos von {child_label}"
+            else:
+                # Fallback to direct code navigation link
+                final_link = f"{base_url}/login/{c.zugangscode}"
+                link_text = f"Fotos von {child_label}"
+                missing_links_count += 1
+            
+            html_link = f'<a href="{final_link}">{link_text}</a>'
+            if html_link not in aggregation[email]["links"]:
+                aggregation[email]["links"].append(html_link)
+
+        # 4. Format for Supermailer/Gmail
+        final_result = []
+        for email, data in aggregation.items():
+            children_str = " und ".join(data["children"]) if len(data["children"]) > 1 else (data["children"][0] if data["children"] else "Eurem Kind")
+            links_html = "".join([f"{l}<br>" for l in data["links"]])
+            
+            final_result.append({
+                "E-Mail-Adresse Käufer": email,
+                "Name Käufer": data["parent_name"],
+                "Kindernamen": children_str,
+                "Anzahl Kinder": len(data["children"]),
+                "LinksHTML": links_html
+            })
+
+        progress_msg = f"Analyse fertig! {len(final_result)} Empfänger identifiziert."
+        if missing_links_count > 0:
+            progress_msg += f" (Hinweis: {missing_links_count} Links wurden generiert, da sie noch nicht gescraped wurden.)"
+
+        task_store[task_id] = {"""
+
+if old_code in content:
+    content = content.replace(old_code, new_code)
+    with open('fotograf-de-scraper/backend/main.py', 'w') as f:
+        f.write(content)
+    print("Patched successfully")
+else:
+    print("Old code not found")