scrape_fotograf.py aktualisiert

scrape_fotograf.py

@@ -39,7 +39,6 @@ SELECTORS = {
 }
 
 def take_error_screenshot(driver, error_name):
-    # ... (Funktion bleibt unverändert) ...
     os.makedirs(OUTPUT_DIR, exist_ok=True)
     timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
     filename = f"error_{error_name}_{timestamp}.png"
@@ -51,7 +50,6 @@ def take_error_screenshot(driver, error_name):
         print(f"!!! Konnte keinen Screenshot speichern: {e}")
 
 def setup_driver():
-    # ... (Funktion bleibt unverändert) ...
     print("Initialisiere Chrome WebDriver...")
     options = Options()
     options.add_argument('--headless')
@@ -66,8 +64,15 @@ def setup_driver():
         print(f"Fehler bei der Initialisierung des WebDrivers: {e}")
         return None
 
+# HIER IST DIE FEHLENDE FUNKTION WIEDER EINGEFÜGT
+def load_all_credentials():
+    try:
+        with open(CREDENTIALS_FILE, 'r') as f:
+            return json.load(f)
+    except (FileNotFoundError, json.JSONDecodeError):
+        return None
+
 def login(driver, username, password):
-    # ... (Funktion bleibt unverändert) ...
     print("Starte Login-Vorgang...")
     try:
         driver.get(LOGIN_URL)
@@ -94,11 +99,9 @@ def login(driver, username, password):
         take_error_screenshot(driver, "login_error") 
         return False
 
-# Die finale, vollständige Logik
 def process_full_job(driver, job_url):
     wait = WebDriverWait(driver, 15)
     
-    # 1. Job-Namen holen
     print(f"\nVerarbeite Job-URL: {job_url}")
     driver.get(job_url)
     try:
@@ -109,7 +112,6 @@ def process_full_job(driver, job_url):
         take_error_screenshot(driver, "job_name_not_found")
         return []
 
-    # 2. Alle Album-Links von der Übersichtsseite sammeln
     job_id = job_url.split('/')[-1]
     albums_overview_url = f"https://app.fotograf.de/config_jobs_photos/index/{job_id}"
     print(f"Navigiere zur Alben-Übersicht: {albums_overview_url}")
@@ -120,16 +122,18 @@ def process_full_job(driver, job_url):
         album_rows = wait.until(EC.presence_of_all_elements_located((By.XPATH, SELECTORS["album_overview_rows"])))
         print(f"{len(album_rows)} Alben in der Übersicht gefunden.")
         for row in album_rows:
-            album_name = row.find_element(By.XPATH, SELECTORS["album_overview_link"]).text
-            album_link = row.find_element(By.XPATH, SELECTORS["album_overview_link"]).get_attribute('href')
-            albums_to_visit.append({"name": album_name, "url": album_link})
+            try:
+                album_name = row.find_element(By.XPATH, SELECTORS["album_overview_link"]).text
+                album_link = row.find_element(By.XPATH, SELECTORS["album_overview_link"]).get_attribute('href')
+                albums_to_visit.append({"name": album_name, "url": album_link})
+            except NoSuchElementException:
+                continue # Ignoriere Zeilen, die kein Album-Link haben (z.B. Team-Bilder)
         print(f"Sammeln der Album-Links abgeschlossen.")
     except TimeoutException:
         print("Konnte die Album-Liste nicht finden.")
         take_error_screenshot(driver, "album_overview_error")
         return []
 
-    # 3. Jedes Album besuchen und die Personen mit 0 Logins finden
     final_results = []
     for album in albums_to_visit:
         print(f"\n--- Betrete Album: {album['name']} ---")
@@ -149,8 +153,6 @@ def process_full_job(driver, job_url):
                         buyer_link_element = person_row.find_element(By.XPATH, SELECTORS["person_buyer_link"])
                         buyer_page_url = buyer_link_element.get_attribute('href')
                         
-                        # Temporär eine neue Seite öffnen, um die E-Mail zu holen
-                        # (man könnte auch die buyer_page_url speichern und später abarbeiten)
                         current_window = driver.current_window_handle
                         driver.execute_script("window.open(arguments[0]);", buyer_page_url)
                         driver.switch_to.window(driver.window_handles[-1])
@@ -165,12 +167,10 @@ def process_full_job(driver, job_url):
                             "Käufer E-Mail": email
                         })
                         
-                        # Tab schließen und zurückkehren
                         driver.close()
                         driver.switch_to.window(current_window)
                         
                 except (ValueError, NoSuchElementException):
-                    # Ignoriere Zeilen, die nicht dem Format entsprechen
                     continue
         except TimeoutException:
             print(f"  Keine Personen-Tabelle im Album '{album['name']}' gefunden. Überspringe.")
@@ -179,13 +179,11 @@ def process_full_job(driver, job_url):
             
     return final_results
 
-# ... (Rest des Skripts: save_results_to_csv, get_profile_choice, etc. bleiben gleich) ...
 def save_results_to_csv(results):
     if not results:
         print("\nKeine Daten zum Speichern vorhanden.")
         return
     os.makedirs(OUTPUT_DIR, exist_ok=True)
-    # Feldnamen an die neue Struktur anpassen
     fieldnames = ["Auftragsname", "Album", "Kind Vorname", "Käufer E-Mail"]
     print(f"\nSpeichere {len(results)} Ergebnisse in '{OUTPUT_FILE}'...")
     with open(OUTPUT_FILE, 'w', newline='', encoding='utf-8') as f: