scrape_fotograf.py aktualisiert

scrape_fotograf.py

@@ -14,10 +14,10 @@ from selenium.common.exceptions import TimeoutException, NoSuchElementException,
 # --- Konfiguration & Konstanten ---
 CREDENTIALS_FILE = 'fotograf_credentials.json'
 OUTPUT_DIR = 'output'
-OUTPUT_FILE = os.path.join(OUTPUT_DIR, 'nutzer_ohne_logins.csv')
+OUTPUT_FILE = os.path.join(OUTPUT_DIR, 'nutzer_mit_wenig_logins.csv') # Dateiname angepasst
 LOGIN_URL = 'https://app.fotograf.de/login/login'
 
-# --- Selektoren (FINALE, VOLLSTÄNDIGE VERSION) ---
+# --- Selektoren (unverändert) ---
 SELECTORS = {
     "cookie_accept_button": "#CybotCookiebotDialogBodyLevelButtonLevelOptinAllowAll",
     "login_user": "#login-email",
@@ -26,7 +26,6 @@ SELECTORS = {
     "job_name": "h1",
     "album_overview_rows": "//table/tbody/tr",
     "album_overview_link": ".//td[2]//a",
-    # NEU: Selector für die Gesamtzahl der Zugangscodes
     "access_code_count": "//span[text()='Zugangscodes']/following-sibling::strong",
     "person_rows": "//div[contains(@class, 'border-legacy-silver-550') and .//span[text()='Logins']]",
     "person_vorname": ".//span[text()='Vorname']/following-sibling::strong",
@@ -140,7 +139,6 @@ def process_full_job(driver, job_url):
         print(f"\n--- Betrete Album: {album['name']} ---")
         driver.get(album['url'])
         try:
-            # NEU: Pagination-Logik
             total_codes_text = wait.until(EC.visibility_of_element_located((By.XPATH, SELECTORS["access_code_count"]))).text
             num_pages = math.ceil(int(total_codes_text) / 20)
             print(f"Album hat {total_codes_text} Zugangscodes auf {num_pages} Seite(n).")
@@ -161,9 +159,11 @@ def process_full_job(driver, job_url):
                     person_row = person_rows[i]
                     
                     login_count_text = person_row.find_element(By.XPATH, SELECTORS["person_logins"]).text
-                    if int(login_count_text) == 0:
+                    
+                    # --- HIER IST DIE GEÄNDERTE LOGIK ---
+                    if int(login_count_text) <= 1:
                         vorname = person_row.find_element(By.XPATH, SELECTORS["person_vorname"]).text
-                        print(f"    --> ERFOLG: '{vorname}' mit 0 Logins gefunden!")
+                        print(f"    --> ERFOLG: '{vorname}' mit {login_count_text} Login(s) gefunden!")
                         
                         access_code_page_url = person_row.find_element(By.XPATH, SELECTORS["person_access_code_link"]).get_attribute('href')
                         driver.get(access_code_page_url)
@@ -240,7 +240,7 @@ def get_profile_choice():
         except ValueError: print("Ungültige Eingabe.")
 
 def main():
-    print("--- Fotograf.de Scraper für Nutzer ohne Logins (FINALE VERSION) ---")
+    print("--- Fotograf.de Scraper für Nutzer mit wenig Logins (0 oder 1) ---")
     credentials = get_profile_choice()
     if not credentials: return