Floke/Brancheneinstufung2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

scrape_fotograf.py aktualisiert

Browse Source
This commit is contained in:
Floke
2025-07-16 15:30:24 +00:00
parent 4b3b03b987
commit e8321ff09d
1 changed files with 28 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
scrape_fotograf.py
View File

@@ -8,7 +8,7 @@ from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException, NoSuchElementException, InvalidSelectorException from selenium.common.exceptions import TimeoutException, NoSuchElementException
# --- Konfiguration & Konstanten --- # --- Konfiguration & Konstanten ---
CREDENTIALS_FILE = 'fotograf_credentials.json' CREDENTIALS_FILE = 'fotograf_credentials.json'
@@ -16,24 +16,27 @@ OUTPUT_DIR = 'output'
OUTPUT_FILE = os.path.join(OUTPUT_DIR, 'nutzer_ohne_logins.csv') OUTPUT_FILE = os.path.join(OUTPUT_DIR, 'nutzer_ohne_logins.csv')
LOGIN_URL = 'https://app.fotograf.de/login/login' LOGIN_URL = 'https://app.fotograf.de/login/login'
# --- Selektoren (FINALE VERSION 2.0) --- # --- Selektoren (FINALE VERSION 3.0) ---
SELECTORS = { SELECTORS = {
"cookie_accept_button": "#CybotCookiebotDialogBodyLevelButtonLevelOptinAllowAll", "cookie_accept_button": "#CybotCookiebotDialogBodyLevelButtonLevelOptinAllowAll",
"login_user": "#login-email", "login_user": "#login-email",
"login_pass": "#login-password", "login_pass": "#login-password",
"login_button": "#login-submit", "login_button": "#login-submit",
"job_name": "h1", "job_name": "h1",
# Album-Übersicht (funktioniert) # Album-Übersicht
"album_overview_rows": "//table/tbody/tr", "album_overview_rows": "//table/tbody/tr",
"album_overview_link": ".//td[2]//a", "album_overview_link": ".//td[2]//a",
# Einzelpersonen-Ansicht (basierend auf Ihrem finalen HTML) # Einzelpersonen-Ansicht (innerhalb eines Albums)
"person_rows": "//div[contains(@class, 'border-legacy-silver-550') and .//span[text()='Logins']]", "person_rows": "//div[contains(@class, 'border-legacy-silver-550') and .//span[text()='Logins']]",
"person_vorname": ".//span[text()='Vorname']/following-sibling::strong", "person_vorname": ".//span[text()='Vorname']/following-sibling::strong",
"person_logins": ".//span[text()='Logins']/following-sibling::strong", "person_logins": ".//span[text()='Logins']/following-sibling::strong",
"person_buyer_link": ".//a[contains(@data-qa-id, 'guest-access-banner-access-code')]", "person_access_code_link": ".//a[contains(@data-qa-id, 'guest-access-banner-access-code')]",
# Käufer-Detailseite (funktioniert) # "Kommunikation"-Seite (nach Klick auf Zugangscode)
"potential_buyer_link": "//a[contains(@href, '/config_customers/view_customer')]",
# Käufer-Detailseite (finale Seite)
"buyer_email": "//span[contains(., '@')]" "buyer_email": "//span[contains(., '@')]"
} }
@@ -77,8 +80,7 @@ def login(driver, username, password):
wait = WebDriverWait(driver, 10) wait = WebDriverWait(driver, 10)
try: try:
print("Suche nach Cookie-Banner...") print("Suche nach Cookie-Banner...")
cookie_button = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, SELECTORS["cookie_accept_button"]))) wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, SELECTORS["cookie_accept_button"]))).click()
cookie_button.click()
print("Cookie-Banner akzeptiert.") print("Cookie-Banner akzeptiert.")
time.sleep(1) time.sleep(1)
except TimeoutException: except TimeoutException:
@@ -121,9 +123,8 @@ def process_full_job(driver, job_url):
print(f"{len(album_rows)} Alben in der Übersicht gefunden.") print(f"{len(album_rows)} Alben in der Übersicht gefunden.")
for row in album_rows: for row in album_rows:
try: try:
album_name = row.find_element(By.XPATH, SELECTORS["album_overview_link"]).text album_link = row.find_element(By.XPATH, SELECTORS["album_overview_link"])
album_link = row.find_element(By.XPATH, SELECTORS["album_overview_link"]).get_attribute('href') albums_to_visit.append({"name": album_link.text, "url": album_link.get_attribute('href')})
albums_to_visit.append({"name": album_name, "url": album_link})
except NoSuchElementException: except NoSuchElementException:
continue continue
print(f"{len(albums_to_visit)} gültige Album-Links gesammelt.") print(f"{len(albums_to_visit)} gültige Album-Links gesammelt.")
@@ -137,26 +138,26 @@ def process_full_job(driver, job_url):
print(f"\n--- Betrete Album: {album['name']} ---") print(f"\n--- Betrete Album: {album['name']} ---")
driver.get(album['url']) driver.get(album['url'])
try: try:
# Warten, bis die Personen-DIVs geladen sind
person_rows = wait.until(EC.presence_of_all_elements_located((By.XPATH, SELECTORS["person_rows"]))) person_rows = wait.until(EC.presence_of_all_elements_located((By.XPATH, SELECTORS["person_rows"])))
print(f"{len(person_rows)} Personen in diesem Album gefunden.") print(f"{len(person_rows)} Personen in diesem Album gefunden.")
for person_row in person_rows: for person_row in person_rows:
try: try:
login_count_text = person_row.find_element(By.XPATH, SELECTORS["person_logins"]).text login_count = int(person_row.find_element(By.XPATH, SELECTORS["person_logins"]).text)
login_count = int(login_count_text)
if login_count == 0: if login_count == 0:
vorname = person_row.find_element(By.XPATH, SELECTORS["person_vorname"]).text vorname = person_row.find_element(By.XPATH, SELECTORS["person_vorname"]).text
print(f" --> ERFOLG: '{vorname}' mit 0 Logins gefunden!") print(f" --> ERFOLG: '{vorname}' mit 0 Logins gefunden!")
buyer_link_element = person_row.find_element(By.XPATH, SELECTORS["person_buyer_link"]) # 1. Gehe zur "Kommunikation"-Seite
buyer_page_url = buyer_link_element.get_attribute('href') access_code_page_url = person_row.find_element(By.XPATH, SELECTORS["person_access_code_link"]).get_attribute('href')
driver.get(access_code_page_url)
# E-Mail in einem neuen Tab holen, um den Kontext nicht zu verlieren print(f" Navigiere zur Kommunikations-Seite für '{vorname}'...")
driver.execute_script("window.open(arguments[0]);", buyer_page_url)
driver.switch_to.window(driver.window_handles[-1])
# 2. Klicke auf den Link zum potenziellen Käufer, um zur finalen Seite zu gelangen
wait.until(EC.element_to_be_clickable((By.XPATH, SELECTORS["potential_buyer_link"]))).click()
print(f" Navigiere zur Käufer-Detailseite...")
# 3. Extrahiere die E-Mail
email = wait.until(EC.visibility_of_element_located((By.XPATH, SELECTORS["buyer_email"]))).text email = wait.until(EC.visibility_of_element_located((By.XPATH, SELECTORS["buyer_email"]))).text
print(f" E-Mail gefunden: {email}") print(f" E-Mail gefunden: {email}")
@@ -167,10 +168,10 @@ def process_full_job(driver, job_url):
"Käufer E-Mail": email "Käufer E-Mail": email
}) })
driver.close() # Gehe zurück zur Album-Detailseite, um die nächste Person zu prüfen
driver.switch_to.window(driver.window_handles[0]) driver.get(album['url'])
except (ValueError, NoSuchElementException, TimeoutException) as e:
except (ValueError, NoSuchElementException): #print(f" Fehler beim Verarbeiten einer Person: {e}")
continue continue
except TimeoutException: except TimeoutException:
print(f" Keine Personen-Daten im Album '{album['name']}' gefunden. Überspringe.") print(f" Keine Personen-Daten im Album '{album['name']}' gefunden. Überspringe.")
@@ -193,6 +194,7 @@ def save_results_to_csv(results):
print("Speichern erfolgreich!") print("Speichern erfolgreich!")
def get_profile_choice(): def get_profile_choice():
# ... unverändert ...
all_credentials = load_all_credentials() all_credentials = load_all_credentials()
if not all_credentials: return None if not all_credentials: return None
profiles = list(all_credentials.keys()) profiles = list(all_credentials.keys())
@@ -209,6 +211,7 @@ def get_profile_choice():
except ValueError: print("Ungültige Eingabe.") except ValueError: print("Ungültige Eingabe.")
def main(): def main():
# ... unverändert ...
print("--- Fotograf.de Scraper für Nutzer ohne Logins (FINALE VERSION) ---") print("--- Fotograf.de Scraper für Nutzer ohne Logins (FINALE VERSION) ---")
credentials = get_profile_choice() credentials = get_profile_choice()
if not credentials: return if not credentials: return