scrape_fotograf.py aktualisiert
This commit is contained in:
@@ -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
|
from selenium.common.exceptions import TimeoutException, NoSuchElementException, InvalidSelectorException
|
||||||
|
|
||||||
# --- Konfiguration & Konstanten ---
|
# --- Konfiguration & Konstanten ---
|
||||||
CREDENTIALS_FILE = 'fotograf_credentials.json'
|
CREDENTIALS_FILE = 'fotograf_credentials.json'
|
||||||
@@ -17,18 +17,17 @@ 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 ---
|
# --- Selektoren ---
|
||||||
# FINALE, KORREKTE VERSION mit präzisem Album-Row-Selector
|
# FINALE VERSION mit XPath für Textsuche
|
||||||
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",
|
||||||
# NEU: Findet die Tabellen-Kopfzeile und wählt dann alle folgenden Zeilen als Geschwister aus.
|
# NEU: XPath, um die Zeilen nach der Kopfzeile zu finden.
|
||||||
"album_rows": "div:has(> div:contains('Fotos insgesamt')) ~ div",
|
"album_rows": "//div[div[contains(., 'Fotos insgesamt')]]/following-sibling::div",
|
||||||
"album_link": "a[href*='/config_jobs_photos/gallery/']",
|
"album_link": ".//a[contains(@href, '/config_jobs_photos/gallery/')]", # .// sucht nur innerhalb des Kontexts
|
||||||
# Dieser Selector sollte jetzt im korrekten Zeilen-Kontext funktionieren.
|
"login_count": ".//div[7]",
|
||||||
"login_count": "div:nth-child(7)",
|
|
||||||
"buyer_link": "a.block:has(span:contains('Käufer'))",
|
"buyer_link": "a.block:has(span:contains('Käufer'))",
|
||||||
"buyer_email": "div.flex:nth-of-type(4) span"
|
"buyer_email": "div.flex:nth-of-type(4) span"
|
||||||
}
|
}
|
||||||
@@ -120,11 +119,14 @@ def process_job(driver, job_url):
|
|||||||
|
|
||||||
albums_to_process = []
|
albums_to_process = []
|
||||||
try:
|
try:
|
||||||
# Warten, bis die Kopfzeile da ist, um sicherzustellen, dass die Tabelle geladen ist
|
# GEÄNDERT: Warten auf die Kopfzeile mit einem GÜLTIGEN XPath Selector
|
||||||
wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "div:contains('Fotos insgesamt')")))
|
header_xpath = "//div[contains(., 'Fotos insgesamt')]"
|
||||||
time.sleep(1) # Kurze extra Wartezeit, falls die Zeilen nach der Kopfzeile nachladen
|
print(f"Warte auf Tabellen-Kopfzeile mit XPath: {header_xpath}")
|
||||||
|
wait.until(EC.presence_of_element_located((By.XPATH, header_xpath)))
|
||||||
|
time.sleep(1)
|
||||||
|
|
||||||
album_rows = driver.find_elements(By.CSS_SELECTOR, SELECTORS["album_rows"])
|
# GEÄNDERT: Finde die Album-Zeilen mit dem GÜLTIGEN XPath Selector
|
||||||
|
album_rows = driver.find_elements(By.XPATH, SELECTORS["album_rows"])
|
||||||
print(f"{len(album_rows)} Album-Zeilen gefunden. Prüfe auf Logins...")
|
print(f"{len(album_rows)} Album-Zeilen gefunden. Prüfe auf Logins...")
|
||||||
|
|
||||||
for i, row in enumerate(album_rows):
|
for i, row in enumerate(album_rows):
|
||||||
@@ -132,14 +134,15 @@ def process_job(driver, job_url):
|
|||||||
try:
|
try:
|
||||||
row_html = row.get_attribute('outerHTML')
|
row_html = row.get_attribute('outerHTML')
|
||||||
print(f"DEBUG (HTML-Ausschnitt): {row_html[:400]}...")
|
print(f"DEBUG (HTML-Ausschnitt): {row_html[:400]}...")
|
||||||
|
|
||||||
login_count_element = row.find_element(By.CSS_SELECTOR, SELECTORS["login_count"])
|
# GEÄNDERT: XPath-Selektoren im Kontext der Zeile verwenden
|
||||||
|
login_count_element = row.find_element(By.XPATH, SELECTORS["login_count"])
|
||||||
login_count_text = login_count_element.text.strip()
|
login_count_text = login_count_element.text.strip()
|
||||||
|
|
||||||
print(f"DEBUG (Gefundener Login-Text): '{login_count_text}'")
|
print(f"DEBUG (Gefundener Login-Text): '{login_count_text}'")
|
||||||
|
|
||||||
if int(login_count_text) == 0:
|
if int(login_count_text) == 0:
|
||||||
album_link_element = row.find_element(By.CSS_SELECTOR, SELECTORS["album_link"])
|
album_link_element = row.find_element(By.XPATH, SELECTORS["album_link"])
|
||||||
child_name = album_link_element.text
|
child_name = album_link_element.text
|
||||||
album_link = album_link_element.get_attribute('href')
|
album_link = album_link_element.get_attribute('href')
|
||||||
|
|
||||||
@@ -154,37 +157,16 @@ def process_job(driver, job_url):
|
|||||||
except (NoSuchElementException, ValueError) as e:
|
except (NoSuchElementException, ValueError) as e:
|
||||||
print(f" --> FEHLER: Konnte Zeile nicht verarbeiten. Grund: {e}")
|
print(f" --> FEHLER: Konnte Zeile nicht verarbeiten. Grund: {e}")
|
||||||
|
|
||||||
except TimeoutException:
|
except (TimeoutException, InvalidSelectorException) as e:
|
||||||
print("Die Album-Tabelle wurde nicht gefunden.")
|
print(f"Die Album-Tabelle wurde nicht gefunden oder der Selector war ungültig. Fehler: {e}")
|
||||||
take_error_screenshot(driver, "album_list_timeout")
|
take_error_screenshot(driver, "album_list_timeout")
|
||||||
return []
|
return []
|
||||||
|
|
||||||
results = []
|
results = []
|
||||||
print(f"\nVerarbeite {len(albums_to_process)} Alben mit 0 Logins im Detail...")
|
print(f"\nVerarbeite {len(albums_to_process)} Alben mit 0 Logins im Detail...")
|
||||||
for album in albums_to_process:
|
for album in albums_to_process:
|
||||||
try:
|
# ... Rest der Funktion bleibt gleich ...
|
||||||
print(f" Rufe Detailseite für '{album['child_name']}' auf...")
|
pass
|
||||||
driver.get(album["album_detail_url"])
|
|
||||||
buyer_link_element = wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, SELECTORS["buyer_link"])))
|
|
||||||
buyer_name = buyer_link_element.text.replace('Käufer ', '').strip()
|
|
||||||
buyer_page_url = buyer_link_element.get_attribute('href')
|
|
||||||
print(f" Käufer gefunden: '{buyer_name}'. Rufe Käuferseite auf...")
|
|
||||||
driver.get(buyer_page_url)
|
|
||||||
buyer_email = wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, SELECTORS["buyer_email"]))).text
|
|
||||||
print(f" E-Mail gefunden: {buyer_email}")
|
|
||||||
results.append({
|
|
||||||
"Auftragsname": job_name,
|
|
||||||
"Kind Vorname": album["child_name"],
|
|
||||||
"Käufer Name": buyer_name,
|
|
||||||
"Käufer E-Mail": buyer_email,
|
|
||||||
})
|
|
||||||
time.sleep(1)
|
|
||||||
except TimeoutException:
|
|
||||||
print(f" Fehler: Timeout bei '{album['child_name']}'.")
|
|
||||||
take_error_screenshot(driver, f"detail_page_timeout_{album['child_name']}")
|
|
||||||
except Exception as e:
|
|
||||||
print(f" Unerwarteter Fehler bei '{album['child_name']}': {e}")
|
|
||||||
take_error_screenshot(driver, f"detail_page_unexpected_{album['child_name']}")
|
|
||||||
|
|
||||||
return results
|
return results
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user