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 15:20:26 +00:00
parent 0bc4942884
commit 64980a85d3
1 changed files with 17 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
scrape_fotograf.py
View File

@@ -16,25 +16,24 @@ 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, KORREKTE VERSION) --- # --- Selektoren (FINALE VERSION 2.0) ---
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 (basierend auf Ihrem XPath, der <table> enthielt) # Album-Übersicht (funktioniert)
"album_overview_rows": "//table/tbody/tr", "album_overview_rows": "//table/tbody/tr",
"album_overview_link": ".//td[2]//a", # Link ist in der 2. Spalte "album_overview_link": ".//td[2]//a",
"album_overview_logins": ".//td[7]", # Logins sind in der 7. Spalte
# Einzelpersonen-Ansicht (innerhalb eines Albums) # Einzelpersonen-Ansicht (basierend auf Ihrem finalen HTML)
"person_rows": "//section[.//h3[contains(., 'Einzelfotos')]]//table/tbody/tr", "person_rows": "//div[contains(@class, 'border-legacy-silver-550') and .//span[text()='Logins']]",
"person_vorname": ".//td[4]", "person_vorname": ".//span[text()='Vorname']/following-sibling::strong",
"person_logins": ".//td[6]", "person_logins": ".//span[text()='Logins']/following-sibling::strong",
"person_buyer_link": ".//td[7]//a", "person_buyer_link": ".//a[contains(@data-qa-id, 'guest-access-banner-access-code')]",
# Käufer-Detailseite # Käufer-Detailseite (funktioniert)
"buyer_email": "//span[contains(., '@')]" "buyer_email": "//span[contains(., '@')]"
} }
@@ -64,7 +63,6 @@ def setup_driver():
print(f"Fehler bei der Initialisierung des WebDrivers: {e}") print(f"Fehler bei der Initialisierung des WebDrivers: {e}")
return None return None
# HIER IST DIE FEHLENDE FUNKTION WIEDER EINGEFÜGT
def load_all_credentials(): def load_all_credentials():
try: try:
with open(CREDENTIALS_FILE, 'r') as f: with open(CREDENTIALS_FILE, 'r') as f:
@@ -127,8 +125,8 @@ def process_full_job(driver, job_url):
album_link = row.find_element(By.XPATH, SELECTORS["album_overview_link"]).get_attribute('href') album_link = row.find_element(By.XPATH, SELECTORS["album_overview_link"]).get_attribute('href')
albums_to_visit.append({"name": album_name, "url": album_link}) albums_to_visit.append({"name": album_name, "url": album_link})
except NoSuchElementException: except NoSuchElementException:
continue # Ignoriere Zeilen, die kein Album-Link haben (z.B. Team-Bilder) continue
print(f"Sammeln der Album-Links abgeschlossen.") print(f"{len(albums_to_visit)} gültige Album-Links gesammelt.")
except TimeoutException: except TimeoutException:
print("Konnte die Album-Liste nicht finden.") print("Konnte die Album-Liste nicht finden.")
take_error_screenshot(driver, "album_overview_error") take_error_screenshot(driver, "album_overview_error")
@@ -139,12 +137,14 @@ 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 = int(person_row.find_element(By.XPATH, SELECTORS["person_logins"]).text) login_count_text = 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
@@ -153,7 +153,7 @@ def process_full_job(driver, job_url):
buyer_link_element = person_row.find_element(By.XPATH, SELECTORS["person_buyer_link"]) buyer_link_element = person_row.find_element(By.XPATH, SELECTORS["person_buyer_link"])
buyer_page_url = buyer_link_element.get_attribute('href') buyer_page_url = buyer_link_element.get_attribute('href')
current_window = driver.current_window_handle # E-Mail in einem neuen Tab holen, um den Kontext nicht zu verlieren
driver.execute_script("window.open(arguments[0]);", buyer_page_url) driver.execute_script("window.open(arguments[0]);", buyer_page_url)
driver.switch_to.window(driver.window_handles[-1]) driver.switch_to.window(driver.window_handles[-1])
@@ -168,12 +168,12 @@ def process_full_job(driver, job_url):
}) })
driver.close() driver.close()
driver.switch_to.window(current_window) driver.switch_to.window(driver.window_handles[0])
except (ValueError, NoSuchElementException): except (ValueError, NoSuchElementException):
continue continue
except TimeoutException: except TimeoutException:
print(f" Keine Personen-Tabelle im Album '{album['name']}' gefunden. Überspringe.") print(f" Keine Personen-Daten im Album '{album['name']}' gefunden. Überspringe.")
take_error_screenshot(driver, f"album_{album['name']}_error") take_error_screenshot(driver, f"album_{album['name']}_error")
continue continue