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

Letzte Version war Super

Browse Source 
Hat gut funktioniert, jetzt versuchen wir noch die Pagination zu ergänzen
This commit is contained in:
Floke
2025-07-16 18:51:29 +00:00
parent 6b1b2d441c
commit 265f32181d
1 changed files with 65 additions and 53 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
scrape_fotograf.py
View File

@@ -2,6 +2,7 @@ import json
import os import os
import time import time
import csv import csv
import math
from datetime import datetime from datetime import datetime
from selenium import webdriver from selenium import webdriver
from selenium.webdriver.chrome.options import Options from selenium.webdriver.chrome.options import Options
@@ -16,7 +17,7 @@ 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 --- # --- Selektoren (FINALE, VOLLSTÄNDIGE VERSION) ---
SELECTORS = { SELECTORS = {
"cookie_accept_button": "#CybotCookiebotDialogBodyLevelButtonLevelOptinAllowAll", "cookie_accept_button": "#CybotCookiebotDialogBodyLevelButtonLevelOptinAllowAll",
"login_user": "#login-email", "login_user": "#login-email",
@@ -25,6 +26,8 @@ SELECTORS = {
"job_name": "h1", "job_name": "h1",
"album_overview_rows": "//table/tbody/tr", "album_overview_rows": "//table/tbody/tr",
"album_overview_link": ".//td[2]//a", "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_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",
@@ -100,7 +103,7 @@ def process_full_job(driver, job_url):
try: try:
driver.get(job_url) driver.get(job_url)
except InvalidArgumentException: except InvalidArgumentException:
print(f"!!! FEHLER: Die URL '{job_url}' wurde von Selenium als ungültig angesehen. Bitte prüfen Sie die Eingabe.") print(f"!!! FEHLER: Die URL '{job_url}' wurde von Selenium als ungültig angesehen.")
return [] return []
try: try:
@@ -137,8 +140,21 @@ 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:
# 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).")
for page_num in range(1, num_pages + 1):
current_page_url = album['url']
if page_num > 1:
current_page_url += f"?page_guest_accesses={page_num}"
print(f" Verarbeite Seite {page_num}...")
driver.get(current_page_url)
num_persons = len(wait.until(EC.presence_of_all_elements_located((By.XPATH, SELECTORS["person_rows"])))) num_persons = len(wait.until(EC.presence_of_all_elements_located((By.XPATH, SELECTORS["person_rows"]))))
print(f"{num_persons} Personen in diesem Album gefunden.") print(f" {num_persons} Personen auf dieser Seite gefunden.")
for i in range(num_persons): for i in range(num_persons):
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"])))
@@ -176,19 +192,16 @@ def process_full_job(driver, job_url):
break break
except StaleElementReferenceException: except StaleElementReferenceException:
print(f" Timing-Fehler (StaleElement), Versuch {attempt + 1}/3. Warte kurz...") print(f" Timing-Fehler, Versuch {attempt + 1}/3...")
time.sleep(1) time.sleep(1)
if attempt == 2: if attempt == 2: raise
print(" Fehler war persistent, überspringe diese Person.")
take_error_screenshot(driver, f"stale_error_{vorname}")
except TimeoutException: except TimeoutException:
print(f" Timeout beim Warten auf Details für '{vorname}'. Überspringe.") print(f" Timeout beim Warten auf Details für '{vorname}'.")
take_error_screenshot(driver, f"timeout_error_{vorname}") take_error_screenshot(driver, f"timeout_error_{vorname}")
break break
print(f" Kehre zurück zur Album-Übersicht '{album['name']}'...") print(f" Kehre zurück zur Album-Seite {page_num}...")
driver.get(album['url']) driver.get(current_page_url)
wait.until(EC.presence_of_element_located((By.XPATH, SELECTORS["person_rows"]))) wait.until(EC.presence_of_element_located((By.XPATH, SELECTORS["person_rows"])))
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.")
@@ -231,7 +244,6 @@ def main():
credentials = get_profile_choice() credentials = get_profile_choice()
if not credentials: return if not credentials: return
# GEÄNDERT: URL-Eingabe wird explizit von "Bracketed Paste" Codes bereinigt
job_url_raw = input("Bitte gib die URL des zu bearbeitenden Fotoauftrags ein (Einstellungs-Seite): ") job_url_raw = input("Bitte gib die URL des zu bearbeitenden Fotoauftrags ein (Einstellungs-Seite): ")
job_url_cleaned = job_url_raw.replace("\x1b[200~", "").replace("\x1b[201~", "") job_url_cleaned = job_url_raw.replace("\x1b[200~", "").replace("\x1b[201~", "")
job_url = job_url_cleaned.strip() job_url = job_url_cleaned.strip()