54756yg.py

54756yg.py

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from webdriver_manager.chrome import ChromeDriverManager
import os
import time
import urllib.request

def setup_driver():
    chrome_options = Options()
    chrome_options.add_argument("--headless")
    chrome_options.add_argument("--disable-gpu")
    chrome_options.add_argument("--no-sandbox")
    chrome_options.add_argument("user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36")
    service = Service(ChromeDriverManager().install())
    return webdriver.Chrome(service=service, options=chrome_options)

def download_images(url, folder):
    if not os.path.exists(folder):
        os.makedirs(folder)

    driver = setup_driver()
    try:
        driver.get(url)
        WebDriverWait(driver, 20).until(EC.presence_of_element_located((By.CLASS_NAME, "thumbnail")))
        time.sleep(5)

        thumbnails = driver.find_elements(By.CLASS_NAME, "thumbnail")
        print(f"Găsite {len(thumbnails)} miniaturi.")

        for i, thumbnail in enumerate(thumbnails, 1):
            try:
                img = thumbnail.find_element(By.TAG_NAME, "img")
                img_url = img.get_attribute("src")
                if img_url:
                    filename = os.path.join(folder, f"page_{i}.jpg")
                    print(f"Descărcare imagine: {img_url} -> {filename}")
                    urllib.request.urlretrieve(img_url, filename)
                    print(f"✅ Descărcat: {filename}")
            except Exception as e:
                print(f"❌ Eroare la descărcarea imaginii {i}: {str(e)}")

    except Exception as e:
        print(f"❌ Eroare la încărcarea paginii: {str(e)}")
    finally:
        driver.quit()

def main():
    base_url = "https://adt.4r4754y.net/ro/view/RevistaDeChimie_1956_1/?pg=0&layout=s"
    download_folder = r"g:\Downloads2\ArcanumImages"

    print(f"🚀 Începere procesare de la URL-ul: {base_url}")
    download_images(base_url, download_folder)
    print(f"📁 Imaginile au fost salvate în: {download_folder}")

if __name__ == "__main__":
    main()