teleport pro 4346.py

teleport pro 4346.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 selenium.common.exceptions import TimeoutException
from webdriver_manager.chrome import ChromeDriverManager
from urllib.parse import urljoin, unquote, urlparse
import os
import requests
from tqdm import tqdm
import re
import time

def setup_driver():
    chrome_options = Options()
    chrome_options.add_argument("--headless")
    service = Service(ChromeDriverManager().install())
    return webdriver.Chrome(service=service, options=chrome_options)

def is_valid_url(url):
    # Acceptă orice URL de pe uyuyuuy legat de secțiunea secolul-20
    parsed_url = urlparse(url)
    return (parsed_url.netloc == 'uyuyuuy' and
            'secolul-20' in parsed_url.path.lower() and
            not url.endswith('#'))

def clean_filename(filename):
    return re.sub(r'[<>:"/\\|?*]', '', filename)

def get_all_links(driver, base_url):
    print(f"Colectare link-uri de la: {base_url}")
    driver.get(base_url)
    try:
        WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.TAG_NAME, "body")))
        time.sleep(2)
    except TimeoutException:
        print(f"Timeout la încărcarea paginii: {base_url}")
        return []

    links = set()
    elements = driver.find_elements(By.TAG_NAME, "a")
    print(f"Elemente <a> găsite: {len(elements)}")

    for element in elements:
        href = element.get_attribute('href')
        if href and is_valid_url(href):
            print(f"Link găsit: {href}")
            links.add(href)

    print(f"Total link-uri valide găsite: {len(links)}")
    return links

def is_pdf_url(url):
    return url.lower().endswith('.pdf') or 'filename=' in url.lower()

def extract_filename_from_url(url):
    # Extrage numele fișierului din parametrul filename al URL-ului dl.asp
    if 'filename=' in url:
        filename = re.search(r'filename=([^&]+)', url)
        if filename:
            return unquote(filename.group(1))
    # Fallback pe ultima parte a URL-ului dacă nu există filename
    return unquote(url.split('/')[-1].split('?')[0])

def download_pdf(url, folder):
    headers = {
        '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',
        'Referer': 'https://uyuyuuy/?iopl',
        'Accept': 'application/pdf,*/*'
    }
    try:
        filename = extract_filename_from_url(url)
        filename = os.path.join(folder, clean_filename(filename))

        if os.path.exists(filename):
            print(f"Fișierul {filename} există deja. Skip descărcare.")
            return True

        print(f"Descărcare PDF: {url}")
        response = requests.get(url, headers=headers, stream=True, timeout=30)
        total_size = int(response.headers.get('content-length', 0))

        if response.status_code == 200:
            with open(filename, 'wb') as f, tqdm(
                desc=filename,
                total=total_size,
                unit='iB',
                unit_scale=True,
                unit_divisor=1024,
            ) as progress_bar:
                for data in response.iter_content(chunk_size=8192):
                    size = f.write(data)
                    progress_bar.update(size)
            print(f"✅ Descărcat cu succes: {filename}")
            return True
        else:
            print(f"❌ Nu s-a putut descărca PDF-ul de la {url}. Cod de status: {response.status_code}")
            return False
    except requests.RequestException as e:
        print(f"❌ Eroare la descărcarea {url}: {str(e)}")
        return False

def process_links(driver, base_url, folder):
    visited = set()
    to_visit = [base_url]
    downloaded_pdfs = set()

    specific_pdf = "https://uyuyuuy/reviste/secolul-20/dl.asp?filename=1961_nr-01-secolul-20-revista-de-literatura-universala.pdf"
    if is_pdf_url(specific_pdf):
        print(f"Încercare descărcare PDF specific: {specific_pdf}")
        download_pdf(specific_pdf, folder)
        downloaded_pdfs.add(specific_pdf)

    while to_visit:
        current_url = to_visit.pop(0)
        if current_url in visited:
            continue

        visited.add(current_url)
        print(f"\n📄 Procesare pagină: {current_url}")

        links = get_all_links(driver, current_url)

        pdf_links = [link for link in links if is_pdf_url(link)]
        other_links = [link for link in links if not is_pdf_url(link) and link not in visited]

        print(f"🔍 Link-uri PDF găsite: {len(pdf_links)}")
        for pdf in pdf_links:
            print(f"  - {pdf}")

        for link in pdf_links:
            if link not in downloaded_pdfs:
                success = download_pdf(link, folder)
                if success:
                    downloaded_pdfs.add(link)

        to_visit.extend(other_links)
        print(f"📊 Status: {len(downloaded_pdfs)} PDF-uri descărcate, {len(visited)} pagini vizitate, {len(to_visit)} pagini în așteptare")

        time.sleep(2)

def main():
    base_url = "https://uyuyuuy/?iopl"
    download_folder = r"g:\Downloads2"

    if not os.path.exists(download_folder):
        os.makedirs(download_folder)

    driver = setup_driver()
    try:
        print(f"🚀 Începere procesare de la URL-ul: {base_url}")
        process_links(driver, base_url, download_folder)
        print("✅ Procesul de căutare și descărcare a fost finalizat.")
        print(f"📁 Fișierele au fost salvate în: {download_folder}")
    except Exception as e:
        print(f"❌ Eroare neașteptată: {str(e)}")
    finally:
        driver.quit()

if __name__ == "__main__":
    main()