telerpot3654.py

telerpot3654.py

import requests
from bs4 import BeautifulSoup
import os
import time
import re

def download_biblioteca_sociologie():
    base_url = "https://b56hgf.ro/carti/"
    download_folder = "biblioteca_sociologie_pdfs"

    os.makedirs(download_folder, exist_ok=True)
    print(f"📁 Folder: {os.path.abspath(download_folder)}")

    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
        'Accept-Language': 'ro-RO,ro;q=0.9,en;q=0.8',
        'Referer': 'https://b56hgf.ro/',
    }

    session = requests.Session()
    session.headers.update(headers)

    # Pasul 1: Colectăm toate link-urile /download/ din pagina de cărți
    print("🔍 Scanare pagini de cărți...")

    download_pages = []
    page = 1

    while True:
        url = base_url if page == 1 else f"{base_url}page/{page}/"
        print(f"📄 Pagina {page}...")

        try:
            response = session.get(url, timeout=30)
            if response.status_code == 404:
                break
            response.raise_for_status()

            soup = BeautifulSoup(response.content, 'html.parser')
            found = 0

            for link in soup.find_all('a', href=True):
                href = link['href']
                if '/download/' in href and href not in download_pages:
                    if 'b56hgf.ro/download/' in href:
                        download_pages.append(href)
                        found += 1

            print(f"   Găsite: {found} cărți")
            if found == 0:
                break

            page += 1
            time.sleep(0.5)

        except Exception as e:
            print(f"   Eroare: {e}")
            break

    # Eliminăm duplicatele
    download_pages = list(set(download_pages))
    print(f"\n🎯 Total cărți unice: {len(download_pages)}")

    if not download_pages:
        return

    # Pasul 2: Pentru fiecare carte, extragem data-downloadurl și descărcăm
    print(f"\n⏬ Începe descărcarea...\n")

    success = 0
    failed = []

    for i, page_url in enumerate(download_pages, 1):
        try:
            # Extrage numele cărții din URL
            title = page_url.split('/download/')[-1].rstrip('/')[:80]
            filename = re.sub(r'[<>:"/\\|?*]', '_', title) + '.pdf'
            filepath = os.path.join(download_folder, filename)

            if os.path.exists(filepath) and os.path.getsize(filepath) > 10000:
                print(f"{i}. ✓ Există: {filename[:50]}...")
                success += 1
                continue

            print(f"{i}. 📖 {title[:50]}...")

            # Accesăm pagina de descărcare pentru a obține URL-ul real
            response = session.get(page_url, timeout=30)
            if response.status_code != 200:
                print(f"   ❌ Nu pot accesa pagina")
                failed.append(page_url)
                continue

            soup = BeautifulSoup(response.content, 'html.parser')

            # Căutăm data-downloadurl
            download_link = soup.find('a', {'data-downloadurl': True})

            if not download_link:
                # Alternativ, căutăm orice link cu wpdmdl
                for link in soup.find_all('a', href=True):
                    if 'wpdmdl=' in link.get('href', ''):
                        real_url = link['href']
                        break
                else:
                    print(f"   ❌ Nu găsesc link-ul de descărcare")
                    failed.append(page_url)
                    continue
            else:
                real_url = download_link['data-downloadurl']

            print(f"   ⬇️  Descarc...")

            # Descărcăm PDF-ul
            session.headers['Referer'] = page_url
            response = session.get(real_url, timeout=120, stream=True)

            if response.status_code == 200:
                content_type = response.headers.get('Content-Type', '')

                with open(filepath, 'wb') as f:
                    for chunk in response.iter_content(chunk_size=8192):
                        if chunk:
                            f.write(chunk)

                size = os.path.getsize(filepath)

                # Verificăm dacă e PDF valid
                with open(filepath, 'rb') as f:
                    header = f.read(5)

                if header == b'%PDF-' and size > 5000:
                    print(f"   ✅ OK ({size:,} bytes)")
                    success += 1
                else:
                    os.remove(filepath)
                    print(f"   ❌ Nu e PDF valid (Content-Type: {content_type})")
                    failed.append(page_url)
            else:
                print(f"   ❌ HTTP {response.status_code}")
                failed.append(page_url)

            time.sleep(2)

        except Exception as e:
            print(f"   ❌ Eroare: {e}")
            failed.append(page_url)

    print(f"\n{'='*50}")
    print(f"✅ Descărcate cu succes: {success}")
    print(f"❌ Eșuate: {len(failed)}")
    print(f"📁 {os.path.abspath(download_folder)}")

    if failed:
        print(f"\n📋 URL-uri eșuate:")
        for url in failed[:10]:
            print(f"   {url}")

if __name__ == "__main__":
    download_biblioteca_sociologie()