downloader.py

import requests
from bs4 import BeautifulSoup
import os
from PyPDF2 import PdfReader, PdfWriter
from rich.progress import track

def merge_pdfs(folder_path, output_filename):
    pdf_writer = PdfWriter()
    pdfs = [item for item in os.listdir(folder_path) if item.endswith('.pdf')]
    for item in track(pdfs, description="Merging..."):
        pdf_reader = PdfReader(os.path.join(folder_path, item))
        for page in pdf_reader.pages:
            pdf_writer.add_page(page)

    with open(output_filename, 'wb') as out:
        pdf_writer.write(out)

def download_pdfs(url, download_folder):
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')
    links = soup.find_all('a')

    pdf_links = [link for link in links if link.get('href') and link['href'].endswith('.pdf')]

    for link in track(pdf_links, description="Downloading..."):
        href = link['href']
        full_url = requests.compat.urljoin(url, href)
        filename = os.path.join(download_folder, href.split('/')[-1])
        with requests.get(full_url, stream=True) as r:
            r.raise_for_status()
            with open(filename, 'wb') as f:
                for chunk in r.iter_content(chunk_size=8192):
                    f.write(chunk)

# URL de la pàgina web
url = "https://www.ree.es/es/actividades/operacion-del-sistema-electrico/procedimientos-de-operacion"
# Carpeta on es desaran els PDFs
download_folder = "/tmp/pos"

#download_pdfs(url, download_folder)


# Nom de l'arxiu de sortida
output_filename = '/tmp/po_unified.pdf'

merge_pdfs(download_folder, output_filename)