Download any manuals from https://www.manua.ls

manuals.py

# This script gathers all the pages of a manual and merges them into a PDF.
# You'll need to play a bit with inspect-element in order to figure out the format the correct url,
# but it should be easy to adapt it to any manual.
# This script is specifically for https://www.manua.ls/audi/q3-2018/manual.
# Their url format is https://www.manua.ls/viewer/{manual-id}/{page-number}/bg{page-number-hex}.png
# Example: https://www.manua.ls/viewer/668006/100/bg64.png
# Enjoy!
import requests
from tqdm import tqdm
from PIL import Image
from io import BytesIO
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter
from reportlab.lib.utils import ImageReader

def download_image(url):
    response = requests.get(url)
    if response.status_code == 200:
        return Image.open(BytesIO(response.content))
    else:
        print(f"Failed to download {url}")
        return None

def save_images_as_pdf(images, pdf_filename):
    c = canvas.Canvas(pdf_filename, pagesize=letter)
    width, height = letter
    for image in images:
        image_width, image_height = image.size
        aspect_ratio = image_width / image_height
        new_width = width
        new_height = width / aspect_ratio
        if new_height > height:
            new_height = height
            new_width = height * aspect_ratio

        # Convert PIL image to byte stream
        img_byte_arr = BytesIO()
        image.save(img_byte_arr, format='PNG')
        img_byte_arr.seek(0)

        # Draw image from byte stream
        c.drawImage(ImageReader(img_byte_arr), 0, height - new_height, width=new_width, height=new_height)
        c.showPage()
    c.save()

def main():
    base_url = "https://www.manua.ls/viewer/668006/"
    images = []
    for i in tqdm(range(1, 231)):  # Adjust the range as needed
        url = f"{base_url}{i}/bg{hex(i)[2:]}.png"
        image = download_image(url)
        if image:
            images.append(image)
    
    if images:
        save_images_as_pdf(images, "output.pdf")
        print("PDF created successfully")
    else:
        print("No images downloaded")

if __name__ == "__main__":
    main()