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()

webp-manuals.py

# Use this script for webp manuals
# example: https://www.manua.ls/growatt/min-3000-11400tl-xh-us/manual?p=1
# pip install selenium webdriver-manager pillow tqdm
# By default Firefox is used, but it's easy to adapt to chrome, see below
"""
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager

options = Options()
options.headless = True
options.add_argument("--window-size=1200,1600")
driver = webdriver.Chrome(options=options)
"""

from selenium import webdriver
from selenium.webdriver.firefox.options import Options
from selenium.webdriver.firefox.service import Service
from webdriver_manager.firefox import GeckoDriverManager
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from PIL import Image
from tqdm import tqdm
import io
import time

def get_screenshot(driver, url, consent):
    driver.get(url)

    # Wait for consent and give time for JS to load elements
    if consent:
        try:
            consent_button = WebDriverWait(driver, 3).until(
                EC.element_to_be_clickable((By.XPATH, '//button[@aria-label="Consent"]'))
            )
            consent_button.click()
        except:
            pass
    else:
        time.sleep(1)

    viewer_div = driver.find_element(By.ID, "viewer")

    # Save screenshot of just one element
    png = viewer_div.screenshot_as_png

    # Optional, intermediary save step
    # viewer_div.screenshot(f"{url[-1]}.png")
    return Image.open(io.BytesIO(png))

def main():
    options = Options()
    options.headless = True
    options.set_preference("layout.css.devPixelsPerPx", "1.5")
    driver = webdriver.Firefox(options=options)
 
    base_url = "https://www.manua.ls"
    images = []
    try:
        for i in tqdm(range(1, 82)): # number of pages 81
            url = f"{base_url}/growatt/min-3000-11400tl-xh-us/manual?p={i}" # manual name may differ
            img = get_screenshot(driver, url, consent=(i == 1))
            if img:
                images.append(img)
    finally:
        driver.quit()

    if images:
        images[0].save("output.pdf", save_all=True, append_images=images[1:])
        print("PDF created successfully")
    else:
        print("No screenshots taken")
    driver.quit()

if __name__ == "__main__":
    main()

Works beautifully. Thank you.

it seems they may have gotten more clever recently. the images download fine, but any text elements on the page are now part of separate div classes and so are not downloaded.

an example with lots of text elements: https://www.manua.ls/growatt/min-3000-11400tl-xh-us/manual?p=44

Another trick is to use https://www.manualslib.com/ instead which allows PDF downloading ;)

they dont have this 81 page manual

Hmm, oh yeah I didn't check for your specific case. I just solved mine 30min ago and wanted to share the tip but unfortunate for you :/

it seems they may have gotten more clever recently. the images download fine, but any text elements on the page are now part of separate div classes and so are not downloaded.

an example with lots of text elements: https://www.manua.ls/growatt/min-3000-11400tl-xh-us/manual?p=44

Apparently they can do that for webp manuals. The good news is that the url keeps increasing as a counter https://www.manua.ls/growatt/min-3000-11400tl-xh-us/manual?p=50, then ?p=51 and so on.
The quick and dirty option is to use a webdriver (eg selenium) and take screenshots of the "viewer" element. That would probably take some time, so you might want to grab a coffee or let it run overnight, until you let your computer do the work. I estimate about 30 min for this 80 page manual.

ill look into that, thanks.

I played a bit with https://gist.github.com/apetenchea/4df556a49f9a2543be877c31355b4164#file-webp-manuals-py
It should do the job, if you have the patience to wait for it.

thanks, ill mess with that

this is great. i made two changes:

viewer_div = driver.find_element(By.CLASS_NAME, "viewer-page")
doing it this way removes the viewer UI (the arrows still show. i know selenium can hide elements, but this is good enough for what i need)
and
options.add_argument("--headless")
the other headless method works for chrome but not FF.