eficiencyFlask.py

from flask import Flask, request, jsonify
import requests
from urllib.parse import urlparse

app = Flask(__name__)

def get_highest_quality_images(images_data):
    quality_priority = ['2048', '638', '320']
    all_slides = images_data.get('all_slides', [])
    
    images_by_quality = {quality: [] for quality in quality_priority}
    
    for slide in all_slides:
        quality = slide.get('quality')
        if quality in images_by_quality:
            images_by_quality[quality] = slide.get('images', [])
    
    for quality in quality_priority:
        if images_by_quality[quality]:
            return images_by_quality[quality]
    
    return []

def extract_filename_from_url(url):
    path = urlparse(url).path
    path_parts = path.strip('/').split('/')
    
    if len(path_parts) >= 2:
        username = path_parts[0]
        title = path_parts[1]
        
        title = title.replace(':', '-').replace('?', '-').replace('/', '-')
        
        return f"{username}-{title}"
    return "downloaded_file"

@app.route('/slideshare', methods=['GET'])
def slideshare():
    url = request.args.get('url')
    filetype = request.args.get('filetype')
    
    if not url or not filetype:
        return jsonify({
            'error': 'Missing required parameters: url, filetype',
            'Example': f'{request.host}/slideshare?url=https://www.slideshare.net/StevanyStevany/materi-lengkap-tentang-power-point&filetype=pdf'
        }), 400

    session = requests.Session()  # Using session for connection pooling

    headers_get = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36',
    }

    headers_post = {
        'accept': '*/*',
        'accept-language': 'en-US,en;q=0.6',
        'content-type': 'application/json',
        'origin': 'https://slidesaver.app',
        'referer': 'https://slidesaver.app/',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36',
    }

    try:
        # Fetch images data from Slidesaver
        response_get = session.get(f'https://slidesaver.app/api/get-images?url={url}', headers=headers_get)
        response_get.raise_for_status()
        images_data = response_get.json()
        
        images = get_highest_quality_images(images_data)

        if not images:
            return jsonify({'error': 'No images found.'}), 404

        json_data = {
            'images': images,
            'type': filetype,
        }

        # Request download URL for the given filetype
        response_post = session.post('https://slidesaver.app/api/get-slide', headers=headers_post, json=json_data)
        response_post.raise_for_status()
        response_content = response_post.json()
        
        download_url = response_content.get('download_url')
        
        if not download_url:
            return jsonify({'error': 'Failed to get download URL from response.'}), 500

        filename_base = extract_filename_from_url(url)
        filename = f'{filename_base}.{filetype}'

        return jsonify({
            'download_url': download_url,
            'filename': filename
        })
    
    except requests.RequestException as e:
        return jsonify({'error': f'Request failed: {str(e)}'}), 500
    finally:
        session.close()  # Close the session

if __name__ == '__main__':
    app.run(debug=False, threaded=True)  # Enable threading for better concurrency

main_flask.py

from flask import Flask, request, jsonify
import requests
from urllib.parse import urlparse

app = Flask(__name__)

def get_highest_quality_images(images_data):
    quality_priority = ['2048', '638', '320']
    all_slides = images_data.get('all_slides', [])
    
    images_by_quality = {quality: [] for quality in quality_priority}
    
    for slide in all_slides:
        quality = slide.get('quality')
        if quality in images_by_quality:
            images_by_quality[quality] = slide.get('images', [])
    
    for quality in quality_priority:
        if images_by_quality[quality]:
            return images_by_quality[quality]
    
    return []

def extract_filename_from_url(url):
    path = urlparse(url).path
    path_parts = path.strip('/').split('/')
    
    if len(path_parts) >= 2:
        username = path_parts[0]
        title = path_parts[1]
        
        title = title.replace(':', '-').replace('?', '-').replace('/', '-')
        
        return f"{username}-{title}"
    else:
        return "downloaded_file"

@app.route('/slideshare', methods=['GET'])
def slideshare():
    url = request.args.get('url')
    filetype = request.args.get('filetype')
    
    if not url or not filetype:
        return jsonify({
            'error': 'Missing required parameters: url, filetype',
            'Example': f'{request.host}/slideshare?url=https://www.slideshare.net/StevanyStevany/materi-lengkap-tentang-power-point&filetype=pdf'
        }), 400

    headers_get = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36',
    }

    # Fetch images data from Slidesaver
    response_get = requests.get(f'https://slidesaver.app/api/get-images?url={url}', headers=headers_get)
    response_get.raise_for_status()
    images_data = response_get.json()
    
    images = get_highest_quality_images(images_data)

    if not images:
        return jsonify({'error': 'No images found.'}), 404

    headers_post = {
        'sec-fetch-mode': 'cors',
        'sec-fetch-site': 'same-origin',
        'sec-gpc': '1',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36',
    }

    json_data = {
        'images': images,
        'type': filetype,
    }

    response_post = requests.post('https://slidesaver.app/api/get-slide', headers=headers_post, json=json_data)
    response_post.raise_for_status()
    response_content = response_post.json()
    
    download_url = response_content.get('download_url')
    
    if not download_url:
        return jsonify({'error': 'Failed to get download URL from response.'}), 500

    filename_base = extract_filename_from_url(url)
    filename = f'{filename_base}.{filetype}'

    return jsonify({
        'download_url': download_url,
        'filename': filename
    })

if __name__ == '__main__':
    app.run(debug=False, threaded=True)

new_slideshare.py

import requests
from urllib.parse import urlparse

def get_highest_quality_images(images_data):
    # Define the priority order of image qualities
    quality_priority = ['2048', '638', '320']
    all_slides = images_data.get('all_slides', [])
    
    # Create a dictionary to store images by quality
    images_by_quality = {quality: [] for quality in quality_priority}
    
    for slide in all_slides:
        quality = slide.get('quality')
        if quality in images_by_quality:
            images_by_quality[quality] = slide.get('images', [])
    
    # Find the highest quality images based on the defined priority
    for quality in quality_priority:
        if images_by_quality[quality]:
            return images_by_quality[quality]
    
    # If no images found for any priority, return an empty list
    return []

def extract_filename_from_url(url):
    # Extract the username and title from the URL
    path = urlparse(url).path
    path_parts = path.strip('/').split('/')
    
    if len(path_parts) >= 2:
        username = path_parts[0]
        title = path_parts[1]
        
        # Replace any special characters in the title with dashes
        title = title.replace(':', '-').replace('?', '-').replace('/', '-')
        
        return f"{username}-{title}"
    else:
        return "downloaded_file"

def download_slide_share_file(url, filetype):
    headers_get = {
        'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8',
        'accept-language': 'en-US,en;q=0.6',
        'cache-control': 'max-age=0',
        'priority': 'u=0, i',
        'sec-ch-ua': '"Not)A;Brand";v="99", "Brave";v="127", "Chromium";v="127"',
        'sec-ch-ua-mobile': '?0',
        'sec-ch-ua-platform': '"Windows"',
        'sec-fetch-dest': 'document',
        'sec-fetch-mode': 'navigate',
        'sec-fetch-site': 'none',
        'sec-fetch-user': '?1',
        'sec-gpc': '1',
        'upgrade-insecure-requests': '1',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36',
    }

    # Step 1: Fetch images data from Slidesaver
    response_get = requests.get(
        f'https://slidesaver.app/api/get-images?url={url}',
        headers=headers_get,
    )
    response_get.raise_for_status()
    images_data = response_get.json()

    images = get_highest_quality_images(images_data)

    if not images:
        print('No images found.')
        return

    print("Retrieved images:", images)

    headers_post = {
        'accept': '*/*',
        'accept-language': 'en-US,en;q=0.6',
        'content-type': 'application/json',
        'origin': 'https://slidesaver.app',
        'priority': 'u=1, i',
        'referer': 'https://slidesaver.app/',
        'sec-ch-ua': '"Not)A;Brand";v="99", "Brave";v="127", "Chromium";v="127"',
        'sec-ch-ua-mobile': '?0',
        'sec-ch-ua-platform': '"Windows"',
        'sec-fetch-dest': 'empty',
        'sec-fetch-mode': 'cors',
        'sec-fetch-site': 'same-origin',
        'sec-gpc': '1',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36',
    }

    json_data = {
        'images': images,
        'type': filetype,
    }

    # Step 2: Request download URL for the given filetype
    response_post = requests.post(
        'https://slidesaver.app/api/get-slide', 
        headers=headers_post, 
        json=json_data
    )
    response_post.raise_for_status()
    response_content = response_post.json()
    
    # Extracting the download URL from the JSON response
    download_url = response_content.get('download_url')
    
    if not download_url:
        print('Failed to get download URL from response.')
        return

    print(f"Download URL: {download_url}")

    # Extract filename from the URL
    filename_base = extract_filename_from_url(url)
    filename = f'{filename_base}.{filetype}'

    # Step 3: Download the file
    response_download = requests.get(download_url)

    if response_download.status_code == 200:
        # Save the new file
        with open(filename, 'wb') as file:
            file.write(response_download.content)
        print(f'File downloaded and saved as {filename}')
    else:
        print(f'Failed to download the file. Status code: {response_download.status_code}')

# User inputs
url = input("Enter the SlideShare URL: ")  # Example: https://www.slideshare.net/StevanyStevany/materi-lengkap-tentang-power-point
filetype = input("Enter the filetype (pdf/pptx): ")

download_slide_share_file(url, filetype)

quart_main.py

from quart import Quart, request, jsonify
import aiohttp
from urllib.parse import urlparse

app = Quart(__name__)

def get_highest_quality_images(images_data):
    quality_priority = ['2048', '638', '320']
    all_slides = images_data.get('all_slides', [])
    
    images_by_quality = {quality: [] for quality in quality_priority}
    
    for slide in all_slides:
        quality = slide.get('quality')
        if quality in images_by_quality:
            images_by_quality[quality] = slide.get('images', [])
    
    for quality in quality_priority:
        if images_by_quality[quality]:
            return images_by_quality[quality]
    
    return []

def extract_filename_from_url(url):
    path = urlparse(url).path
    path_parts = path.strip('/').split('/')
    
    if len(path_parts) >= 2:
        username = path_parts[0]
        title = path_parts[1]
        title = title.replace(':', '-').replace('?', '-').replace('/', '-')
        return f"{username}-{title}"
    return "downloaded_file"

async def fetch_images_data(session, url):
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36',
    }
    async with session.get(f'https://slidesaver.app/api/get-images?url={url}', headers=headers, timeout=30) as response:
        response.raise_for_status()
        return await response.json()

async def request_download_url(session, images, filetype):
    headers = {
        'sec-fetch-mode': 'cors',
        'sec-fetch-site': 'same-origin',
        'sec-gpc': '1',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36',
    }
    json_data = {
        'images': images,
        'type': filetype,
    }
    async with session.post('https://slidesaver.app/api/get-slide', headers=headers, json=json_data, timeout=30) as response:
        response.raise_for_status()
        return await response.json()

@app.route('/slideshare', methods=['GET'])
async def slideshare():
    url = request.args.get('url')
    filetype = request.args.get('filetype')
    
    if not url or not filetype:
        return jsonify({
            'error': 'Missing required parameters: url, filetype',
            'Example': f'{request.host}/slideshare?url=https://www.slideshare.net/StevanyStevany/materi-lengkap-tentang-power-point&filetype=pdf'
        }), 400

    async with aiohttp.ClientSession() as session:
        try:
            images_data = await fetch_images_data(session, url)
            images = get_highest_quality_images(images_data)

            if not images:
                return jsonify({'error': 'No images found.'}), 404

            response_content = await request_download_url(session, images, filetype)
            download_url = response_content.get('download_url')

            if not download_url:
                return jsonify({'error': 'Failed to get download URL from response.'}), 500

            filename_base = extract_filename_from_url(url)
            filename = f'{filename_base}.{filetype}'

            return jsonify({
                'download_url': download_url,
                'filename': filename
            })

        except Exception as e:
            return jsonify({'error': str(e)}), 500

if __name__ == '__main__':
    app.run(debug=False)

slideshare.py

import requests
import os

url = input("Enter the SlideShare URL: ") # https://www.slideshare.net/StevanyStevany/materi-lengkap-tentang-power-point

filetype = input("Enter the filetype (pdf/pptx): ")

headers_get = {
    'accept': '*/*',
    'accept-language': 'id,en;q=0.9,en-GB;q=0.8,en-US;q=0.7,sv;q=0.6',
    'priority': 'u=1, i',
    'referer': 'https://slidesaver.app/',
    'sec-ch-ua': '"Chromium";v="124", "Microsoft Edge";v="124", "Not-A.Brand";v="99"',
    'sec-ch-ua-mobile': '?0',
    'sec-ch-ua-platform': '"Windows"',
    'sec-fetch-dest': 'empty',
    'sec-fetch-mode': 'cors',
    'sec-fetch-site': 'same-origin',
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36 Edg/124.0.0.0',
}

response_get = requests.get(
    f'https://slidesaver.app/api/get-images?url={url}',
    headers=headers_get,
)

images = response_get.json().get("images", [])

print("Retrieved images:", images)

headers_post = {
    'accept': '*/*',
    'accept-language': 'id,en;q=0.9,en-GB;q=0.8,en-US;q=0.7,sv;q=0.6',
    'content-type': 'application/json',
    'origin': 'https://slidesaver.app',
    'priority': 'u=1, i',
    'referer': 'https://slidesaver.app/',
    'sec-ch-ua': '"Chromium";v="124", "Microsoft Edge";v="124", "Not-A.Brand";v="99"',
    'sec-ch-ua-mobile': '?0',
    'sec-ch-ua-platform': '"Windows"',
    'sec-fetch-dest': 'empty',
    'sec-fetch-mode': 'cors',
    'sec-fetch-site': 'same-origin',
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36 Edg/124.0.0.0',
}

json_data = {
    'images': images,
    'type': filetype,
}

response_post = requests.post('https://slidesaver.app/api/get-slide', headers=headers_post, json=json_data)
response_content = response_post.content.decode('utf-8')
download_url = response_content.strip('"')

print(f"Download URL: {download_url}")

response_download = requests.get(download_url)

if response_download.status_code == 200:
    get_title_from_url = download_url.split('/')[-1].split('.')[0]
    filename = f'{get_title_from_url}.{filetype}'

    # filename = 'output.pptx'
    # # Check if the file exists and remove it
    # if os.path.exists(filename):
    #     os.remove(filename)
    #     print(f"Removed existing file: {filename}")
    
    # Save the new file
    with open(filename, 'wb') as file:
        file.write(response_download.content)
    print(f'File downloaded and saved as {filename}')
else:
    print(f'Failed to download the file. Status code: {response_download.status_code}')