Skip to content

PyWebIO vs. Flask

Python3
  • Seit einigen Monaten, entwickle ich zum Lernen mit Flask. Davor habe ich schon mal PyWebIO eingesetzt. Beides sind Webframeworks. Was sind so meine Gedanken dazu.

    Code Beispiel PyWebIO

    @use_scope('backup')
        def backup():
            clear_scope()
            BackupList.load_json()
    
            # we build header and tdata for table
            tab_init = []
    
            # Print data from backups
            for count, value in enumerate(backups):
                # print("Control", count, backups[value].name)
    
                if count == 0:
                    tab_init.append(['No.', 'Backup name of the restic data backup', 'Actions'])
    
                if backups[value].init == "1":
                    button_list = {"label": 'Init', "value": 'Init', "color": 'primary', "disabled": True}
                    tab_init.append([count + 1,
                                     backups[count].name,
                                     put_buttons([
                                          button_list],
                                         onclick=partial(actions, count + 1))
                                     ])
                else:
                    button_list = {'label': 'Init', 'value': 'Init', 'color': 'primary', "disabled": False}
                    tab_init.append([count + 1,
                                     backups[count].name,
                                     put_buttons([
                                          button_list],
                                         onclick=partial(actions, count + 1))
                                     ])
    

    PyWebIO - Pro

    Contra

    • Nur für kleine Projekte geeignet
    • Kleine Community

    Code Beispiel Flask

    @home.route('/dashboard', methods=['GET'])
    @login_required
    def dashboard():
        refreshed = False
        refreshed = 'refreshed' in request.args
        # print("Refreshed", refreshed)
    
        data2 = all_data.get_all_stocks()
    
        data = sorted(data2.values(), key=lambda x: x['name_stock'], reverse=False)
    
        sums = []
        total_sum = all_data.get_total_sum('total_sum')
        sums.append(float(total_sum) if total_sum is not None else 0.0)
        old_total_sum = all_data.get_total_sum('old_total_sum')
        sums.append(float(old_total_sum) if total_sum is not None else 0.0)
        # print("SUMS", sums)
    
        return render_template('dashboard.html',
                               refreshed=refreshed,
                               data=data,
                               sums=sums,
                               active_menu='dashboard',
                               test_mode=config.TEST_MODE)
    

    Flask - Pro

    • Auch für große Projekte geeignet
    • Gute Dokumentation
    • Große aktive Community

    Contra

    • Leider muss man sich auch viel mit HTML, CSS & Javascript beschäftigen

    Fazit

    An PyWebIO hat mir sehr gut gefallen, das man so ziemlich alles mit Python Code machen kann, bis man an die Grenzen stößt. Mit Flask kann man wesentlich komplexere Webanwendungen bauen, dank Blueprints kann man das auch ordentlich strukturieren. Was mich sofort an Flask genervt hat ist, das man nun wieder HTML, CSS & Javascript drauf haben sollte. Aber, das ist halt auch der große Vorteil gegenüber PyWebIO, man ist wesentlich flexibler.

    Ich habe mir vorgenommen, mein vorhandenes Projekt ResticUI auf Flask umzubauen. Mal schauen, wie sich das so entwickelt. Mein aktuelles privates Flask Projekt (portfolio) ist mittlerweile gut ausgereift ist aber leider zu sehr auf meine privaten Anforderungen zugeschnitten, so dass ich es nicht public stellen kann. Evtl. baue ich das später mal entsprechend um.

    Happy Coding!

  • Mist, jetzt habe ich auch noch Streamlit gefunden. Jetzt geht mir langsam die Zeit aus...

  • 0 Stimmen
    1 Beiträge
    82 Aufrufe
    Niemand hat geantwortet
  • 0 Stimmen
    5 Beiträge
    144 Aufrufe
    FrankMF

    Hab ChatGPT nochmal nach der Installation auf einem Production Server befragt.

    ChatGPT

    Certainly! Here's a short example of the steps you can follow to deploy a Flask application on a production server using Nginx and Gunicorn:

    Prepare your server:

    Set up a server (e.g., using a cloud provider like AWS, DigitalOcean, or a dedicated server) and ensure it has a clean, up-to-date installation of a Linux distribution (e.g., Ubuntu or CentOS).

    Install required software:

    Install necessary software packages on your server. You'll need Python, pip (Python package manager), Nginx, and Gunicorn. You can use your distribution's package manager (e.g., apt for Ubuntu or yum for CentOS) to install these dependencies.

    Deploy your Flask application:

    Copy your Flask application code and any required dependencies to your server.

    Set up a virtual environment (optional but recommended):

    Create a virtual environment for your Flask application to isolate its dependencies. You can use venv or virtualenv for this purpose.

    Install Flask and any required Python packages within your virtual environment:

    pip install flask

    Test your Flask application:

    Ensure your Flask application runs correctly within your server's virtual environment.

    Configure Gunicorn:

    Create a Gunicorn configuration file (e.g., gunicorn_config.py) to specify the settings for running your Flask application. Here's a simple example: workers = 4 # Number of Gunicorn worker processes bind = '0.0.0.0:8000' # The address and port Gunicorn should listen on

    Start Gunicorn:

    Start Gunicorn with your Flask application: gunicorn -c gunicorn_config.py your_app:app

    Configure Nginx:

    Create an Nginx server block (often located in /etc/nginx/sites-available) to define how Nginx should handle incoming requests. Here's a simplified example: server { listen 80; server_name your_domain.com www.your_domain.com; location / { proxy_pass http://127.0.0.1:8000; # Pass requests to Gunicorn proxy_set_header Host $host; proxy_set_header X-Real-IP $remote_addr; } }

    Enable the Nginx server block and restart Nginx:

    sudo ln -s /etc/nginx/sites-available/your_config /etc/nginx/sites-enabled/ sudo nginx -t # Test Nginx configuration sudo systemctl restart nginx

    Configure your DNS:

    Point your domain name to your server's IP address.

    Secure your server (optional but recommended):

    Set up SSL/TLS certificates for your domain to enable HTTPS. You can use Let's Encrypt for free SSL certificates.

    Monitor your application:

    Set up monitoring tools and logs to keep track of your application's performance and troubleshoot any issues.

    These are the basic steps to deploy a Flask application on a production server with Nginx and Gunicorn. Please note that this is a simplified example, and there are many additional considerations, such as database configuration, security, and optimization, depending on your specific application and requirements. It's also important to keep your server and software up to date and follow security best practices to ensure the stability and security of your production environment.

    Das werde ich doch mal ausprobieren 😎

  • 0 Stimmen
    2 Beiträge
    425 Aufrufe
    FrankMF

    Ok, ich war leider nicht in der Lage den CODE-Server hinter einem Proxy zu installieren. Das CODE-Team scheint Docker zu lieben und das andere nur am Rande zu machen. Ohne Liebe 🙂

    Da ich extrem lange Ladezeiten hatte und die Software insgesamt nicht den Eindruck machte, das man das gerne produktiv auf einem Server nutzen möchte, habe ich den Server eben wieder gelöscht.

    Jetzt fehlt mir leider, die deepl.com Anbindung, aber das kann man ja auch über die Webseite nutzen.

    Ich nutze jetzt wieder den eingebauten CODE-Server, der eigentlich ein App-Image ist.

    28c41010-5ce1-4f7c-89d5-1c9b253011d0-grafik.png

    Der klare Vorteil, es läuft incl. Dokumenten Freigabe 🙂

    Nicht vergessen, unter Allow list for WOPI requests kommen die Server Adressen des Nextcloud-Webservers rein!

    c1a06c2c-86b5-4750-a062-7ba9d8dd8253-grafik.png

  • Pycharm & Docker

    Verschoben Linux
    1
    0 Stimmen
    1 Beiträge
    94 Aufrufe
    Niemand hat geantwortet
  • Restic UI - PyWebIO

    Python3
    3
    0 Stimmen
    3 Beiträge
    254 Aufrufe
    FrankMF

  • Quartz64 - dts File bearbeiten

    Angeheftet Verschoben Quartz64
    3
    0 Stimmen
    3 Beiträge
    268 Aufrufe
    FrankMF

    Ich weiß nicht, wonach ich gesucht habe, vermutlich nach

    apt install device-tree-compiler

    das gibt es im Manjaro Image nicht, es heißt ganz einfach dtc 😎 Also, ganz einfach mit

    pacman -S dtc

    installieren. Dann kann man sich diesen Umweg mit snapd sparen.

  • Debian 11 Bullseye released!

    Linux
    4
    0 Stimmen
    4 Beiträge
    283 Aufrufe
    FrankMF

    Mein Systemadmin auf der Arbeit meinte heute, angesprochen auf das Problem, läuft der Network-Manager? Ok, gute Frage...... Schauen wir mal.

    Ich bin mir leider nicht 100% sicher, ob er vor meinem Eingreifen lief, ich denke aber schon. Warum ich unsicher bin?

    root@debian:~# systemctl enable systemd-networkd.service Created symlink /etc/systemd/system/dbus-org.freedesktop.network1.service → /lib/systemd/system/systemd-networkd.service. Created symlink /etc/systemd/system/multi-user.target.wants/systemd-networkd.service → /lib/systemd/system/systemd-networkd.service. Created symlink /etc/systemd/system/sockets.target.wants/systemd-networkd.socket → /lib/systemd/system/systemd-networkd.socket. Created symlink /etc/systemd/system/network-online.target.wants/systemd-networkd-wait-online.service → /lib/systemd/system/systemd-networkd-wait-online.service.

    Ok, danach

    root@debian:~# systemctl start systemd-networkd.service root@debian:~# systemctl status systemd-networkd.service ● systemd-networkd.service - Network Service Loaded: loaded (/lib/systemd/system/systemd-networkd.service; enabled; ven> Active: active (running) since Tue 2021-08-17 17:36:38 CEST; 6s ago TriggeredBy: ● systemd-networkd.socket Docs: man:systemd-networkd.service(8) Main PID: 1288 (systemd-network) Status: "Processing requests..." Tasks: 1 (limit: 19087) Memory: 3.9M CPU: 39ms CGroup: /system.slice/systemd-networkd.service └─1288 /lib/systemd/systemd-networkd Aug 17 17:36:38 debian systemd[1]: Starting Network Service... Aug 17 17:36:38 debian systemd-networkd[1288]: enp25s0: Gained IPv6LL Aug 17 17:36:38 debian systemd-networkd[1288]: Enumeration completed Aug 17 17:36:38 debian systemd[1]: Started Network Service.

    Danach ging immer noch nix.

    root@debian:/etc/network# ^C root@debian:/etc/network# nmcli device show GENERAL.DEVICE: wlx7cdd907cbec2 GENERAL.TYPE: wifi GENERAL.HWADDR: BA:59:C0:76:C7:F5 GENERAL.MTU: 1500 GENERAL.STATE: 20 (nicht verfügbar) GENERAL.CONNECTION: -- GENERAL.CON-PATH: -- GENERAL.DEVICE: enp25s0 GENERAL.TYPE: ethernet GENERAL.HWADDR: 30:9C:23:60:C6:8E GENERAL.MTU: 1500 GENERAL.STATE: 10 (nicht verwaltet) GENERAL.CONNECTION: -- GENERAL.CON-PATH: -- WIRED-PROPERTIES.CARRIER: an IP4.ADDRESS[1]: 192.168.3.169/24 IP4.GATEWAY: 192.168.3.1 IP4.ROUTE[1]: dst = 192.168.3.0/24, nh = 0.0.0.0, mt = 0 IP4.ROUTE[2]: dst = 0.0.0.0/0, nh = 192.168.3.1, mt = 0 IP6.ADDRESS[1]: 2a02:908:1260:13bc:329c:23ff:xxxx:xxxx/64 IP6.ADDRESS[2]: fd8a:6ff:2880:0:329c:23ff:fe60:c68e/64 IP6.ADDRESS[3]: fe80::329c:23ff:fe60:c68e/64 IP6.GATEWAY: fe80::e4d3:f0ff:fe8f:2354 IP6.ROUTE[1]: dst = fe80::/64, nh = ::, mt = 256 IP6.ROUTE[2]: dst = ::/0, nh = fe80::e4d3:f0ff:fe8f:2354, mt = 1024 IP6.ROUTE[3]: dst = 2a02:908:xxxx:xxxx::/64, nh = ::, mt = 256 IP6.ROUTE[4]: dst = fd8a:6ff:2880::/64, nh = ::, mt = 256

    Jetzt hatte ich das erste Mal einen Ansatz, wonach ich suchen musste.

    GENERAL.STATE: 10 (nicht verwaltet)

    Etwas Suche im Netz und dann das

    nano /etc/NetworkManager/NetworkManager.conf

    Inhalt der Datei

    [main] plugins=ifupdown,keyfile [ifupdown] managed=false

    Das false in true geändert. Danach ein

    systemctl restart NetworkManager

    und ich konnte den Network-Manager auf dem Desktop benutzen!?!?!?

    Bildschirmfoto vom 2021-08-17 18-07-25.png

    Irgendwas ist da durcheinander im Bullseye 😳

  • ReactPHP auf einem ROCKPro64 testen

    Linux
    1
    0 Stimmen
    1 Beiträge
    174 Aufrufe
    Niemand hat geantwortet