pad-bis/pad-bis.py

# Flask application to serve the web pages
from flask import Flask, request, redirect, url_for, jsonify
from flask_cors import CORS

# Mediawiki client to interact with the Wiki
import mwclient

# BS to read the html table from the wiki
from bs4 import BeautifulSoup


# os and dotenv to store the mediawiki credentials in a safe place
import os
from dotenv import load_dotenv
from pathlib import Path

# datetime to work with dates
from datetime import datetime
import dateutil.parser


# load the mediawiki credentials from the shared folder
dotenv_path = Path("/var/www/.mw-credentials")
load_dotenv(dotenv_path=dotenv_path)


# prefix to add /soupboat/padliography to all the routes
# and to leave the @app.route() decorator more clean

class PrefixMiddleware(object):
    def __init__(self, app, prefix=""):
        self.app = app
        self.prefix = prefix

    def __call__(self, environ, start_response):

        if environ["PATH_INFO"].startswith(self.prefix):
            environ["PATH_INFO"] = environ["PATH_INFO"][len(self.prefix):]
            environ["SCRIPT_NAME"] = self.prefix
            return self.app(environ, start_response)
        else:
            start_response("404", [("Content-Type", "text/plain")])
            return ["This url does not belong to the app.".encode()]


# create flask application
app = Flask(__name__)
CORS(app)


# Url prefix for the soupboat
base_url = os.environ.get('BASE_URL', '')

# Page of the wiki with the pads
padliography = 'Padliography2'

# register the middleware to prefix all the requests with our base_url
app.wsgi_app = PrefixMiddleware(app.wsgi_app, prefix=base_url)


def add_pad(link, title, overview, categories, date):

    site = mwclient.Site('pzwiki.wdka.nl', path='/mw-mediadesign/')

    site.login(
        username=os.environ.get('MW_BOT'),
        password=os.environ.get('MW_KEY')
    )

    page = site.pages[padliography]
    text = page.text()

    # parsed_date = dateutil.parser.parse(date)
    # date = datetime.strftime(parsed_date, 'yyyy-mm-yyyy')

    new_row = f'|-\n| {link} || {title} || {overview} || {categories} || {date} \n|-\n' + '|}'

    text = text.replace('|}', new_row)

    page.edit(text, f'New pad in the {padliography}: {title}')


def get_pads():

    site = mwclient.Site('pzwiki.wdka.nl', path='/mw-mediadesign/')
    site.login(
        username=os.environ.get('MW_BOT'),
        password=os.environ.get('MW_KEY'),

    )

    html = site.api('parse', prop='text', page=padliography)
    table = BeautifulSoup(html['parse']['text']['*'], features="html.parser").find(
        "table", attrs={"class": "padliography"})

    headers = [header.text.lower().strip() for header in table.find_all('th')]
    pads = [
        {headers[i]: cell.text.rstrip('\n')
         for i, cell in enumerate(row.find_all('td'))}
        for row in table.find_all('tr')]
    pads = [pad for pad in pads if pad != {}]
    return pads


@app.route('/', methods=['GET', 'POST'])
def home():

    if request.method == 'POST':
        link = request.json.get('link', None)
        title = request.json.get('title', None)
        overview = request.json.get('overview', '')
        categories = request.json.get('categories', '')
        date = request.json.get('date', None)

        date = datetime.strftime(datetime.strptime(
            date, 'yyyy-mm-dd'), 'dd-mm-yyyy')
        add_pad(link, title, overview, categories, date)
        redirect(url_for('home'))

    response = {
        'page': padliography,
        'pads': get_pads()
    }

    return jsonify(response)


app.run(port=3147, debug=True)