integration-custom/src/cwg/smalldate-parser.ts

/*
 * vertretungsplan.io custom crawler
 * Copyright (C) 2019 Jonas Lochmann
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU Affero General Public License as
 * published by the Free Software Foundation, version 3 of the
 * License.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU Affero General Public License for more details.
 *
 * You should have received a copy of the GNU Affero General Public License
 * along with this program.  If not, see <https://www.gnu.org/licenses/>.
 */

import * as cheerio from 'cheerio'
import * as request from 'request-promise-native'
import * as trimNewlines from 'trim-newlines'

const footer = '\n\nInformationen zum Projekt \"Campus Kastanienallee\" gibt es hier.'

function parseBody (body: string) {
  let $ = cheerio.load(body)
  $('br').replaceWith('\n')

  let content = $('div[id=content]').find('p').first()

  if (!content) {
    return []
  }

  let text = trimNewlines(content.text().trim()).trim()

  if (text.lastIndexOf(footer) === text.length - footer.length) {
    text = text.substring(0, text.length - footer.length)
  }

  return [{
    title: 'Wichtige Termine demnächst',
    content: text
  }]
}

export async function getSmallDates (url: string) {
  const body = await request(url)

  return parseBody(body)
}