You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 

51 lines
1.3 KiB

/*
* 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'
function parseBody (body: string) {
let $ = cheerio.load(body)
$('br').replaceWith('\n')
const content = $('div[id=content]')
if (!content) {
return []
}
const p = content.find('p')
if (!p) {
return []
}
const text = trimNewlines(p.text().trim()).trim()
return [{
title: 'langfristige Termine',
content: text
}]
}
export async function getDates (url: string) {
const body = await request(url)
return parseBody(body)
}