Last active
September 30, 2018 15:19
-
-
Save silkimen/aec783594d6c07d529249c023b574c78 to your computer and use it in GitHub Desktop.
Crawling offerings in interhyp customer portal
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
(function() { | |
const whitelistedIndexes = [0, 10, 12, 14, 16, 18, 20, 22, 24]; | |
const getCsvLine = row => row.join(';'); | |
const removeRedundancy = value => value.replace('Darlehensbetrag ', ''); | |
const getValue = element => `"${element.innerHTML}"`; | |
const isWhitelisted = (element, index) => whitelistedIndexes.includes(index); | |
const getTag = row => Array | |
.from( | |
row.getElementsByTagName('h3').length ? row.getElementsByTagName('h3') : | |
row.getElementsByTagName('div').length ? row.getElementsByTagName('div') : | |
row.getElementsByTagName('span') | |
); | |
const getRows = container => Array | |
.from(container.getElementsByClassName('data-row')) | |
.map(getTag) | |
.flat() | |
.filter(isWhitelisted) | |
.map(getValue) | |
.map(removeRedundancy); | |
const getContainers = () => Array | |
.from(document.getElementsByClassName('ehyp-package-bids-bid')); | |
const getCsvData = () => getContainers() | |
.map(getRows) | |
.map(getCsvLine); | |
const csvHeader = '"Anbieter";"Kreditsumme";"Effektiver Zins";"Monatsrate";"Sollzinsbindung";"Tilgung";"Restschuld";"Bereitstellungszinsfreie Zeit";"Sondertilgung"\n'; | |
return csvHeader + getCsvData().join('\n'); | |
}()); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment