Created
November 15, 2021 19:54
-
-
Save giehlman/18a6195280a69eebe3925d32d50876e3 to your computer and use it in GitHub Desktop.
Gelbe Seiten DOM Scraper
This file contains hidden or 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
// copy&paste in chrome dev tools console | |
var hits = document.getElementsByClassName("mod-Treffer"); | |
var all = []; | |
for (var i = 0; i < hits.length; i++) { | |
var res = getLineFromDomHit(hits[i]); | |
console.log(res); | |
all.push(res); | |
} | |
function getLineFromDomHit(hit) { | |
var title = hit.getElementsByTagName("h2")[0].textContent; | |
var cloned = hit.getElementsByTagName("address")[0].getElementsByTagName("p")[0].cloneNode(true); | |
cloned.getElementsByClassName("mod-AdresseKompakt__entfernung")[0].remove(); | |
var raw = cloned.innerText; | |
var clean = raw.replace(/\s\s+/g, ' ').trim(); | |
var street = clean.split(",")[0].trim(); | |
var postalcity = clean.split(",")[1].trim(); | |
return { | |
title:title, | |
street: street, | |
postalcity: postalcity | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment