Created
October 23, 2022 09:08
-
-
Save brkydnc/bad6b7c55acd4836e70299ded1c53ce4 to your computer and use it in GitHub Desktop.
Scrap https://www.nufusune.com/ data.
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
import { DOMParser } from "https://deno.land/x/deno_dom/deno-dom-wasm.ts"; | |
const capitalize = str => str.charAt(0).toLocaleUpperCase("tr-TR") + str.slice(1).toLocaleLowerCase("tr-TR"); | |
const parser = new DOMParser(); | |
const fetchDocument = path => fetch("https://www.nufusune.com/" + path) | |
.then(response => response.text()) | |
.then(text => parser.parseFromString(text, "text/html")); | |
const indexOfDistricts = await fetchDocument("ilceler"); | |
const anchors = indexOfDistricts.querySelectorAll('td[data-label="İL ADI"] a'); | |
const promises = Array.from(anchors).map(async anchor => { | |
const href = anchor.getAttribute("href"); | |
const cityId = href.slice(0, -9); | |
const cityName = capitalize(anchor.textContent.slice(0, -9)); | |
const districts = await fetchDocument(href).then(async document => { | |
const anchors = document.querySelectorAll('td[data-label="İLÇELERİ"] a'); | |
const promises = Array.from(anchors).map(async anchor => { | |
const href = anchor.getAttribute("href"); | |
const districtId = href.slice(0, -(21 + cityName.length)); | |
const districtName = capitalize(anchor.textContent); | |
const neighborhoods = await fetchDocument(href).then(async document => { | |
const neighborhoods = Array.from(document.querySelectorAll("#ikiye1 li a")) | |
.map(anchor => capitalize(anchor.textContent.slice(0, -10))); | |
const villages = Array.from(document.querySelectorAll("#ikiye2 li a")) | |
.map(anchor => capitalize(anchor.textContent.slice(0, -5))); | |
return neighborhoods.concat(villages); | |
}); | |
return { id: districtId, name: districtName, neighborhoods } | |
}) | |
return await Promise.all(promises); | |
}); | |
return { id: cityId, name: cityName, districts } | |
}); | |
const data = await Promise.all(promises); | |
Deno.writeTextFile("./data.json", JSON.stringify(data)); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment