Last active
May 31, 2022 12:06
-
-
Save andersonbosa/13684328cf2b86c9d2df4108e3de515b to your computer and use it in GitHub Desktop.
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 parseResponseToDOM (html) { | |
var parser = new DOMParser() | |
var dom = parser.parseFromString(html, "text/html") | |
return {parser, dom} | |
} | |
async function getDomFromUrl (url) { | |
return fetch(url) | |
.then(resp => resp.text()) | |
.then(parseResponseToDOM) | |
.catch(err => console.log(err)) | |
} | |
const pensadorDom = await getDomFromUrl('https://www.pensador.com/poemas_de_amor/1/') | |
const phraseBlocks = Array.from(pensadorDom.dom.querySelectorAll('[id*=phrase-block]')) | |
function getInnerText (domItem, selector='') { | |
if (!selector) { | |
return domItem.innerText.trim() | |
} | |
const item = domItem.querySelector(selector) | |
return item && item.innerText.trim() | |
} | |
} | |
function parsePhrases (domItem) { | |
return { | |
author: getInnerText(domItem, 'span.autor').replace(/\n/g, ''), | |
phrase: getInnerText(domItem, 'p.frase') | |
} | |
} | |
const parsedPhrases = phraseBlocks.map(parsePhrases) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment