Created
May 31, 2024 01:00
-
-
Save aaronfay/bbfcf1037eeb1b4aa5032d5d6021cebf to your computer and use it in GitHub Desktop.
Scraping reviews from capterra
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 downloadFileWithContents(filename, fileContents) { | |
const blob = new Blob([fileContents], {type: 'text'}); | |
const elem = window.document.createElement('a'); | |
elem.href = window.URL.createObjectURL(blob); | |
elem.download = filename; | |
document.body.appendChild(elem); | |
elem.click(); | |
document.body.removeChild(elem); | |
} | |
function getRows() { | |
allCards = document.querySelectorAll('.review-card') | |
return Array.from(allCards).map(card => { | |
first = card.querySelector('p:nth-of-type(1)').innerText | |
index = 0 | |
comments = '' | |
if (first.startsWith('Comments:')) { | |
index = 1 | |
comments = card.querySelector(`p:nth-of-type(1)`) | |
} | |
cons = card.querySelector(`p:nth-of-type(${index + 4})`) | |
comments = comments ? comments.innerText : '' | |
cons = cons ? "" + cons.innerText : '' | |
comments = comments.trim().replace('"', '\"').replace(/\"/g, "'").replace(/(?:\r\n|\r|\n)/g, ' ') | |
cons = cons.trim().replace('"', '\"').replace(/\"/g, "'").replace(/(?:\r\n|\r|\n)/g, ' ') | |
return `${comments}|${cons}` | |
}) | |
} | |
downloadFileWithContents('mycsv.csv', getRows().join('\n')) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment