Created
November 8, 2023 21:02
-
-
Save ecairol/f3cd58fca08196747599207501cfc171 to your computer and use it in GitHub Desktop.
Scrape Google paginated list
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
nodes = document.querySelectorAll('#center_col #search [role="heading"]'); | |
Array.from(nodes).forEach((node) => { | |
const title = node.textContent.slice(0, 100); | |
const publisher = node.previousSibling.innerText; | |
const link = node.closest('a').getAttribute('href'); | |
const date = new Date(node.parentNode.lastChild.innerText); | |
const year = date.getFullYear(); | |
const month = String(date.getMonth() + 1).padStart(2, '0'); | |
const day = String(date.getDate()).padStart(2, '0'); | |
formattedDate = `${year}-${month}-${day}`; | |
let db = sessionStorage.getItem('googlecontent') || "[]"; | |
db = JSON.parse(db); | |
db.push(` | |
<li>${formattedDate} | ${publisher} | <a href="${link}" target="_blank">${title}</a></li> | |
`); | |
sessionStorage.setItem( 'googlecontent', JSON.stringify(db) ); | |
} ); | |
// Final output (Save As from browser) | |
output = JSON.parse(sessionStorage.getItem('googlecontent')) | |
print = ''; output.forEach( i => { print += ' ' + i }); console.info(print); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment