Last active
October 29, 2024 15:51
-
-
Save RohanAwhad/41f42cec8acb0f21016f5b7adc519a21 to your computer and use it in GitHub Desktop.
Extract details from the search response in Apollo.io
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 extractRowData(rowElement) { | |
// Function to extract text or attribute from an element if it exists | |
function getElementData(selector, attribute = 'text') { | |
const element = rowElement.querySelector(selector); | |
if (!element) return null; | |
if (attribute === 'text') return element.textContent.trim(); | |
return element.getAttribute(attribute); | |
} | |
// Extracting the values based on their aria-label, role, or data-* attributes | |
const name = getElementData('a[data-to^="/people"]'); // Select the person link | |
const jobTitle = getElementData('span[class*="zp_xvo3G"]'); // Selecting based on class pattern | |
const company = getElementData('a[data-to^="/organizations"] span.zp_xvo3G'); | |
const companyLogoURL = getElementData('img', 'src'); // Extract image src | |
const linkedInProfileURL = getElementData('a[href*="linkedin.com"]', 'href'); // Extract LinkedIn URL | |
const location = getElementData('span[class*="zp_xvo3G"]'); // Similar span for location | |
const industry = getElementData('span.zp_CEZf9'); // Industry data based on specific class | |
const engagementCount = getElementData('span[data-count-size]', 'text'); // Count data | |
const skills = Array.from(rowElement.querySelectorAll('span.zp_CEZf9')).map(el => el.textContent).join(', '); // Gathering all skills | |
const profileURL = getElementData('a[data-to^="/people"]', 'href'); // Profile URL | |
const companyProfileURL = getElementData('a[data-to^="/organizations"]', 'href'); // Company Profile URL | |
// Creating a structured object | |
return { | |
name, | |
jobTitle, | |
company, | |
companyLogoURL, | |
linkedInProfileURL, | |
location, | |
industry, | |
engagementCount, | |
skills, | |
profileURL, | |
companyProfileURL | |
}; | |
} | |
async function extractDataAndPaginate() { | |
const results = []; | |
function extractDataFromPage() { | |
const data = []; | |
document.querySelectorAll('div[role="rowgroup"]')[1].querySelectorAll('div[role="row"]').forEach((row) => {data.push(extractRowData(row))}); | |
return data; | |
} | |
async function clickNextAndWaitForLoad() { | |
return new Promise((resolve, reject) => { | |
const nextPageButton = document.querySelector('button[aria-label="Next"]:not([disabled])'); | |
if (!nextPageButton) { | |
resolve('done'); | |
return; | |
} | |
// Trigger the click event for the next page | |
nextPageButton.click(); | |
setTimeout(() => { | |
console.log('loaded'); | |
resolve('loaded'); | |
}, 10000); // 10-second wait | |
}); | |
} | |
let status = ''; | |
do { | |
results.push(...extractDataFromPage()); | |
status = await clickNextAndWaitForLoad(); | |
} while (status !== 'done'); | |
return results; | |
} | |
function downloadResults(data, filename = 'results.json') { | |
const jsonString = JSON.stringify(data); | |
const blob = new Blob([jsonString], { type: 'application/json' }); | |
const link = document.createElement('a'); | |
link.href = URL.createObjectURL(blob); | |
link.download = filename; | |
document.body.appendChild(link); | |
link.click(); | |
document.body.removeChild(link); | |
} | |
/* | |
// Usage | |
extractDataAndPaginate().then((results) => { | |
console.log(results); | |
downloadResults(results) | |
}); | |
*/ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment