I have Puppeteer setup, and I was able get all of the rows using:
let rows = await page.$$eval('#myTable tr', row => row);
Now I want for each row to get "td's" and then get the innerText from those.
Basically I want to do this:
var tds = myRow.querySelectorAll("td");
Where myRow is a table row, with Puppeteer.
One way to achieve this is to use evaluate that first gets an array of all the TDs then returns the textContent of each TD:
const puppeteer = require('puppeteer');
const html = `
<html>
<body>
<table>
<tr><td>One</td><td>Two</td></tr>
<tr><td>Three</td><td>Four</td></tr>
</table>
</body>
</html>`;
(async () => {
const browser = await puppeteer.launch();
const page = await browser.newPage();
await page.goto(`data:text/html,${html}`);
const data = await page.evaluate(() => {
const tds = Array.from(document.querySelectorAll('table tr td'))
return tds.map(td => td.innerText)
});
//You will now have an array of strings
//[ 'One', 'Two', 'Three', 'Four' ]
console.log(data);
//One
console.log(data[0]);
await browser.close();
})();
You could also use something like:
const data = await page.$$eval('table tr td', tds => tds.map((td) => {
return td.innerText;
}));
//[ 'One', 'Two', 'Three', 'Four' ]
console.log(data);
You can also scrape the innerText into a two-dimensional array representing your table.
[
['A1', 'B1', 'C1'], // Row 1
['A2', 'B2', 'C2'], // Row 2
['A3', 'B3', 'C3'] // Row 3
]
const result = await page.$$eval('#example-table tr', rows => {
return Array.from(rows, row => {
const columns = row.querySelectorAll('td');
return Array.from(columns, column => column.innerText);
});
});
console.log(result[1][2]); // "C2"
const result = await page.evaluate(() => {
const rows = document.querySelectorAll('#example-table tr');
return Array.from(rows, row => {
const columns = row.querySelectorAll('td');
return Array.from(columns, column => column.innerText);
});
});
console.log(result[1][2]); // "C2"
A 2D array one-liner:
let results = await page.$eval('table tbody', tbody => [...tbody.rows].map(r => [...r.cells].map(c => c.innerText)))
