Last active
April 25, 2018 19:37
-
-
Save inverse/30ae19ae7d7f4a1d358e32a01078df22 to your computer and use it in GitHub Desktop.
scraping
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
const puppeteer = require('puppeteer'); | |
(async () => { | |
const browser = await puppeteer.launch({args: ['--no-sandbox'], headless: true}); | |
const page = await browser.newPage(); | |
await page.goto('https://www.bibiblocksberg.de/hoerspiele'); | |
const loadMoreSelector = '.pager__item a'; | |
for(i = 0; i < 6; i++) { | |
await page.click(loadMoreSelector); | |
await page.waitFor(1000); | |
} | |
const songHrefSelector = '.views-field-field-ep-title a'; | |
const links = await page.$$eval(songHrefSelector, hrefs => hrefs.map((a) => { | |
return a.href | |
})); | |
for (i = 0; i < links.length; ++i) { | |
await page.goto(links[i]); | |
const src = await page.$eval('audio', e => e.src); | |
console.log(src); | |
} | |
await browser.close(); | |
})(); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment