I am attempting to use Puppeteer and puppeteer-extra-plugin-recaptcha through Apify to solve the Recaptcha on a login page.
In time, I will want to do the full login. For now, I am attempting to do the Recaptcha solution, using Google's demo. puppeteer-extra-plugin-recaptcha taps up the 2captcha service via API key to do the solving.
Unfortunately, in my code, the important solveRecaptchas() throws an error:
TypeError: page.solveRecaptchas is not a function
Full error:
2021-10-17T10:04:54.502Z ERROR PuppeteerCrawler: handleRequestFunction failed, reclaiming failed request back to the list or queue {"url":"https://www.google.com/recaptcha/api2/demo","retryCount":1,"id":"ylMuptksDTSkKJl"}
2021-10-17T10:04:54.504Z TypeError: page.solveRecaptchas is not a function
2021-10-17T10:04:54.505Z at PuppeteerCrawler.handlePageFunction (/home/myuser/main.js:85:28)
2021-10-17T10:04:54.507Z at PuppeteerCrawler._handleRequestFunction (/home/myuser/node_modules/apify/build/crawlers/browser_crawler.js:324:52)
2021-10-17T10:04:54.509Z at processTicksAndRejections (node:internal/process/task_queues:96:5)
2021-10-17T10:04:54.511Z at async PuppeteerCrawler._runTaskFunction (/home/myuser/node_modules/apify/build/crawlers/basic_crawler.js:431:13)
2021-10-17T10:04:54.513Z at async AutoscaledPool._maybeRunTask (/home/myuser/node_modules/apify/build/autoscaling/autoscaled_pool.js:408:17)
My code:
/**************************************/
/* Setup requires */
/**************************************/
const Apify = require("apify");
const puppeteer = require("puppeteer-extra");
const PuppeteerExtraPluginRecaptcha = require("puppeteer-extra-plugin-recaptcha");
const StealthPlugin = require("puppeteer-extra-plugin-stealth");
// puppeteer.use(StealthPlugin()); // Should this be used?
/**************************************/
/* Use Recaptcha */
/**************************************/
function addPlugins() {
const captchaOptions = {
provider: {
id: "2captcha",
token: "my-2captcha-api-key",
},
solveInactiveChallenges: true,
visualFeedback: true,
};
puppeteer.use(PuppeteerExtraPluginRecaptcha(captchaOptions));
}
/**************************************/
/* Through Apify? */
/**************************************/
Apify.main(
async () => {
/**************************************/
/* Cue up URL */
/**************************************/
// Is this what to do and where to do it?
// cf. https://reposhub.com/nodejs/http/apifytech-apify-js.html
const requestQueue = await Apify.openRequestQueue();
await requestQueue.addRequest(
{
url: "https://www.google.com/recaptcha/api2/demo",
}
);
// const pseudoUrls = [new Apify.PseudoUrl('https://www.iana.org/[.*]')];
/**************************************/
/* Puppeteer Crawler */
/**************************************/
const crawler = new Apify.PuppeteerCrawler(
{
requestQueue,
launchContext: {
launcher: puppeteer,
launchOptions: {
devtools: false,
headless: false,
ignoreHTTPSErrors: true,
defaultViewport: { width: 1366, height: 768 },
timeout: 60 * 1000,
args: [
"--no-sandbox",
"--disable-web-security",
"--disable-setuid-sandbox",
"--disable-features=IsolateOrigins,site-per-process",
"--flag-switches-begin --disable-site-isolation-trials --flag-switches-end",
],
},
},
handlePageFunction: async ({ request, page }) => {
// ...some code
// Should URL be enqueued here, not above?
// solve captcha (if one exists)
await page.solveRecaptchas(); // https://github.com/berstend/puppeteer-extra/issues/184
// additional code
},
});
await crawler.run();
}
);
Possible causes I have read about include:
- Not defining details for the solving plugin - notably, the API key - but I seem to have done so.
- Something about different methods for solving in pre-existing browser pages (doesn't seem relevant?).
- Possible impact of iFrame. But, when I loop to get any child frames, I still get the error.
