Documentation

Online store: collect the complete catalog (JavaScript)

Collect a complete store catalog when products span several pages. Use the pattern to refresh a product and price list regularly.

Choose JavaScript, paste the complete source from this article and set the run parameters below. The source for this collection is ScrapingCourse. This walkthrough applies to the specified demonstration page.

Example settings

{
  "path": "/ecommerce/",
  "mode": "http",
  "expected": 188
}

path selects the page, mode selects an algorithm branch, and expected sets the control count for this example. It is not a plan limit. When the source dataset changes, check the expected count against it.

How the algorithm works

Start at /ecommerce/. The http mode selects ordinary HTML requests; this catalog does not require browser clicks.
Add each URL to visited before requesting it. If the next-page link points back to a processed page, stop instead of looping indefinitely.
Request fresh HTML and check the response. withoutCache() reads the current catalog rather than previously cached HTML.
Find products using two markup variants: .product-item and li.product. Product names and prices also have selectors for both card layouts.
Read the next-page link. absolutize resolves a relative address against the current page URL.
Finish when there is no next link, then compare the number of unique products with expected.

Products are processed by collect(html). Read the name first, skip empty names, and use the card link as the key, falling back to the name when necessary. seen prevents the same key being emitted twice. This matters when a later HTML read includes products already collected.

Details that matter

The HTTP branch allows at most 50 distinct pages. This protects the algorithm against incorrect links; the expected product count is a separate setting.

JavaScript details

JavaScript uses an asynchronous run function. Await network and browser actions; parsing already received HTML is synchronous. collect closes over the shared product-key Set. Its return value is the card count in the current HTML, not the number of new records.

Expected output

The configured demonstration dataset expects 188 unique records. The final check compares the actual unique key count with expected.

Field	Contents
`name`	Product name with leading and trailing whitespace removed.
`price`	Price converted from text to a number.
`image`	Image URL read from the card src attribute.

Complete scenario source

The source is shared by this collection. This example runs its http branch using the parameters above. Copy the complete block into the JavaScript editor; no fixed sign-in credentials or service keys need to be added.

async function run(ctx) {
  const origin = 'https://www.scrapingcourse.com';
  const path = String(ctx.param('path', '/pagination'));
  const mode = String(ctx.param('mode', 'http'));
  const auto = ctx.param('auto_captcha', true) !== false;
  const seen = new Set();
  const collect = (html) => {
    const dom = ctx.dom(html);
    for (const card of dom.qa('.product-item, li.product')) {
      const name = card.q('.product-name, .woocommerce-loop-product__title')?.text().trim() ?? '';
      const key = card.q('a')?.attr('href') ?? name;
      if (!name || seen.has(key)) continue;
      const price = ctx.text().money(card.q('.product-price, .price')?.text() ?? '');
      const image = card.q('img')?.attr('src') ?? '';
      seen.add(key);
      ctx.emit({name, price, image}, key);
    }
    return dom.qa('.product-item, li.product').length;
  };
  if (mode === 'http') {
    let url = origin + path;
    const visited = new Set();
    while (url && visited.size < 50) {
      if (visited.has(url)) throw new Error('Pagination returned an already processed page');
      visited.add(url);
      const response = await ctx.http().withoutCache().get(url, auto);
      if (!response.ok()) throw new Error('The source could not be opened: ' + response.status);
      const html = response.body;
      collect(html);
      const next = ctx.dom(html).attr('a[rel="next"], a.next.page-numbers', 'href');
      url = next ? ctx.url().absolutize(url, next) : null;
    }
    if (url) throw new Error('The pagination safety limit was reached');
  } else {
    const page = await ctx.browser().open(origin + path, ['*/ajax/products*'], {}, auto);
    try {
      if (mode === 'login') {
        const dom = ctx.dom(await page.content());
        const hint = dom.qa('p').map(node => node.text()).find(text => text.includes('Demo Credentials:')) ?? '';
        const password = hint.match(/Password:\s*([^\s|]+)/i)?.[1];
        let email = hint.match(/Email:\s*([^\s|]+@[^\s|]+)/i)?.[1];
        const encoded = dom.attr('[data-cfemail]', 'data-cfemail');
        if (!email && encoded && encoded.length > 2) {
          const key = parseInt(encoded.slice(0, 2), 16);
          email = '';
          for (let i = 2; i < encoded.length; i += 2) email += String.fromCharCode(parseInt(encoded.slice(i, i + 2), 16) ^ key);
        }
        if (!email || !password) throw new Error('The page does not contain demo credentials');
        await page.type('#email', email);
        await page.type('#password', password);
        await page.click('button[type="submit"]');
      }
      if (mode === 'challenge') {
        const text = (ctx.dom(await page.content()).text('body') ?? '').replace(/\s+/g, ' ');
        if (!/You (?:successfully )?bypassed|successfully bypassed|Congratulations/i.test(text)) throw new Error('The expected page content was not received');
        ctx.emit({name: path, passed: true}, path);
      } else {
        await page.waitFor('.product-name:not(:empty)', 15000);
        if (mode === 'button') {
          let complete = false;
          for (let i = 0; i < 30; i++) {
            const before = ctx.dom(await page.content());
            collect(await page.content());
            const button = before.q('#load-more-btn');
            if (!button || /display:\s*none/.test(button.attr('style') ?? '')) { complete = true; break; }
            const offset = button.attr('data-offset');
            const count = before.qa('.product-item').length;
            await page.click('#load-more-btn');
            const response = await page.waitForResponse('*offset=' + offset, 15000);
            if (!response || (Number(response.status) < 200 || Number(response.status) >= 300) || response.truncated || response.error) throw new Error('The next batch could not be loaded');
            if (String(response.body ?? '').trim() === '') { complete = true; break; }
            await page.waitFor('.product-item:nth-child(' + (count + 1) + ')');
          }
          if (!complete) throw new Error('The batch loading safety limit was reached');
        }
        if (mode === 'scroll') {
          let stable = 0;
          let previous = 0;
          for (let i = 0; i < 40 && stable < 3; i++) {
            await page.scroll(3, 400);
            const count = collect(await page.content());
            stable = count === previous ? stable + 1 : 0;
            previous = count;
          }
          if (stable < 3) throw new Error('The feed is still loading: increase the scroll limit');
        }
        collect(await page.content());
      }
    } finally { await page.close(); }
  }
  const expected = Number(ctx.param('expected', 1));
  if (mode !== 'challenge' && seen.size !== expected) throw new Error('Incomplete result: ' + seen.size + ' instead of ' + expected);
}