How to scrape banking news data from Starling Bank using the Minexa.ai extension

Tracking every press release, product announcement, and leadership update from a fast-moving digital bank like Starling Bank by hand is the kind of task that sounds manageable until you actually try it at scale.

Starling Bank's news page at starlingbank.com/news/ publishes a steady stream of articles covering everything from AI feature launches and bond issuances to SME research and leadership appointments. If you need that data in a structured format for competitive monitoring, content research, or financial intelligence workflows, copying it manually row by row is not a realistic option.

This guide shows how to extract that data using Minexa.ai, a Chrome extension that detects, extracts, and exports structured data from any web page without requiring any code.

Watch the full tutorial first

Before walking through each step, here is the complete video walkthrough showing the extraction from start to finish on Starling Bank's news page.

https://www.youtube.com/watch?v=IL1Nj_RlY8A

Without a tool: what collecting this data actually looks like

Without a dedicated extraction tool, gathering Starling Bank news data means opening each page, reading through article cards, copying headlines and dates into a spreadsheet, and then repeating that across however many paginated pages exist. The news section spans multiple pages, so even a single collection run takes significant time. And if you want to track changes over time, the whole process starts again from scratch each time.

With Minexa.ai, the same task runs automatically across all pages in a single job, and the output lands in a structured spreadsheet or JSON file ready to use.

Step 1: open Minexa.ai and navigate to Starling Bank news

Start by opening the Minexa.ai home page and then navigating to starlingbank.com/news/ in your browser. Once the page has loaded, open the Minexa.ai Chrome extension.

The extension opens a popup confirming you are on the correct page. Click the confirmation button to proceed. Minexa.ai will immediately begin analysing the page structure.

Step 2: pagination detected automatically

Without a tool, tracking how many pages of news exist and navigating each one manually adds time to every collection run. Minexa.ai detects the pagination structure on its own. You can see the list of paginated pages it found and confirm before continuing.

After reviewing the detected pages, click Continue. The next screen shows pagination validation and your scraping options, including whether to scrape only the list or also follow each article link to extract detail page content.

Step 3: choose simple or advanced scraping mode

Minexa.ai gives you two modes. Simple mode works for most news listing pages and requires no configuration. Advanced mode gives you more control over which fields are prioritised. For Starling Bank's news page, simple mode captures all the key fields without any additional setup.

Once you select your mode, Minexa.ai highlights the repeating article card container on the page so you can confirm it has identified the right section before extraction begins.

Step 4: review extracted fields

After container confirmation, Minexa.ai shows a preview of all extracted data points. For Starling Bank's news page, these include the article headline, publication date, article link, image source path, and CSS layout classes per card.

You can also view generated code samples at this stage before completing the configuration.

What the extracted data looks like

Here is a sample of the structured output Minexa.ai produces from Starling Bank's news page:

[
  {
    "news_headline": "HM Treasury's AI Champions publish plan to accelerate safe AI adoption across UK financial services",
    "publish_date": "14th July 2026",
    "article_link": "/news/hm-treasury-s-ai-champions-publish-plan-to-accelerate-safe-ai-adoption-across-uk-financial-services",
    "image_src": "/images/500x500/cb3eb7a008/harriet-rees.png"
  },
  {
    "news_headline": "Starling Unveils Expense Cards and Team Access Tool for Small Business Customers",
    "publish_date": "9th July 2026",
    "article_link": "/news/starling-unveils-expense-cards-and-team-access-tool-for-small-business-customers",
    "image_src": "/images/680x440/1706359172/businessexpense-newsroom-680x440.png"
  },
  {
    "news_headline": "New AI feature detects romance scammers, investment heists and deepfake phishing attempts",
    "publish_date": "24th June 2026",
    "article_link": "/news/new-ai-feature-detects-romance-scammers",
    "image_src": "/images/1920x1080/72a0ecd430/scam-intelligence-logo.png"
  }
]

The article_link field returns a relative path per article, which you can combine with the base domain to construct a direct URL to any individual news page. The publish_date field gives a readable date string per row, making chronological sorting straightforward. The image_src field includes the resolution-specific path, so downstream rendering does not require any additional asset lookups.

Step 5: run the job and export

After completing configuration, the job summary screen shows your schedule and export options. You can run the job immediately or set it to repeat on a daily or weekly basis so new Starling Bank articles are captured automatically without any manual intervention.

Once the job runs, the data appears in a structured table inside Minexa.ai. From there you can export directly to Excel, Google Sheets, or JSON.

If you want to start extracting Starling Bank news data today, the Minexa.ai extension is available to download here. The setup for this type of page takes a few minutes and the scraper can be reused on any future run without repeating configuration.

For a broader introduction to the extraction workflow, the guide on scraping catalogue data without code covers similar concepts across a different content type.