Skip to content
Get started

Extract data

Do4U finds opening hours, prices, addresses, dates and contact details in a text or on a web page and returns them as clean lists, ready for a schema markup, an import or a spreadsheet. Next to every entry you see the passage it was read from. The AI proposes the entries; the code checks them: the passage must be in your source, every time, date, amount and house number must stand in it, texts such as names must appear in the source, times and dates must be valid, amounts are numbers with an ISO currency code. What is not in the source does not become data; it appears in a separate list. The values stay exactly as written in your source.

Try it now Pricing

Who it is for

For shop and website owners, agencies, data teams and support teams who want to turn text or a web page into structured data, for example for local business markup, a price table or a calendar import.

Typical uses

  • Turn the contact page of a business into opening hours, address and phone numbers
  • Collect the prices from a price list or a menu into a table
  • List the dates of an event page for a calendar import
  • Prepare the facts for FAQ and schema markup

Example

Input

Bella Pasta, 12 Main Street, 10115 Berlin, Germany. Open Monday to Friday 11:00–22:00, Saturday 12:00–23:00, Sunday closed. Pizza Margherita 9.50 EUR. Table booking: +49 30 1234567.

Result

Opening hours: Monday to Friday 11:00–22:00 (five entries), Saturday 12:00–23:00, Sunday closed Prices: Pizza Margherita – 9.50 EUR Address: 12 Main Street, 10115 Berlin, DE Contact: phone +49 30 1234567 Every entry shows the passage it was read from. Anything the text does not say is not in the result.

A fixed example, shortened. Real results are AI-generated: please check them.

Price and limits

Price
usually 1–3 credits
Available with
Free, With package
Input limit
One page with up to 300,000 characters of HTML

Privacy

Processed on our own servers in the EU (Poland). Inputs and results are deleted after 7 days (Free) or 30 days (packages), or right after you see the result if you choose not to store them. Images are deleted right after processing.

In the API

Tool name: extract_data. Create a job with POST /api/v1/jobs and fetch the result with GET /api/v1/jobs/{id}. You find your API key in your account.

curl -X POST https://do4u.eu/api/v1/jobs \
  -H "Authorization: Bearer d4u_…" -H "Content-Type: application/json" \
  -d '{"tool": "extract_data", "url": "https://example.com/"}'

Full API documentation →

Questions and answers

Can the AI invent opening hours or prices?

It can try, but the code does not let it through. Every entry has to quote the passage of your text it was read from. The code checks that the passage exists, that every time, date, amount and house number stands in it, that texts such as names and street names appear in the source, and that times and dates are valid. Entries that fail are not part of the data; they appear in a separate list.

In which format do I get the data?

Times as 24-hour HH:MM, dates in ISO 8601 (YYYY-MM-DD, or --MM-DD if the text names no year), weekdays by name and by ISO number 1 to 7, amounts as numbers with an ISO 4217 currency code, countries as ISO 3166 codes. You download everything as JSON, or each kind as CSV. Your browser creates the files.

Which languages work?

Text in any language. The values stay exactly as written in your source; only the short remarks come in the language of your text or in the one you choose. The code checks weekday and month names in 13 languages, and weekday names also in Japanese, Chinese and Korean (months are written as numbers there); in other languages an entry is marked as only partly checked.

Is my text stored?

Only as long as needed: 7 days on Free, 30 days with a package – or not at all if you choose not to store it. Processing happens on our own servers in the EU (Poland).

Can I use the result right away?

Results are AI-generated. Please read them before you publish or send them.

Related tools

  • FAQ and schema markup

    Writes FAQ entries from a page or support texts and builds valid JSON-LD for FAQPage, Organization, LocalBusiness and Product. The code checks the required fields and compares every detail with your source.

  • SEO title & description

    Three variants of page title and meta description, with the length checked.

  • Summarise

    Text or web address in, a short summary and the key points out.

All tools →