PINGDOM_CHECK

#ExtractSummit2026 The world's largest web scraping conference returns. Austin Oct 7–8 · Dublin Nov 10–11.

Register now
Data Services
Pricing
Login
Try Zyte APIContact Sales
  • Unblocking and Extraction

    Zyte API

    The ultimate API for web scraping. Avoid website bans and access a headless browser or AI Parsing

    Ban Handling

    Headless Browser

    AI Extraction

    Enterprise

    DocumentationSupport

    Hosting and Deployment

    Scrapy Cloud

    Run, monitor, and control your Scrapy spiders however you want to.

    Coding Agent Add-Ons

    Agentic Web Data

    Plugins that give coding agents the context to build production Scrapy projects. Starts with Claude Code.

  • Data Services
  • Pricing
  • Blog

    Learn

    Case Studies

    Webinars

    Videos

    White Papers

    Join our Community
    Web scraping APIs vs proxies: A head-to-head comparison
    Blog Post
    The seven habits of highly effective data teams
    Blog Post
  • Product and E-commerce

    From e-commerce and online marketplaces

    Data for AI

    Collect and structure web data to feed AI

    Job Posting

    From job boards and recruitment websites

    Real Estate

    From Listings portals and specialist websites

    News and Article

    From online publishers and news websites

    Search

    Search engine results page data (SERP)

    Social Media

    From social media platforms online

  • Meet Zyte

    Our story, people and values

    Contact us

    Get in touch

    Support

    Knowledge base and raise support tickets

    Terms and Policies

    Accept our terms and policies

    Open Source

    Our open source projects and contributions

    Web Data Compliance

    Guidelines and resources for compliant web data collection

    Join the team building the future of web data
    We're Hiring
    Trust Center
    Security, compliance & certifications
Login
Try Zyte APIContact Sales

Zyte Developers

Coding tools & hacks straight to your inbox

Become part of the community and receive a bi-weekly dosage of all things code.

Join us
    • Zyte Data
    • News & Articles
    • Search
    • Social Media
    • Product
    • Data for AI
    • Job Posting
    • Real Estate
    • Zyte API - Ban Handling
    • Zyte API - Headless Browser
    • Zyte API - AI Extraction
    • Web Scraping Copilot
    • Zyte API Enterprise
    • Scrapy Cloud
    • Solution Overview
    • Blog
    • Webinars
    • Case Studies
    • White Papers
    • Documentation
    • Web Scraping Maturity Self-Assesment
    • Web Data compliance
    • Meet Zyte
    • Jobs
    • Terms and Policies
    • Trust Center
    • Support
    • Contact us
    • Pricing
    • Do not sell
    • Cookie settings
    • Sign up
    • Talk to us
    • Cost estimator
Home
Blog
Zyte A.I. Automatic Extraction API | e-commerce & articles
Light
Dark

Zyte’s new AI-powered Automatic Extraction API for e-commerce & article extraction

Read Time
3 Mins
Posted on
April 9, 2019
Product Update
Today, we’re delighted to announce the launch of the beta program for Zyte's new AI-powered Automatic Extraction API for automated product and article extraction.
By
Ian Kerins
×

Try Zyte API

Zyte proxies and smart browser tech rolled into a single API.
Start FreeFind out more
Subscribe to our Blog

Zyte’s new AI-powered Automatic Extraction API for e-commerce & article extraction

Today, we’re delighted to announce the launch of the beta program for Zyte's new AI-powered Automatic Extraction API for automated product and article extraction.

After much development and refinement with alpha users, our team has refined this machine learning technology to the point that the data extraction engine is capable of automatically identifying common items on product and article web pages and extracting them without the need to develop and maintain individual web crawlers for each site.

Enabling developers to easily turn unstructured product and article pages into structured datasets at a scale, speed, and flexibility that is nearly impossible to achieve when manually developing spiders.

With the AI-enabled data extraction engine contained within the developer API, you now have the potential to extract product data from 100,000 e-commerce sites without having to write 100,000 custom spiders for each.

As result, today we’re delighted to announce the launch of the Zyte Automatic Extraction API's public beta.

Join the beta program today

If you are interested in e-commerce or media monitoring and would like to get early access to the Zyte Automatic Extraction API then be sure to sign up for the public beta program.

When you sign up for the beta program you will be issued an API key and documentation on how to use the API.

From there you are free to use the Zyte Automatic Extraction API for your own projects and retain ownership of the data you extracted when the beta program closes.

What's even better, the beta program is completely free. You will be assigned a daily/monthly request quota which you are free to consume as you wish.

The beta program will run until July 9th, so if you’d like to be involved then be sure to sign up today as places are limited.

How to use the API?

Once you’ve been approved to join the beta program and have received your API key, using the API is very straightforward.

Currently, the API has a single endpoint: https://developerapi.scrapinghub.com/v1/extract. A request is composed of one or more queries where each query contains a URL to extract from, and a page type that indicates what the extraction result should be (product or article).

Requests and responses are transmitted in JSON format over HTTPS. Authentication is performed using HTTP Basic Authentication where your API key is the username and the password is empty.

To make a request simply send a POST request to the API along with your API key, target URL, and pageType (either article or product):

Plain text
Copy to clipboard
Open code in new window
EnlighterJS 3 Syntax Highlighter
curl --verbose --user '[api key]':'' --header 'Content-Type: application/json' --data '[{"url": "https://blog.scrapinghub.com/gopro-study", "pageType": "article"}]' https://developerapi.scrapinghub.com/v1/extract
curl --verbose --user '[api key]':'' --header 'Content-Type: application/json' --data '[{"url": "https://blog.scrapinghub.com/gopro-study", "pageType": "article"}]' https://developerapi.scrapinghub.com/v1/extract
curl --verbose  --user '[api key]':''  --header 'Content-Type: application/json'  --data '[{"url": "https://blog.scrapinghub.com/gopro-study", "pageType": "article"}]'  https://developerapi.scrapinghub.com/v1/extract 

Or, in Python:

Plain text
Copy to clipboard
Open code in new window
EnlighterJS 3 Syntax Highlighter
import requests response = requests.post('https://developerapi.scrapinghub.com/v1/extract', auth=('[api key]', ''), json=[{'url': 'https://blog.scrapinghub.com/gopro-study', 'pageType': 'article'}]) print(response.json())
import requests response = requests.post('https://developerapi.scrapinghub.com/v1/extract', auth=('[api key]', ''), json=[{'url': 'https://blog.scrapinghub.com/gopro-study', 'pageType': 'article'}]) print(response.json())
import requests response = requests.post('https://developerapi.scrapinghub.com/v1/extract', auth=('[api key]', ''), json=[{'url': 'https://blog.scrapinghub.com/gopro-study', 'pageType': 'article'}]) print(response.json())

To facilitate query batching (see below) API responses are wrapped in a JSON array.

Here is an article from our blog that we want to extract structured data from:

article screenshot

And the response from the article extraction API:

Plain text
Copy to clipboard
Open code in new window
EnlighterJS 3 Syntax Highlighter
[ { "article": { "articleBody": "Unbeknownst to many, there is a data revolution happening in finance.nnIn their never ending search for alpha hedge funds and investment banks are increasingly turning to new alternative sources of data to give them an informational edge over the market.nnOn the 31st May, Scrapinghub got ...", "articleBodyRaw": "<span id="hs_cos_wrapper_post_body"" class=""hs_cos_wrapper hs_cos_wrapper_meta_field hs_cos_wrapper_type_rich_text"" data-hs-cos-general-type=""meta_field"" data-hs-cos-type=""rich_text""><p><span>Unbeknownst to many
[ { "article": { "articleBody": "Unbeknownst to many, there is a data revolution happening in finance.nnIn their never ending search for alpha hedge funds and investment banks are increasingly turning to new alternative sources of data to give them an informational edge over the market.nnOn the 31st May, Scrapinghub got ...", "articleBodyRaw": "<span id="hs_cos_wrapper_post_body"" class=""hs_cos_wrapper hs_cos_wrapper_meta_field hs_cos_wrapper_type_rich_text"" data-hs-cos-general-type=""meta_field"" data-hs-cos-type=""rich_text""><p><span>Unbeknownst to many
[ { "article": { "articleBody": "Unbeknownst to many, there is a data revolution happening in finance.nnIn their never ending search for alpha hedge funds and investment banks are increasingly turning to new alternative sources of data to give them an informational edge over the market.nnOn the 31st May, Scrapinghub got ...", "articleBodyRaw": "<span id="hs_cos_wrapper_post_body"" class=""hs_cos_wrapper hs_cos_wrapper_meta_field hs_cos_wrapper_type_rich_text"" data-hs-cos-general-type=""meta_field"" data-hs-cos-type=""rich_text""><p><span>Unbeknownst to many
automatic extraction

Try Automatic Extraction for free, or get in touch to discover custom data extraction solutions that work for your business. 

Zyte Automatic Extraction, powered by AI, makes data extraction easy and fast. This way you get back quick and reliable data in a structured format.

As a result you can make better decisions on how you want to improve your products and services, and grow your business. 

×

Try Zyte API

Zyte proxies and smart browser tech rolled into a single API.
Start FreeFind out more

Get the latest posts straight to your inbox

No matter what data type you're looking for, we've got you

G2.com

Capterra.com

Proxyway.com

EWDCI logoMost loved workplace certificateZyte rewardISO 27001 iconG2 rewardG2 rewardG2 reward

© Zyte Group Limited 2026