Zyte API

|AI Extraction

Turn pages into structured data instantly, like magic

End the pain of parsing. Let AI understand the page and extract the data for you.

Try free Read the docs

The hidden cost of writing parsers

Death by DOM

Identifying and testing XPath or CSS selectors is slow and repetitive.

Error-prone

Fragile selectors break when site markup changes.

Slow to scale

Scraping dozens of sites means never-ending maintenance.

Try AI Extraction

Pick your AI superpower

Three ways to turn any web page into valuable data.

1. Broad

Instant extraction from any page

Just get the data. One parameter is all you need. "pageContent": true is your key to instantly extract the main content of any page. No selectors in sight, no HTML to clean up – just clean, slim-line content, ready for LLMs or any use case.

Read the docs

Request

{
  "httpResponseBody": true,
  "pageContent": true,
}

def parse(self, response):
  http_response_body: bytes = response.body
  with open("http_response_body.html", "wb") as fp:
    fp.write(http_response_body)
    product = response.raw_api_response["product"]
    yield product
}

Response

{
  "headline": "Royal Victoria Infirmary",
  "itemMain": "Hospital NHS hospital Royal Victoria Infirmary Queen Victoria Road, Newcastle Upon Tyne, Tyne and Wear, NE1 4LP (0191) 233 6161 Provided and run by: The Newcastle upon Tyne Hospitals NHS Foundation Trust Overview Latest inspection summary All inspection reports and timeline Registration details Map and contact details Get alerts when we inspect Give feedback on care at this service About your care...",
  // ...,
  "itemMainXPath": "//*[@id=\"main-content-wrapper\"]",
  "metadata": {
    "dateDownloaded":"2025-08-12T16:14:22Z"
  }
}

2. Specialist

Rich, content-specific schemas

Zyte API uses machine learning models to identify and return standard data schema from a range of specific data types such as Product, Article, Job Posting, Search Engine.

Product

Instant extraction from ecommerce web pages.

Name
Price
Currency
Description
Images
Specifications

Read the docs

{
  "name": "StoneShoesbasket",
  "product": "Stoneshoes",
  "price": "149",
  "currency": "USD",
  "currencyRaw": "$",
  "regularPrice": "199.00",
  "availability": "InStock",
  "sku": "A123DK9823",
  "mpn": "code-123",
  "gtin": [],
  "brand": {},
  "breadcrumbs": [],
  "mainImage": {},
  "images": [],
  "description": "product description",
  "descriptionHtml": "&lt;article&gt;HTML description for Product ...",
  "aggregateRating": {},
  "color": "Red",
  "size": "XL",
  "weight": {},
  "material": "Metal, Plastic",
}

Article

Unlock the intelligence in news content.

Headline
Article body
Page number
URL
Date published
Date modified
Breadcrumbs

Read the docs

{"article": {
  "headline": "20 Years Ago, Steve Jobs Built the ‘Coolest Computer Ever.’ It Bombed",
  "articleBody": "This month marks the 20th anniversary of the Power Mac G4 Cube ...",
  "articleBodyHtml": "&lt;article&gt;&lt;p&gt;This month marks the 20th anniversary of the Power Mac G4 Cube, which debuted July 19, ...",
  "description": "This month marks the 20th anniversary of the Power Mac G4 Cube, which debuted July 19, 2000. It also marks the 19th anniversary of Apple’s",
  "datePublished": "2025-08-24T12:00:00",
  "datePublishedRaw": "12 hours ago",
  "dateModified": "2025-08-24T12:00:00",
  "dateModifiedRaw": "last modified 12 hours ago",
  "authors": [ { "name": "Martin J. Sally" } ],
  "inLanguage": "en",
  "url": "/mnt/data/59a41520-bc-.png"
}}

Job Posting

Gather key components from every job ad.

Job title
Base salary
Job location
Description
Employment type

Read the docs

{
	"url": "https://people.yummy.co.uk/job-search/restaurant-939@51.5061676,0.1050473/london/crew-member-thamesmead-939/pdx-ym-3ef1bf0e-0015-4d0f-8201-000246a1a831-77342",
	"statusCode": 200,
	"jobPosting": {
		"jobTitle": "Crew Member - Thamesmead 939",
		"datePublished": "2025-10-08T00:00:00",
		"datePublishedRaw": "2025-10-08",
		"description":
			"Yummy is one of the most recognised brands in the world, and the backbone of our brand is commitment to a set of…",
		"descriptionHtml":
			"&lt;article&gt;&lt;p&gt;Yummy is one of the most recognised brands in the ll.&lt;/p&gt;&lt;p&gt;Join us and you’ll become part of a team that works together to provide the best customer experience. If you’ve visited one of …&lt;/p&gt;&lt;/article&gt;",
		"employmentType": "Full Time",
		"hiringOrganization": { "name": "Yummy Careers UK" },
		"baseSalary": { "raw": "£9.52 - £12.26", "valueMax": "9.52", "currency": "GBP", "currencyRaw": "£" },
		"jobLocation": { "raw": "SE28 8RD UK" },
		"url": "https://people.yummy.co.uk/job-search/restaurant-939@51.5061676,0.1050473/london/crew-member-thamesmead-939/pdx-ym-3ef1bf0e-0015-4d0f-8201-000246a1a831-77342",
	},
	"metadata": { "probability": 0.6755940318107605, "dateDownloaded": "2025-10-09T09:39:58Z" },
	"httpResponseBody": null,
}

Search Engine

Extract and rank organic live results.

Organic results
URLs
Page number
Metadata

Read the docs

{
	"organicResults": [
		{
			"description": "Shop our most popular brands ... Blue Buffalo dog food ... American Journey dog food ... Hill’s Science Diet dog food ... Purina Pro Plan dog food.",
			"name": "Dog Food: Top Brands, Low Prices (Free Shipping)",
			"url": "https://www.chewy.com/b/food-332",
			"rank": 1,
			"displayedUrlText": "https://www.chewy.com › food-332",
		},
		{
			"description": "All Dog FoodOpen Farmhttps://openfarmpet.com › collections › dog-foodOpen Farmhttps://openfarmpet.com › collections › dog-foodExclusive offer: Get 20% off your next 2 Autoship orders at openfarmpet.com. Enter code V3G1EG9E4JNE at checkout to qualify. Maximum discount value per ...4.7 store rating (17K) · $10 to $33 · Free delivery over $50 · 30-day returns",
			"name": "All Dog Food",
			"url": "https://openfarmpet.com/collections/dog-food",
			"rank": 2,
			"displayedUrlText": "https://openfarmpet.com › collections › dog-food",
		},
	],
}

3. Magic

Conjure any field, on command

Our most powerful capability, custom attributes extraction, puts a scraping-tuned Large Language Model at your beck and call.

Extract mode

No more selectors. Use natural language to instruct Zyte API to find and return custom on-page data.

Example

{
  "pockets": {
    "type": "integer",
    "description": "What is the number of pockets in this garment?"
  }
}

Copy

Generate mode

Go beyond language-based extraction. Summarize, transform or translate captured data before it is even returned.

Example

{
  "datetime_posted": {
    "type": "string",
    "description": "the date when the article was created, in the following format: YYYY/MM/DD"
  }
}

Copy

Read the docs

See it in action

Add AI Extraction to your first request

Built to work the way you do

AI Extraction integrates seamlessly with your existing Zyte API workflows.

Plays well with Scrapy

Use AI Extraction directly inside your Scrapy spiders with no extra parsing logic — just one parameter in your request and the data arrives structured."

Domain-trained models

Specialized AI models for ecommerce products, articles, jobs, and search engine results ensure accuracy and efficiency.

Flexible schema

Get common fields by default, then customize the schema to fit your needs. Add or remove fields with either code or natural language prompts.

No-maintenance parsing

Forget fixing brittle selectors when sites change — our AI adapts automatically to evolving page structures.

Simple pricing that
scales with your needs

Explore transparent pricing designed to grow with your needs.

See our pricing plans

"Awards, five-star reviews and millions of happy customers"

The results are in: Zyte customers love our products. Check out these views and reviews on independent sites.

Always there

Zyte was able to offer the most simple and effective rotating proxy solution for us. It just works.

Aurélien Jemma

CEO at Liwango

Collaboration with Zyte has been easy and support was always there throughout our journey.

Ru Hickson

Data Engineer at Kinzen

It was literally 5 lines of code to get started with Smart Proxy Manager and see crawling success.

Oskar Bruening

CTO at Peek

Without Zyte Smart Proxy Manager our business is not successful.

Michael Raburn

Co-Founder of Bridge Below

Deploy in minutes

Quick to Integrate, Easy to Use.

Our headless browser power is easy to control using a simple API call.

from base64 import b64decode

import requests

api_response = requests.post(
  "https://api.zyte.com/v1/extract",
  auth=("YOUR_ZYTE_API_KEY", ""),
  json={
    "url": "https://toscrape.com",
    "httpResponseBody": True,
  },
)
body: bytes = b64decode(api_response.json()["httpResponseBody"])1

Copy

from scrapy import Spider

class ToScrapeSpider(Spider):
  name = "toscrape_com"
  start_urls = ["https://toscrape.com"]

  def parse(self, response):
    http_response_text: str = response.text1

Copy

See Docs Try Free

Turn pages into structured data instantly, like magic

The hidden cost of writing parsers

Death by DOM

Error-prone

Slow to scale

Pick your AI superpower

Instant extraction from any page

Rich, content-specific schemas

Product

Article

Job Posting

Search Engine

Conjure any field, on command

Extract mode

Generate mode

Add AI Extraction to your first request

Built to work the way you do

Plays well with Scrapy

Domain-trained models

Flexible schema

No-maintenance parsing

Simple pricing thatscales with your needs

"Awards, five-star reviews and millions of happy customers"

Quick to Integrate, Easy to Use.

Simple pricing that
scales with your needs