Web Extraction

Extract structured data from URLs

Pull schema-shaped JSON out of one or many pages in a single call. An LLM maps each page onto your schema and/or prompt. Point at a single page, a list, or a crawl scope with a trailing /* wildcard; optionally let web search find extra source pages, return per-field confidence with the source passage behind each value, and merge everything into one deduplicated collection of entities. Charged per page that returns data.

POST

web

extract

curl --request POST \
  --url https://api.hydrafetch.com/v1/web/extract \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '
{
  "urls": [
    "https://example.com/products/widget",
    "https://example.com/products/*"
  ],
  "schema": {},
  "prompt": "Pull the product name, price in USD, and whether it is in stock.",
  "preferStructure": true,
  "enableWebSearch": true,
  "showSources": true,
  "showConfidence": true,
  "mergeEntities": true,
  "maxAge": 302400000
}
'

import requests

url = "https://api.hydrafetch.com/v1/web/extract"

payload = {
    "urls": ["https://example.com/products/widget", "https://example.com/products/*"],
    "schema": {},
    "prompt": "Pull the product name, price in USD, and whether it is in stock.",
    "preferStructure": True,
    "enableWebSearch": True,
    "showSources": True,
    "showConfidence": True,
    "mergeEntities": True,
    "maxAge": 302400000
}
headers = {
    "X-API-Key": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'X-API-Key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    urls: ['https://example.com/products/widget', 'https://example.com/products/*'],
    schema: {},
    prompt: 'Pull the product name, price in USD, and whether it is in stock.',
    preferStructure: true,
    enableWebSearch: true,
    showSources: true,
    showConfidence: true,
    mergeEntities: true,
    maxAge: 302400000
  })
};

fetch('https://api.hydrafetch.com/v1/web/extract', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.hydrafetch.com/v1/web/extract",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'urls' => [
        'https://example.com/products/widget',
        'https://example.com/products/*'
    ],
    'schema' => [
        
    ],
    'prompt' => 'Pull the product name, price in USD, and whether it is in stock.',
    'preferStructure' => true,
    'enableWebSearch' => true,
    'showSources' => true,
    'showConfidence' => true,
    'mergeEntities' => true,
    'maxAge' => 302400000
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "X-API-Key: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.hydrafetch.com/v1/web/extract"

	payload := strings.NewReader("{\n  \"urls\": [\n    \"https://example.com/products/widget\",\n    \"https://example.com/products/*\"\n  ],\n  \"schema\": {},\n  \"prompt\": \"Pull the product name, price in USD, and whether it is in stock.\",\n  \"preferStructure\": true,\n  \"enableWebSearch\": true,\n  \"showSources\": true,\n  \"showConfidence\": true,\n  \"mergeEntities\": true,\n  \"maxAge\": 302400000\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("X-API-Key", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.hydrafetch.com/v1/web/extract")
  .header("X-API-Key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"urls\": [\n    \"https://example.com/products/widget\",\n    \"https://example.com/products/*\"\n  ],\n  \"schema\": {},\n  \"prompt\": \"Pull the product name, price in USD, and whether it is in stock.\",\n  \"preferStructure\": true,\n  \"enableWebSearch\": true,\n  \"showSources\": true,\n  \"showConfidence\": true,\n  \"mergeEntities\": true,\n  \"maxAge\": 302400000\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.hydrafetch.com/v1/web/extract")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["X-API-Key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"urls\": [\n    \"https://example.com/products/widget\",\n    \"https://example.com/products/*\"\n  ],\n  \"schema\": {},\n  \"prompt\": \"Pull the product name, price in USD, and whether it is in stock.\",\n  \"preferStructure\": true,\n  \"enableWebSearch\": true,\n  \"showSources\": true,\n  \"showConfidence\": true,\n  \"mergeEntities\": true,\n  \"maxAge\": 302400000\n}"

response = http.request(request)
puts response.read_body

{
  "data": {
    "results": [
      {
        "url": "https://example.com/products/widget",
        "data": {},
        "error": null,
        "fields": {}
      }
    ],
    "sources": [
      "<string>"
    ],
    "collection": [
      {
        "data": {},
        "sources": [
          "<string>"
        ]
      }
    ]
  }
}

Authorizations

X-API-Key

string

header

required

Body

application/json

urls

string[]

required

The pages to extract from. Each must be an http(s) URL. A trailing /* marks a crawl scope: every page discovered under that path is extracted and merged into the result.

Maximum array length: 10

Example:

[
  "https://example.com/products/widget",
  "https://example.com/products/*"
]

schema

object

JSON Schema describing the shape you want back. Optional if prompt is given; when both are present the schema fixes the field names and types while the prompt guides what to pull.

prompt

string

Natural-language instruction for what to extract. Use with or instead of a schema.

Maximum string length: 2000

Example:

"Pull the product name, price in USD, and whether it is in stock."

preferStructure

boolean

Preserve document structure (headings, lists, tables) over prose density when reading the page — good for listing and catalog pages. Default off.

enableWebSearch

boolean

Pull in extra source pages by web-searching your prompt, to fill fields your URLs do not cover. Requires a prompt.

showSources

boolean

Return the concrete list of URLs that were actually extracted, after any wildcard and web-search expansion. Default off.

showConfidence

boolean

For each field, return a confidence score and the exact source passage the value was drawn from. Default off.

mergeEntities

boolean

Merge the per-page results into one deduplicated collection — one row per entity, with its contributing source URLs — instead of a separate result per page. Default off.

maxAge

number

Reuse a recent capture of each page if it is younger than this many milliseconds. Omit or 0 to always fetch fresh. Capped at 7 days.

Required range: 0 <= x <= 604800000

Response

200 - application/json

The extracted data.

data

object

required

Show child attributes

⌘I

Extract structured data from URLs

curl --request POST \
  --url https://api.hydrafetch.com/v1/web/extract \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '
{
  "urls": [
    "https://example.com/products/widget",
    "https://example.com/products/*"
  ],
  "schema": {},
  "prompt": "Pull the product name, price in USD, and whether it is in stock.",
  "preferStructure": true,
  "enableWebSearch": true,
  "showSources": true,
  "showConfidence": true,
  "mergeEntities": true,
  "maxAge": 302400000
}
'

import requests

url = "https://api.hydrafetch.com/v1/web/extract"

payload = {
    "urls": ["https://example.com/products/widget", "https://example.com/products/*"],
    "schema": {},
    "prompt": "Pull the product name, price in USD, and whether it is in stock.",
    "preferStructure": True,
    "enableWebSearch": True,
    "showSources": True,
    "showConfidence": True,
    "mergeEntities": True,
    "maxAge": 302400000
}
headers = {
    "X-API-Key": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'X-API-Key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    urls: ['https://example.com/products/widget', 'https://example.com/products/*'],
    schema: {},
    prompt: 'Pull the product name, price in USD, and whether it is in stock.',
    preferStructure: true,
    enableWebSearch: true,
    showSources: true,
    showConfidence: true,
    mergeEntities: true,
    maxAge: 302400000
  })
};

fetch('https://api.hydrafetch.com/v1/web/extract', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.hydrafetch.com/v1/web/extract",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'urls' => [
        'https://example.com/products/widget',
        'https://example.com/products/*'
    ],
    'schema' => [
        
    ],
    'prompt' => 'Pull the product name, price in USD, and whether it is in stock.',
    'preferStructure' => true,
    'enableWebSearch' => true,
    'showSources' => true,
    'showConfidence' => true,
    'mergeEntities' => true,
    'maxAge' => 302400000
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "X-API-Key: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.hydrafetch.com/v1/web/extract"

	payload := strings.NewReader("{\n  \"urls\": [\n    \"https://example.com/products/widget\",\n    \"https://example.com/products/*\"\n  ],\n  \"schema\": {},\n  \"prompt\": \"Pull the product name, price in USD, and whether it is in stock.\",\n  \"preferStructure\": true,\n  \"enableWebSearch\": true,\n  \"showSources\": true,\n  \"showConfidence\": true,\n  \"mergeEntities\": true,\n  \"maxAge\": 302400000\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("X-API-Key", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.hydrafetch.com/v1/web/extract")
  .header("X-API-Key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"urls\": [\n    \"https://example.com/products/widget\",\n    \"https://example.com/products/*\"\n  ],\n  \"schema\": {},\n  \"prompt\": \"Pull the product name, price in USD, and whether it is in stock.\",\n  \"preferStructure\": true,\n  \"enableWebSearch\": true,\n  \"showSources\": true,\n  \"showConfidence\": true,\n  \"mergeEntities\": true,\n  \"maxAge\": 302400000\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.hydrafetch.com/v1/web/extract")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["X-API-Key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"urls\": [\n    \"https://example.com/products/widget\",\n    \"https://example.com/products/*\"\n  ],\n  \"schema\": {},\n  \"prompt\": \"Pull the product name, price in USD, and whether it is in stock.\",\n  \"preferStructure\": true,\n  \"enableWebSearch\": true,\n  \"showSources\": true,\n  \"showConfidence\": true,\n  \"mergeEntities\": true,\n  \"maxAge\": 302400000\n}"

response = http.request(request)
puts response.read_body

{
  "data": {
    "results": [
      {
        "url": "https://example.com/products/widget",
        "data": {},
        "error": null,
        "fields": {}
      }
    ],
    "sources": [
      "<string>"
    ],
    "collection": [
      {
        "data": {},
        "sources": [
          "<string>"
        ]
      }
    ]
  }
}