Scrape a URL

JSON

{
  "url": "https://example.com",
  "formats": {
    "html": true
  }
}

curl https://api.context.dev/v1/web/scrape \
  -H "Authorization: Bearer $CONTEXT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "url": "https://example.com",
  "formats": {
    "html": true
  }
}'

import requests

url = "https://api.context.dev/v1/web/scrape"

payload = {
    "url": "https://example.com",
    "formats": { "html": True }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({url: 'https://example.com', formats: {html: true}})
};

fetch('https://api.context.dev/v1/web/scrape', 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.context.dev/v1/web/scrape",
  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([
    'url' => 'https://example.com',
    'formats' => [
        'html' => true
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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.context.dev/v1/web/scrape"

	payload := strings.NewReader("{\n  \"url\": \"https://example.com\",\n  \"formats\": {\n    \"html\": true\n  }\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	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.context.dev/v1/web/scrape")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"url\": \"https://example.com\",\n  \"formats\": {\n    \"html\": true\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.context.dev/v1/web/scrape")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"url\": \"https://example.com\",\n  \"formats\": {\n    \"html\": true\n  }\n}"

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

{
  "url": "https://example.com/",
  "isPartial": true,
  "html": {
    "requested": true,
    "success": true,
    "data": "<h1>Example Domain</h1>"
  },
  "markdown": {
    "requested": true,
    "success": true,
    "data": "# Example Domain"
  },
  "screenshot": {
    "requested": true,
    "success": false,
    "data": null
  },
  "images": {
    "requested": false,
    "success": null,
    "data": null
  },
  "bytes": {
    "requested": false,
    "success": null,
    "data": null
  },
  "parsed": {
    "requested": false,
    "success": null,
    "data": null
  },
  "highlights": {
    "requested": false,
    "success": null,
    "data": null
  },
  "json": {
    "requested": false,
    "success": null,
    "data": null
  },
  "product": {
    "requested": false,
    "success": null,
    "data": null
  }
}

POST

web

scrape

JSON

{
  "url": "https://example.com",
  "formats": {
    "html": true
  }
}

curl https://api.context.dev/v1/web/scrape \
  -H "Authorization: Bearer $CONTEXT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "url": "https://example.com",
  "formats": {
    "html": true
  }
}'

import requests

url = "https://api.context.dev/v1/web/scrape"

payload = {
    "url": "https://example.com",
    "formats": { "html": True }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({url: 'https://example.com', formats: {html: true}})
};

fetch('https://api.context.dev/v1/web/scrape', 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.context.dev/v1/web/scrape",
  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([
    'url' => 'https://example.com',
    'formats' => [
        'html' => true
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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.context.dev/v1/web/scrape"

	payload := strings.NewReader("{\n  \"url\": \"https://example.com\",\n  \"formats\": {\n    \"html\": true\n  }\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	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.context.dev/v1/web/scrape")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"url\": \"https://example.com\",\n  \"formats\": {\n    \"html\": true\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.context.dev/v1/web/scrape")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"url\": \"https://example.com\",\n  \"formats\": {\n    \"html\": true\n  }\n}"

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

{
  "url": "https://example.com/",
  "isPartial": true,
  "html": {
    "requested": true,
    "success": true,
    "data": "<h1>Example Domain</h1>"
  },
  "markdown": {
    "requested": true,
    "success": true,
    "data": "# Example Domain"
  },
  "screenshot": {
    "requested": true,
    "success": false,
    "data": null
  },
  "images": {
    "requested": false,
    "success": null,
    "data": null
  },
  "bytes": {
    "requested": false,
    "success": null,
    "data": null
  },
  "parsed": {
    "requested": false,
    "success": null,
    "data": null
  },
  "highlights": {
    "requested": false,
    "success": null,
    "data": null
  },
  "json": {
    "requested": false,
    "success": null,
    "data": null
  },
  "product": {
    "requested": false,
    "success": null,
    "data": null
  }
}

1 Credit With actions: 2 Credits PDF OCR: +1 Credit per recovered page Set formats to choose outputs. Each output includes requested, success, and data. success is true when retrieved, false when retrieval fails, and null when not requested. Outputs that fail or were not requested return data: null. Successful outputs remain available when another format fails; partial responses set isPartial: true. The base cost is one credit, including cache hits, or two with browser actions. Highlights, JSON, product extraction, and PDF OCR can add credits; see their schema descriptions for charges. All-failed responses are unbilled except missing pages, which retain the base charge and an additional credit when product was requested. See Scrape a webpage for content controls, freshness, and dynamic pages, or the format guides for screenshots, images, and bytes.

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <API_KEY>. Keys have full access by default.

Body

application/json

url

string<uri>

required

The URL to scrape.

Pattern: ^https?://

formats

object

required

Outputs to return. Enable at least one; omitted formats are false.

Show child attributes

sharedParams

object

Shared browser and content settings. Content filters leave screenshots and original bytes unchanged.

Show child attributes

markdownParams

object

Markdown options. Requires formats.markdown: true.

Show child attributes

screenshotParams

object

Screenshot options. Requires formats.screenshot: true.

Show child attributes

imageParams

object

Image options. Requires formats.images: true.

Show child attributes

parseParams

object

Required when formats.parse is true.

Show child attributes

highlightsParams

object

Highlight options. Requires formats.highlights: true.

Show child attributes

maxAgeMs

integer

default:86400000

Maximum age of each cached output. Defaults to 1 day; 0 fetches fresh and updates the requested outputs. Compatible outputs are shared with the individual scrape endpoints. Image results with hosted files refresh after 23 hours; other outputs retain their own freshness.

Required range: 0 <= x <= 2592000000

zdr

enum<string>

default:disabled

Zero data retention. Bypasses caches and uploads; excludes request/response content and tags from logs. Must be enabled for your organization.

Available options:

enabled,

disabled

timeoutOpts

object

Total deadline, including navigation, actions, waiting, and all outputs. Defaults to 60000 milliseconds with behavior fail. Individual outputs have internal deadlines that reserve time to return completed outputs; timed-out outputs have success: false and data: null under either behavior. The overall request deadline remains enforced: fail returns an error if that deadline is reached. Use return-partial to allow the current page state and available outputs when the page is still loading. Partial responses set isPartial. Failed retrievals and incomplete captures are not cached; valid captured pieces may be cached independently. Fixed waits must fit before a response reserve of up to 5000 milliseconds (at most one quarter of the timeout) when using return-partial.

Show child attributes

Response

All nine outputs are present. Each output has success: true when retrieved, success: false and data: null when retrieval failed, or requested: false, success: null, and data: null when not requested. A failed output does not discard successful outputs or fail the request.

url

string<uri>

required

Final URL after redirects and browser actions.

Pattern: ^https?://

html

object

required

Rendered HTML after content filters.

Show child attributes

markdown

object

required

Markdown after content filters.

Show child attributes

screenshot

object

required

An image data URL. Use directly as an image src.

Show child attributes

images

object

required

Images after content filters. Empty when none are found.

Show child attributes

bytes

object

required

Original HTTP response body. Waiting, actions, and content filters never change it.

Show child attributes

parsed

object

required

Fields produced by parseParams.rules, after shared content filters.

Show child attributes

highlights

object

required

Relevant passages for your question or topic, in page order. A heading in square brackets is included when needed to interpret a passage. Empty when the page has no text.

Show child attributes

metadata

object

required

Page details, when available.

Show child attributes

cache_metadata

object

required

Cache outcome for this response. Composite responses are hits only when every cache-controlled fetch contributing to the output was a hit; age_ms is the oldest contributing hit.

Show child attributes

request_id

string<uuid>

required

Unique id of this API call, also sent in the X-Request-Id response header. Quote it when contacting support about a failed request.

Example:

"3f1c2a6e-8b4d-4c1e-9f0a-2d7b5e6c8a91"

json

object

required

Page data extracted using your schema.

Show child attributes

product

object

required

Product details found on the page.

Show child attributes

isPartial

boolean

Present when a requested output fails, capture returns a page that is still loading, images return before processing finishes, or the optional product AI fallback fails or is cut short. Check each output's success field for its result. Valid captured pieces may be cached independently; failed retrievals and incomplete captures are not cached.

key_metadata

object

Credit usage, included whenever a valid API key is provided.

Show child attributes

Web Extraction

Brand Intelligence

People

News

Files

Batch Processing

Monitor Infrastructure

Webhook Deliveries

Request Logs

Authorizations

Body

Response