Fetch a URL as HTML, markdown, or links

curl --request POST \
  --url https://api.webscrape.ai/v1/scrape \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '
{
  "website_url": "https://example.com",
  "clean": false,
  "parse_mode": "accurate",
  "tag_truncate": true,
  "extract_links": false,
  "include_tags": [
    "<string>"
  ],
  "exclude_tags": [
    "<string>"
  ],
  "headers": {},
  "max_age": 1,
  "stealth": false
}
'

import requests

url = "https://api.webscrape.ai/v1/scrape"

payload = {
    "website_url": "https://example.com",
    "clean": False,
    "parse_mode": "accurate",
    "tag_truncate": True,
    "extract_links": False,
    "include_tags": ["<string>"],
    "exclude_tags": ["<string>"],
    "headers": {},
    "max_age": 1,
    "stealth": False
}
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({
    website_url: 'https://example.com',
    clean: false,
    parse_mode: 'accurate',
    tag_truncate: true,
    extract_links: false,
    include_tags: ['<string>'],
    exclude_tags: ['<string>'],
    headers: {},
    max_age: 1,
    stealth: false
  })
};

fetch('https://api.webscrape.ai/v1/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.webscrape.ai/v1/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([
    'website_url' => 'https://example.com',
    'clean' => false,
    'parse_mode' => 'accurate',
    'tag_truncate' => true,
    'extract_links' => false,
    'include_tags' => [
        '<string>'
    ],
    'exclude_tags' => [
        '<string>'
    ],
    'headers' => [
        
    ],
    'max_age' => 1,
    'stealth' => false
  ]),
  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.webscrape.ai/v1/scrape"

	payload := strings.NewReader("{\n  \"website_url\": \"https://example.com\",\n  \"clean\": false,\n  \"parse_mode\": \"accurate\",\n  \"tag_truncate\": true,\n  \"extract_links\": false,\n  \"include_tags\": [\n    \"<string>\"\n  ],\n  \"exclude_tags\": [\n    \"<string>\"\n  ],\n  \"headers\": {},\n  \"max_age\": 1,\n  \"stealth\": false\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.webscrape.ai/v1/scrape")
  .header("X-API-Key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"website_url\": \"https://example.com\",\n  \"clean\": false,\n  \"parse_mode\": \"accurate\",\n  \"tag_truncate\": true,\n  \"extract_links\": false,\n  \"include_tags\": [\n    \"<string>\"\n  ],\n  \"exclude_tags\": [\n    \"<string>\"\n  ],\n  \"headers\": {},\n  \"max_age\": 1,\n  \"stealth\": false\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.webscrape.ai/v1/scrape")

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  \"website_url\": \"https://example.com\",\n  \"clean\": false,\n  \"parse_mode\": \"accurate\",\n  \"tag_truncate\": true,\n  \"extract_links\": false,\n  \"include_tags\": [\n    \"<string>\"\n  ],\n  \"exclude_tags\": [\n    \"<string>\"\n  ],\n  \"headers\": {},\n  \"max_age\": 1,\n  \"stealth\": false\n}"

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

{
  "status": "completed",
  "request_id": "req_aB3xY9Kp",
  "data": {
    "request_id": "<string>",
    "html": "<string>",
    "cleaned": true,
    "links": [
      {
        "url": "<string>",
        "text": "<string>"
      }
    ],
    "metadata": {
      "title": "<string>",
      "description": "<string>",
      "language": "<string>"
    },
    "latency_ms": 123
  },
  "credits_used": 1,
  "credits_remaining": 499
}

POST

scrape

Fetch a URL as HTML, markdown, or links

curl --request POST \
  --url https://api.webscrape.ai/v1/scrape \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '
{
  "website_url": "https://example.com",
  "clean": false,
  "parse_mode": "accurate",
  "tag_truncate": true,
  "extract_links": false,
  "include_tags": [
    "<string>"
  ],
  "exclude_tags": [
    "<string>"
  ],
  "headers": {},
  "max_age": 1,
  "stealth": false
}
'

import requests

url = "https://api.webscrape.ai/v1/scrape"

payload = {
    "website_url": "https://example.com",
    "clean": False,
    "parse_mode": "accurate",
    "tag_truncate": True,
    "extract_links": False,
    "include_tags": ["<string>"],
    "exclude_tags": ["<string>"],
    "headers": {},
    "max_age": 1,
    "stealth": False
}
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({
    website_url: 'https://example.com',
    clean: false,
    parse_mode: 'accurate',
    tag_truncate: true,
    extract_links: false,
    include_tags: ['<string>'],
    exclude_tags: ['<string>'],
    headers: {},
    max_age: 1,
    stealth: false
  })
};

fetch('https://api.webscrape.ai/v1/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.webscrape.ai/v1/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([
    'website_url' => 'https://example.com',
    'clean' => false,
    'parse_mode' => 'accurate',
    'tag_truncate' => true,
    'extract_links' => false,
    'include_tags' => [
        '<string>'
    ],
    'exclude_tags' => [
        '<string>'
    ],
    'headers' => [
        
    ],
    'max_age' => 1,
    'stealth' => false
  ]),
  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.webscrape.ai/v1/scrape"

	payload := strings.NewReader("{\n  \"website_url\": \"https://example.com\",\n  \"clean\": false,\n  \"parse_mode\": \"accurate\",\n  \"tag_truncate\": true,\n  \"extract_links\": false,\n  \"include_tags\": [\n    \"<string>\"\n  ],\n  \"exclude_tags\": [\n    \"<string>\"\n  ],\n  \"headers\": {},\n  \"max_age\": 1,\n  \"stealth\": false\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.webscrape.ai/v1/scrape")
  .header("X-API-Key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"website_url\": \"https://example.com\",\n  \"clean\": false,\n  \"parse_mode\": \"accurate\",\n  \"tag_truncate\": true,\n  \"extract_links\": false,\n  \"include_tags\": [\n    \"<string>\"\n  ],\n  \"exclude_tags\": [\n    \"<string>\"\n  ],\n  \"headers\": {},\n  \"max_age\": 1,\n  \"stealth\": false\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.webscrape.ai/v1/scrape")

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  \"website_url\": \"https://example.com\",\n  \"clean\": false,\n  \"parse_mode\": \"accurate\",\n  \"tag_truncate\": true,\n  \"extract_links\": false,\n  \"include_tags\": [\n    \"<string>\"\n  ],\n  \"exclude_tags\": [\n    \"<string>\"\n  ],\n  \"headers\": {},\n  \"max_age\": 1,\n  \"stealth\": false\n}"

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

{
  "status": "completed",
  "request_id": "req_aB3xY9Kp",
  "data": {
    "request_id": "<string>",
    "html": "<string>",
    "cleaned": true,
    "links": [
      {
        "url": "<string>",
        "text": "<string>"
      }
    ],
    "metadata": {
      "title": "<string>",
      "description": "<string>",
      "language": "<string>"
    },
    "latency_ms": 123
  },
  "credits_used": 1,
  "credits_remaining": 499
}

Authorizations

X-API-Key

string

header

required

Generate from the dashboard. Format: wsg_live_<32 base62 chars>.

Body

application/json

website_url

string<uri>

required

Example:

"https://example.com"

clean

boolean

default:false

Convert HTML to cleaned markdown.

parse_mode

enum<string>

default:accurate

Cleaner mode when clean: true. accurate is more forgiving on malformed pages; speed is faster.

Available options:

accurate,

speed

tag_truncate

boolean

default:true

When clean: true, replace inline images with their alt text to reduce noise. Disable to keep the original image tags.

extract_links

boolean

default:false

Include a deduplicated list of outbound links.

include_tags

string[]

Whitelist of HTML tags to keep when clean: true.

exclude_tags

string[]

Blacklist of HTML tags to drop when clean: true.

headers

object

Custom request headers forwarded to the fetcher (e.g. a specific User-Agent or Accept-Language). Providing any headers disables URL caching for this request.

Show child attributes

max_age

integer

URL-cache opt-in (three-state).

Omitted — no cache: every call fetches fresh.
>0 — return a cached entry if it's fresher than max_age seconds, otherwise fetch and write.

Stealth requests, custom-headered requests, and URLs with query strings or fragments are never cached.

Required range: x >= 0

stealth

boolean

default:false

Use stealth mode. +2 credits.

Response

Successfully fetched.

status

enum<string>

required

Discriminator for the envelope variant.

Available options:

completed

request_id

string

required

Per-request id. Also returned as the X-Request-ID response header. Include it when reporting issues.

Example:

"req_aB3xY9Kp"

data

object

required

Show child attributes

credits_used

integer

required

Example:

1

credits_remaining

integer

required

Example:

499

Overview

Scrape

SmartBrowse

Scrape

SmartBrowse

Fetch a URL as HTML, markdown, or links

Authorizations

Body

Response