SmartScraper - webscrape.ai

Structured extraction with JSON-schema validation

curl --request POST \
  --url https://api.webscrape.ai/v1/smartscraper \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '
{
  "website_url": "https://news.ycombinator.com",
  "user_prompt": "Extract the front-page stories with title, url, and score.",
  "output_schema": {
    "type": "object",
    "properties": {
      "stories": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "title": {
              "type": "string"
            },
            "url": {
              "type": "string"
            },
            "score": {
              "type": "integer"
            }
          }
        }
      }
    }
  },
  "page_complexity": "low",
  "detail_level": "medium",
  "parse_mode": "accurate",
  "plain_text": false,
  "include_tags": [
    "<string>"
  ],
  "exclude_tags": [
    "<string>"
  ],
  "reduce_content": true,
  "experimental": false,
  "headers": {},
  "max_age": 1,
  "stealth": false
}
'

import requests

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

payload = {
    "website_url": "https://news.ycombinator.com",
    "user_prompt": "Extract the front-page stories with title, url, and score.",
    "output_schema": {
        "type": "object",
        "properties": { "stories": {
                "type": "array",
                "items": {
                    "type": "object",
                    "properties": {
                        "title": { "type": "string" },
                        "url": { "type": "string" },
                        "score": { "type": "integer" }
                    }
                }
            } }
    },
    "page_complexity": "low",
    "detail_level": "medium",
    "parse_mode": "accurate",
    "plain_text": False,
    "include_tags": ["<string>"],
    "exclude_tags": ["<string>"],
    "reduce_content": True,
    "experimental": False,
    "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://news.ycombinator.com',
    user_prompt: 'Extract the front-page stories with title, url, and score.',
    output_schema: {
      type: 'object',
      properties: {
        stories: {
          type: 'array',
          items: {
            type: 'object',
            properties: {title: {type: 'string'}, url: {type: 'string'}, score: {type: 'integer'}}
          }
        }
      }
    },
    page_complexity: 'low',
    detail_level: 'medium',
    parse_mode: 'accurate',
    plain_text: false,
    include_tags: ['<string>'],
    exclude_tags: ['<string>'],
    reduce_content: true,
    experimental: false,
    headers: {},
    max_age: 1,
    stealth: false
  })
};

fetch('https://api.webscrape.ai/v1/smartscraper', 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/smartscraper",
  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://news.ycombinator.com',
    'user_prompt' => 'Extract the front-page stories with title, url, and score.',
    'output_schema' => [
        'type' => 'object',
        'properties' => [
                'stories' => [
                                'type' => 'array',
                                'items' => [
                                                                'type' => 'object',
                                                                'properties' => [
                                                                                                                                'title' => [
                                                                                                                                                                                                                                                                'type' => 'string'
                                                                                                                                ],
                                                                                                                                'url' => [
                                                                                                                                                                                                                                                                'type' => 'string'
                                                                                                                                ],
                                                                                                                                'score' => [
                                                                                                                                                                                                                                                                'type' => 'integer'
                                                                                                                                ]
                                                                ]
                                ]
                ]
        ]
    ],
    'page_complexity' => 'low',
    'detail_level' => 'medium',
    'parse_mode' => 'accurate',
    'plain_text' => false,
    'include_tags' => [
        '<string>'
    ],
    'exclude_tags' => [
        '<string>'
    ],
    'reduce_content' => true,
    'experimental' => false,
    '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/smartscraper"

	payload := strings.NewReader("{\n  \"website_url\": \"https://news.ycombinator.com\",\n  \"user_prompt\": \"Extract the front-page stories with title, url, and score.\",\n  \"output_schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"stories\": {\n        \"type\": \"array\",\n        \"items\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"title\": {\n              \"type\": \"string\"\n            },\n            \"url\": {\n              \"type\": \"string\"\n            },\n            \"score\": {\n              \"type\": \"integer\"\n            }\n          }\n        }\n      }\n    }\n  },\n  \"page_complexity\": \"low\",\n  \"detail_level\": \"medium\",\n  \"parse_mode\": \"accurate\",\n  \"plain_text\": false,\n  \"include_tags\": [\n    \"<string>\"\n  ],\n  \"exclude_tags\": [\n    \"<string>\"\n  ],\n  \"reduce_content\": true,\n  \"experimental\": false,\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/smartscraper")
  .header("X-API-Key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"website_url\": \"https://news.ycombinator.com\",\n  \"user_prompt\": \"Extract the front-page stories with title, url, and score.\",\n  \"output_schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"stories\": {\n        \"type\": \"array\",\n        \"items\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"title\": {\n              \"type\": \"string\"\n            },\n            \"url\": {\n              \"type\": \"string\"\n            },\n            \"score\": {\n              \"type\": \"integer\"\n            }\n          }\n        }\n      }\n    }\n  },\n  \"page_complexity\": \"low\",\n  \"detail_level\": \"medium\",\n  \"parse_mode\": \"accurate\",\n  \"plain_text\": false,\n  \"include_tags\": [\n    \"<string>\"\n  ],\n  \"exclude_tags\": [\n    \"<string>\"\n  ],\n  \"reduce_content\": true,\n  \"experimental\": false,\n  \"headers\": {},\n  \"max_age\": 1,\n  \"stealth\": false\n}")
  .asString();

require 'uri'
require 'net/http'

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

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://news.ycombinator.com\",\n  \"user_prompt\": \"Extract the front-page stories with title, url, and score.\",\n  \"output_schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"stories\": {\n        \"type\": \"array\",\n        \"items\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"title\": {\n              \"type\": \"string\"\n            },\n            \"url\": {\n              \"type\": \"string\"\n            },\n            \"score\": {\n              \"type\": \"integer\"\n            }\n          }\n        }\n      }\n    }\n  },\n  \"page_complexity\": \"low\",\n  \"detail_level\": \"medium\",\n  \"parse_mode\": \"accurate\",\n  \"plain_text\": false,\n  \"include_tags\": [\n    \"<string>\"\n  ],\n  \"exclude_tags\": [\n    \"<string>\"\n  ],\n  \"reduce_content\": true,\n  \"experimental\": false,\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>",
    "result": {},
    "latency_ms": 123
  },
  "credits_used": 5,
  "credits_remaining": 495
}

POST

smartscraper

Structured extraction with JSON-schema validation

curl --request POST \
  --url https://api.webscrape.ai/v1/smartscraper \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '
{
  "website_url": "https://news.ycombinator.com",
  "user_prompt": "Extract the front-page stories with title, url, and score.",
  "output_schema": {
    "type": "object",
    "properties": {
      "stories": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "title": {
              "type": "string"
            },
            "url": {
              "type": "string"
            },
            "score": {
              "type": "integer"
            }
          }
        }
      }
    }
  },
  "page_complexity": "low",
  "detail_level": "medium",
  "parse_mode": "accurate",
  "plain_text": false,
  "include_tags": [
    "<string>"
  ],
  "exclude_tags": [
    "<string>"
  ],
  "reduce_content": true,
  "experimental": false,
  "headers": {},
  "max_age": 1,
  "stealth": false
}
'

import requests

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

payload = {
    "website_url": "https://news.ycombinator.com",
    "user_prompt": "Extract the front-page stories with title, url, and score.",
    "output_schema": {
        "type": "object",
        "properties": { "stories": {
                "type": "array",
                "items": {
                    "type": "object",
                    "properties": {
                        "title": { "type": "string" },
                        "url": { "type": "string" },
                        "score": { "type": "integer" }
                    }
                }
            } }
    },
    "page_complexity": "low",
    "detail_level": "medium",
    "parse_mode": "accurate",
    "plain_text": False,
    "include_tags": ["<string>"],
    "exclude_tags": ["<string>"],
    "reduce_content": True,
    "experimental": False,
    "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://news.ycombinator.com',
    user_prompt: 'Extract the front-page stories with title, url, and score.',
    output_schema: {
      type: 'object',
      properties: {
        stories: {
          type: 'array',
          items: {
            type: 'object',
            properties: {title: {type: 'string'}, url: {type: 'string'}, score: {type: 'integer'}}
          }
        }
      }
    },
    page_complexity: 'low',
    detail_level: 'medium',
    parse_mode: 'accurate',
    plain_text: false,
    include_tags: ['<string>'],
    exclude_tags: ['<string>'],
    reduce_content: true,
    experimental: false,
    headers: {},
    max_age: 1,
    stealth: false
  })
};

fetch('https://api.webscrape.ai/v1/smartscraper', 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/smartscraper",
  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://news.ycombinator.com',
    'user_prompt' => 'Extract the front-page stories with title, url, and score.',
    'output_schema' => [
        'type' => 'object',
        'properties' => [
                'stories' => [
                                'type' => 'array',
                                'items' => [
                                                                'type' => 'object',
                                                                'properties' => [
                                                                                                                                'title' => [
                                                                                                                                                                                                                                                                'type' => 'string'
                                                                                                                                ],
                                                                                                                                'url' => [
                                                                                                                                                                                                                                                                'type' => 'string'
                                                                                                                                ],
                                                                                                                                'score' => [
                                                                                                                                                                                                                                                                'type' => 'integer'
                                                                                                                                ]
                                                                ]
                                ]
                ]
        ]
    ],
    'page_complexity' => 'low',
    'detail_level' => 'medium',
    'parse_mode' => 'accurate',
    'plain_text' => false,
    'include_tags' => [
        '<string>'
    ],
    'exclude_tags' => [
        '<string>'
    ],
    'reduce_content' => true,
    'experimental' => false,
    '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/smartscraper"

	payload := strings.NewReader("{\n  \"website_url\": \"https://news.ycombinator.com\",\n  \"user_prompt\": \"Extract the front-page stories with title, url, and score.\",\n  \"output_schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"stories\": {\n        \"type\": \"array\",\n        \"items\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"title\": {\n              \"type\": \"string\"\n            },\n            \"url\": {\n              \"type\": \"string\"\n            },\n            \"score\": {\n              \"type\": \"integer\"\n            }\n          }\n        }\n      }\n    }\n  },\n  \"page_complexity\": \"low\",\n  \"detail_level\": \"medium\",\n  \"parse_mode\": \"accurate\",\n  \"plain_text\": false,\n  \"include_tags\": [\n    \"<string>\"\n  ],\n  \"exclude_tags\": [\n    \"<string>\"\n  ],\n  \"reduce_content\": true,\n  \"experimental\": false,\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/smartscraper")
  .header("X-API-Key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"website_url\": \"https://news.ycombinator.com\",\n  \"user_prompt\": \"Extract the front-page stories with title, url, and score.\",\n  \"output_schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"stories\": {\n        \"type\": \"array\",\n        \"items\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"title\": {\n              \"type\": \"string\"\n            },\n            \"url\": {\n              \"type\": \"string\"\n            },\n            \"score\": {\n              \"type\": \"integer\"\n            }\n          }\n        }\n      }\n    }\n  },\n  \"page_complexity\": \"low\",\n  \"detail_level\": \"medium\",\n  \"parse_mode\": \"accurate\",\n  \"plain_text\": false,\n  \"include_tags\": [\n    \"<string>\"\n  ],\n  \"exclude_tags\": [\n    \"<string>\"\n  ],\n  \"reduce_content\": true,\n  \"experimental\": false,\n  \"headers\": {},\n  \"max_age\": 1,\n  \"stealth\": false\n}")
  .asString();

require 'uri'
require 'net/http'

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

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://news.ycombinator.com\",\n  \"user_prompt\": \"Extract the front-page stories with title, url, and score.\",\n  \"output_schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"stories\": {\n        \"type\": \"array\",\n        \"items\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"title\": {\n              \"type\": \"string\"\n            },\n            \"url\": {\n              \"type\": \"string\"\n            },\n            \"score\": {\n              \"type\": \"integer\"\n            }\n          }\n        }\n      }\n    }\n  },\n  \"page_complexity\": \"low\",\n  \"detail_level\": \"medium\",\n  \"parse_mode\": \"accurate\",\n  \"plain_text\": false,\n  \"include_tags\": [\n    \"<string>\"\n  ],\n  \"exclude_tags\": [\n    \"<string>\"\n  ],\n  \"reduce_content\": true,\n  \"experimental\": false,\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>",
    "result": {},
    "latency_ms": 123
  },
  "credits_used": 5,
  "credits_remaining": 495
}

Hand over a URL and a JSON schema, get validated structured JSON back. Handles long content, noisy pages, and one automatic repair pass on validation failure. Cost: 5 credits per call (+5 with stealth: true). Failed requests cost 0.

Examples

curl https://api.webscrape.ai/v1/smartscraper \
  -H "X-API-Key: wsg_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "website_url": "https://news.ycombinator.com",
    "user_prompt": "Extract the front-page stories with title, url, and score.",
    "output_schema": {
      "type": "object",
      "properties": {
        "stories": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "title": {"type": "string"},
              "url":   {"type": "string"},
              "score": {"type": "integer"}
            }
          }
        }
      }
    }
  }'

import requests

output_schema = {
    "type": "object",
    "properties": {
        "stories": {
            "type": "array",
            "items": {
                "type": "object",
                "properties": {
                    "title": {"type": "string"},
                    "url":   {"type": "string"},
                    "score": {"type": "integer"},
                },
            },
        }
    },
}

r = requests.post(
    "https://api.webscrape.ai/v1/smartscraper",
    headers={"X-API-Key": "wsg_live_..."},
    json={
        "website_url": "https://news.ycombinator.com",
        "user_prompt": "Extract the front-page stories with title, url, and score.",
        "output_schema": output_schema,
    },
    timeout=120,
)
env = r.json()
if env["status"] == "completed":
    for story in env["data"]["result"]["stories"]:
        print(story["title"], story["score"])

const env = await fetch("https://api.webscrape.ai/v1/smartscraper", {
  method: "POST",
  headers: { "X-API-Key": "wsg_live_...", "Content-Type": "application/json" },
  body: JSON.stringify({
    website_url: "https://news.ycombinator.com",
    user_prompt: "Extract the front-page stories with title, url, and score.",
    output_schema: {
      type: "object",
      properties: {
        stories: {
          type: "array",
          items: {
            type: "object",
            properties: {
              title: { type: "string" },
              url:   { type: "string" },
              score: { type: "integer" },
            },
          },
        },
      },
    },
  }),
}).then(r => r.json());

if (env.status === "completed") {
  for (const story of env.data.result.stories) console.log(story.title, story.score);
}

package main

import (
    "bytes"
    "encoding/json"
    "io"
    "net/http"
)

func main() {
    body, _ := json.Marshal(map[string]any{
        "website_url": "https://news.ycombinator.com",
        "user_prompt": "Extract the front-page stories with title, url, and score.",
        "output_schema": map[string]any{
            "type": "object",
            "properties": map[string]any{
                "stories": map[string]any{
                    "type": "array",
                    "items": map[string]any{
                        "type": "object",
                        "properties": map[string]any{
                            "title": map[string]string{"type": "string"},
                            "url":   map[string]string{"type": "string"},
                            "score": map[string]string{"type": "integer"},
                        },
                    },
                },
            },
        },
    })
    req, _ := http.NewRequest("POST", "https://api.webscrape.ai/v1/smartscraper", bytes.NewReader(body))
    req.Header.Set("X-API-Key", "wsg_live_...")
    req.Header.Set("Content-Type", "application/json")
    resp, _ := http.DefaultClient.Do(req)
    defer resp.Body.Close()
    out, _ := io.ReadAll(resp.Body)
    println(string(out))
}

use serde_json::json;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let body = json!({
        "website_url": "https://news.ycombinator.com",
        "user_prompt": "Extract the front-page stories with title, url, and score.",
        "output_schema": {
            "type": "object",
            "properties": {
                "stories": {
                    "type": "array",
                    "items": {
                        "type": "object",
                        "properties": {
                            "title": {"type": "string"},
                            "url":   {"type": "string"},
                            "score": {"type": "integer"}
                        }
                    }
                }
            }
        }
    });
    let resp = reqwest::Client::new()
        .post("https://api.webscrape.ai/v1/smartscraper")
        .header("X-API-Key", "wsg_live_...")
        .json(&body)
        .send()
        .await?;
    println!("{}", resp.text().await?);
    Ok(())
}

Example response

{
  "status": "completed",
  "data": {
    "result": {
      "stories": [
        { "title": "Show HN: ...", "url": "https://...", "score": 312 },
        { "title": "Ask HN: ...", "url": "https://...", "score": 184 }
      ]
    },
    "latency_ms": 1842
  },
  "credits_used": 5,
  "credits_remaining": 495,
  "request_id": "req_aB3xY9Kp"
}

Your extracted data is at data.result. Always check status first.

Tips

user_prompt is required and does the heavy lifting. Add an output_schema when you want the result validated into a fixed shape.
Leave page_complexity at low (the default) for most pages. Bump to high for visually busy pages or schemas with many nested fields.
Failed schema validation comes back as error.code: validation_failed (HTTP 422). Adjust the schema or simplify the prompt and retry.

Page requires a login, click, or pagination before the data shows up? Use SmartBrowse. Schema-driven extraction, running in a real Chrome session.

For schema-design tips, page-complexity tuning, and validation troubleshooting, see the SmartScraper feature page.

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://news.ycombinator.com"

user_prompt

string

required

Plain-English description of what to extract.

Example:

"Extract the front-page stories with title, url, and score."

output_schema

object

JSON Schema enforced on the extracted output. When supplied, the result is validated against the schema and one repair attempt is made before returning validation_failed. Providing both user_prompt and output_schema gives the best results.

Example:

{
  "type": "object",
  "properties": {
    "stories": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "title": { "type": "string" },
          "url": { "type": "string" },
          "score": { "type": "integer" }
        }
      }
    }
  }
}

page_complexity

enum<string>

default:low

low (default) is faster and cheaper. Bump to high for visually busy pages or schemas with many nested fields.

Available options:

low,

high

detail_level

enum<string>

default:medium

How exhaustively to populate the result.

Available options:

low,

medium,

high

parse_mode

enum<string>

default:accurate

Cleaner mode. accurate is more forgiving on malformed pages; speed is faster.

Available options:

accurate,

speed

plain_text

boolean

default:false

Return the raw extracted text under result instead of a parsed JSON object. Bypasses output_schema validation.

include_tags

string[]

Whitelist of HTML tags to keep before extraction.

exclude_tags

string[]

Blacklist of HTML tags to drop before extraction.

reduce_content

boolean

Trim long content before extraction. Helps on pages with lots of repetitive boilerplate. Uses a sensible default when omitted.

experimental

boolean

default:false

Opt in to an alternate extraction path that can do better on hard-to-parse pages. Behavior may change without notice.

headers

object

Custom request headers forwarded to the fetcher. Providing any headers disables URL caching for this request.

Show child attributes

max_age

integer

URL-cache opt-in — same three-state semantics as /scrape (omitted = no cache, 0 = bypass read but write on miss, >0 = return entries fresher than N seconds).

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. +5 credits.

Response

Successfully extracted.

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:

5

credits_remaining

integer

required

Example:

495

​Examples

​Tips

Authorizations

Body

Response

Examples

Tips