Extract structured data

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    url: '<string>',
    schema: {
      type: 'object',
      properties: {
        mission_statement: {type: 'string', description: 'The company\'s stated mission.'},
        case_studies: {
          type: 'array',
          items: {
            type: 'object',
            properties: {title: {type: 'string'}, url: {type: 'string'}},
            required: ['title', 'url'],
            additionalProperties: false
          }
        }
      },
      required: ['mission_statement', 'case_studies'],
      additionalProperties: false
    },
    instructions: '<string>',
    factCheck: false,
    followSubdomains: false,
    maxPages: 5,
    maxDepth: 1,
    pdf: {shouldParse: true},
    includeFrames: false,
    maxAgeMs: 604800000,
    waitForMs: 15000,
    settleAnimations: false,
    actions: [{do: 'wait', timeMs: 15000}],
    stopAfterMs: 80000,
    zdr: 'disabled',
    tags: ['production', 'team-alpha']
  })
};

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

import requests

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

payload = {
    "url": "<string>",
    "schema": {
        "type": "object",
        "properties": {
            "mission_statement": {
                "type": "string",
                "description": "The company's stated mission."
            },
            "case_studies": {
                "type": "array",
                "items": {
                    "type": "object",
                    "properties": {
                        "title": { "type": "string" },
                        "url": { "type": "string" }
                    },
                    "required": ["title", "url"],
                    "additionalProperties": False
                }
            }
        },
        "required": ["mission_statement", "case_studies"],
        "additionalProperties": False
    },
    "instructions": "<string>",
    "factCheck": False,
    "followSubdomains": False,
    "maxPages": 5,
    "maxDepth": 1,
    "pdf": { "shouldParse": True },
    "includeFrames": False,
    "maxAgeMs": 604800000,
    "waitForMs": 15000,
    "settleAnimations": False,
    "actions": [
        {
            "do": "wait",
            "timeMs": 15000
        }
    ],
    "stopAfterMs": 80000,
    "zdr": "disabled",
    "tags": ["production", "team-alpha"]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

require 'uri'
require 'net/http'

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

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\": \"<string>\",\n  \"schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"mission_statement\": {\n        \"type\": \"string\",\n        \"description\": \"The company's stated mission.\"\n      },\n      \"case_studies\": {\n        \"type\": \"array\",\n        \"items\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"title\": {\n              \"type\": \"string\"\n            },\n            \"url\": {\n              \"type\": \"string\"\n            }\n          },\n          \"required\": [\n            \"title\",\n            \"url\"\n          ],\n          \"additionalProperties\": false\n        }\n      }\n    },\n    \"required\": [\n      \"mission_statement\",\n      \"case_studies\"\n    ],\n    \"additionalProperties\": false\n  },\n  \"instructions\": \"<string>\",\n  \"factCheck\": false,\n  \"followSubdomains\": false,\n  \"maxPages\": 5,\n  \"maxDepth\": 1,\n  \"pdf\": {\n    \"shouldParse\": true\n  },\n  \"includeFrames\": false,\n  \"maxAgeMs\": 604800000,\n  \"waitForMs\": 15000,\n  \"settleAnimations\": false,\n  \"actions\": [\n    {\n      \"do\": \"wait\",\n      \"timeMs\": 15000\n    }\n  ],\n  \"stopAfterMs\": 80000,\n  \"zdr\": \"disabled\",\n  \"tags\": [\n    \"production\",\n    \"team-alpha\"\n  ]\n}"

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

package main

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

func main() {

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

	payload := strings.NewReader("{\n  \"url\": \"<string>\",\n  \"schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"mission_statement\": {\n        \"type\": \"string\",\n        \"description\": \"The company's stated mission.\"\n      },\n      \"case_studies\": {\n        \"type\": \"array\",\n        \"items\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"title\": {\n              \"type\": \"string\"\n            },\n            \"url\": {\n              \"type\": \"string\"\n            }\n          },\n          \"required\": [\n            \"title\",\n            \"url\"\n          ],\n          \"additionalProperties\": false\n        }\n      }\n    },\n    \"required\": [\n      \"mission_statement\",\n      \"case_studies\"\n    ],\n    \"additionalProperties\": false\n  },\n  \"instructions\": \"<string>\",\n  \"factCheck\": false,\n  \"followSubdomains\": false,\n  \"maxPages\": 5,\n  \"maxDepth\": 1,\n  \"pdf\": {\n    \"shouldParse\": true\n  },\n  \"includeFrames\": false,\n  \"maxAgeMs\": 604800000,\n  \"waitForMs\": 15000,\n  \"settleAnimations\": false,\n  \"actions\": [\n    {\n      \"do\": \"wait\",\n      \"timeMs\": 15000\n    }\n  ],\n  \"stopAfterMs\": 80000,\n  \"zdr\": \"disabled\",\n  \"tags\": [\n    \"production\",\n    \"team-alpha\"\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))

}

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.context.dev/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([
    'url' => '<string>',
    'schema' => [
        'type' => 'object',
        'properties' => [
                'mission_statement' => [
                                'type' => 'string',
                                'description' => 'The company\'s stated mission.'
                ],
                'case_studies' => [
                                'type' => 'array',
                                'items' => [
                                                                'type' => 'object',
                                                                'properties' => [
                                                                                                                                'title' => [
                                                                                                                                                                                                                                                                'type' => 'string'
                                                                                                                                ],
                                                                                                                                'url' => [
                                                                                                                                                                                                                                                                'type' => 'string'
                                                                                                                                ]
                                                                ],
                                                                'required' => [
                                                                                                                                'title',
                                                                                                                                'url'
                                                                ],
                                                                'additionalProperties' => false
                                ]
                ]
        ],
        'required' => [
                'mission_statement',
                'case_studies'
        ],
        'additionalProperties' => false
    ],
    'instructions' => '<string>',
    'factCheck' => false,
    'followSubdomains' => false,
    'maxPages' => 5,
    'maxDepth' => 1,
    'pdf' => [
        'shouldParse' => true
    ],
    'includeFrames' => false,
    'maxAgeMs' => 604800000,
    'waitForMs' => 15000,
    'settleAnimations' => false,
    'actions' => [
        [
                'do' => 'wait',
                'timeMs' => 15000
        ]
    ],
    'stopAfterMs' => 80000,
    'zdr' => 'disabled',
    'tags' => [
        'production',
        'team-alpha'
    ]
  ]),
  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;
}

curl --request POST \
  --url https://api.context.dev/v1/web/extract \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data @- <<EOF
{
  "url": "<string>",
  "schema": {
    "type": "object",
    "properties": {
      "mission_statement": {
        "type": "string",
        "description": "The company's stated mission."
      },
      "case_studies": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "title": {
              "type": "string"
            },
            "url": {
              "type": "string"
            }
          },
          "required": [
            "title",
            "url"
          ],
          "additionalProperties": false
        }
      }
    },
    "required": [
      "mission_statement",
      "case_studies"
    ],
    "additionalProperties": false
  },
  "instructions": "<string>",
  "factCheck": false,
  "followSubdomains": false,
  "maxPages": 5,
  "maxDepth": 1,
  "pdf": {
    "shouldParse": true
  },
  "includeFrames": false,
  "maxAgeMs": 604800000,
  "waitForMs": 15000,
  "settleAnimations": false,
  "actions": [
    {
      "do": "wait",
      "timeMs": 15000
    }
  ],
  "stopAfterMs": 80000,
  "zdr": "disabled",
  "tags": [
    "production",
    "team-alpha"
  ]
}
EOF

{
  "status": "<string>",
  "url": "<string>",
  "urls_analyzed": [
    "<string>"
  ],
  "data": {},
  "metadata": {
    "numUrls": 123,
    "maxCrawlDepth": 123,
    "numSucceeded": 123,
    "numFailed": 123,
    "numSkipped": 123,
    "numBlocked": 123,
    "actionsApplied": [
      {
        "instruction": "<string>",
        "status": "applied",
        "method": "<string>",
        "targetDescription": "<string>",
        "completionEvidence": "<string>",
        "error": "<string>",
        "durationMs": 123
      }
    ]
  },
  "request_id": "3f1c2a6e-8b4d-4c1e-9f0a-2d7b5e6c8a91",
  "cache_metadata": {
    "status": "hit",
    "age_ms": 1
  },
  "partial": true,
  "key_metadata": {
    "credits_consumed": 123,
    "credits_remaining": 123
  }
}

{
  "message": "<string>",
  "error_code": "INPUT_VALIDATION_ERROR",
  "request_id": "3f1c2a6e-8b4d-4c1e-9f0a-2d7b5e6c8a91",
  "key_metadata": {
    "credits_consumed": 123,
    "credits_remaining": 123
  }
}

{
  "request_id": "3f1c2a6e-8b4d-4c1e-9f0a-2d7b5e6c8a91",
  "message": "<string>",
  "error_code": "INTERNAL_ERROR",
  "required_permission": "logs:read",
  "key_metadata": {
    "credits_consumed": 123,
    "credits_remaining": 123
  }
}

{
  "request_id": "3f1c2a6e-8b4d-4c1e-9f0a-2d7b5e6c8a91",
  "message": "<string>",
  "error_code": "INTERNAL_ERROR",
  "required_permission": "logs:read",
  "key_metadata": {
    "credits_consumed": 123,
    "credits_remaining": 123
  }
}

{
  "request_id": "3f1c2a6e-8b4d-4c1e-9f0a-2d7b5e6c8a91",
  "message": "<string>",
  "error_code": "INTERNAL_ERROR",
  "required_permission": "logs:read",
  "key_metadata": {
    "credits_consumed": 123,
    "credits_remaining": 123
  }
}

{
  "message": "<string>",
  "error_code": "RATE_LIMITED",
  "request_id": "3f1c2a6e-8b4d-4c1e-9f0a-2d7b5e6c8a91",
  "key_metadata": {
    "credits_consumed": 123,
    "credits_remaining": 123
  }
}

{
  "request_id": "3f1c2a6e-8b4d-4c1e-9f0a-2d7b5e6c8a91",
  "message": "<string>",
  "error_code": "INTERNAL_ERROR",
  "required_permission": "logs:read",
  "key_metadata": {
    "credits_consumed": 123,
    "credits_remaining": 123
  }
}

POST

web

extract

Extract structured data

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    url: '<string>',
    schema: {
      type: 'object',
      properties: {
        mission_statement: {type: 'string', description: 'The company\'s stated mission.'},
        case_studies: {
          type: 'array',
          items: {
            type: 'object',
            properties: {title: {type: 'string'}, url: {type: 'string'}},
            required: ['title', 'url'],
            additionalProperties: false
          }
        }
      },
      required: ['mission_statement', 'case_studies'],
      additionalProperties: false
    },
    instructions: '<string>',
    factCheck: false,
    followSubdomains: false,
    maxPages: 5,
    maxDepth: 1,
    pdf: {shouldParse: true},
    includeFrames: false,
    maxAgeMs: 604800000,
    waitForMs: 15000,
    settleAnimations: false,
    actions: [{do: 'wait', timeMs: 15000}],
    stopAfterMs: 80000,
    zdr: 'disabled',
    tags: ['production', 'team-alpha']
  })
};

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

import requests

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

payload = {
    "url": "<string>",
    "schema": {
        "type": "object",
        "properties": {
            "mission_statement": {
                "type": "string",
                "description": "The company's stated mission."
            },
            "case_studies": {
                "type": "array",
                "items": {
                    "type": "object",
                    "properties": {
                        "title": { "type": "string" },
                        "url": { "type": "string" }
                    },
                    "required": ["title", "url"],
                    "additionalProperties": False
                }
            }
        },
        "required": ["mission_statement", "case_studies"],
        "additionalProperties": False
    },
    "instructions": "<string>",
    "factCheck": False,
    "followSubdomains": False,
    "maxPages": 5,
    "maxDepth": 1,
    "pdf": { "shouldParse": True },
    "includeFrames": False,
    "maxAgeMs": 604800000,
    "waitForMs": 15000,
    "settleAnimations": False,
    "actions": [
        {
            "do": "wait",
            "timeMs": 15000
        }
    ],
    "stopAfterMs": 80000,
    "zdr": "disabled",
    "tags": ["production", "team-alpha"]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

require 'uri'
require 'net/http'

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

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\": \"<string>\",\n  \"schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"mission_statement\": {\n        \"type\": \"string\",\n        \"description\": \"The company's stated mission.\"\n      },\n      \"case_studies\": {\n        \"type\": \"array\",\n        \"items\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"title\": {\n              \"type\": \"string\"\n            },\n            \"url\": {\n              \"type\": \"string\"\n            }\n          },\n          \"required\": [\n            \"title\",\n            \"url\"\n          ],\n          \"additionalProperties\": false\n        }\n      }\n    },\n    \"required\": [\n      \"mission_statement\",\n      \"case_studies\"\n    ],\n    \"additionalProperties\": false\n  },\n  \"instructions\": \"<string>\",\n  \"factCheck\": false,\n  \"followSubdomains\": false,\n  \"maxPages\": 5,\n  \"maxDepth\": 1,\n  \"pdf\": {\n    \"shouldParse\": true\n  },\n  \"includeFrames\": false,\n  \"maxAgeMs\": 604800000,\n  \"waitForMs\": 15000,\n  \"settleAnimations\": false,\n  \"actions\": [\n    {\n      \"do\": \"wait\",\n      \"timeMs\": 15000\n    }\n  ],\n  \"stopAfterMs\": 80000,\n  \"zdr\": \"disabled\",\n  \"tags\": [\n    \"production\",\n    \"team-alpha\"\n  ]\n}"

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

package main

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

func main() {

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

	payload := strings.NewReader("{\n  \"url\": \"<string>\",\n  \"schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"mission_statement\": {\n        \"type\": \"string\",\n        \"description\": \"The company's stated mission.\"\n      },\n      \"case_studies\": {\n        \"type\": \"array\",\n        \"items\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"title\": {\n              \"type\": \"string\"\n            },\n            \"url\": {\n              \"type\": \"string\"\n            }\n          },\n          \"required\": [\n            \"title\",\n            \"url\"\n          ],\n          \"additionalProperties\": false\n        }\n      }\n    },\n    \"required\": [\n      \"mission_statement\",\n      \"case_studies\"\n    ],\n    \"additionalProperties\": false\n  },\n  \"instructions\": \"<string>\",\n  \"factCheck\": false,\n  \"followSubdomains\": false,\n  \"maxPages\": 5,\n  \"maxDepth\": 1,\n  \"pdf\": {\n    \"shouldParse\": true\n  },\n  \"includeFrames\": false,\n  \"maxAgeMs\": 604800000,\n  \"waitForMs\": 15000,\n  \"settleAnimations\": false,\n  \"actions\": [\n    {\n      \"do\": \"wait\",\n      \"timeMs\": 15000\n    }\n  ],\n  \"stopAfterMs\": 80000,\n  \"zdr\": \"disabled\",\n  \"tags\": [\n    \"production\",\n    \"team-alpha\"\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))

}

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.context.dev/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([
    'url' => '<string>',
    'schema' => [
        'type' => 'object',
        'properties' => [
                'mission_statement' => [
                                'type' => 'string',
                                'description' => 'The company\'s stated mission.'
                ],
                'case_studies' => [
                                'type' => 'array',
                                'items' => [
                                                                'type' => 'object',
                                                                'properties' => [
                                                                                                                                'title' => [
                                                                                                                                                                                                                                                                'type' => 'string'
                                                                                                                                ],
                                                                                                                                'url' => [
                                                                                                                                                                                                                                                                'type' => 'string'
                                                                                                                                ]
                                                                ],
                                                                'required' => [
                                                                                                                                'title',
                                                                                                                                'url'
                                                                ],
                                                                'additionalProperties' => false
                                ]
                ]
        ],
        'required' => [
                'mission_statement',
                'case_studies'
        ],
        'additionalProperties' => false
    ],
    'instructions' => '<string>',
    'factCheck' => false,
    'followSubdomains' => false,
    'maxPages' => 5,
    'maxDepth' => 1,
    'pdf' => [
        'shouldParse' => true
    ],
    'includeFrames' => false,
    'maxAgeMs' => 604800000,
    'waitForMs' => 15000,
    'settleAnimations' => false,
    'actions' => [
        [
                'do' => 'wait',
                'timeMs' => 15000
        ]
    ],
    'stopAfterMs' => 80000,
    'zdr' => 'disabled',
    'tags' => [
        'production',
        'team-alpha'
    ]
  ]),
  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;
}

curl --request POST \
  --url https://api.context.dev/v1/web/extract \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data @- <<EOF
{
  "url": "<string>",
  "schema": {
    "type": "object",
    "properties": {
      "mission_statement": {
        "type": "string",
        "description": "The company's stated mission."
      },
      "case_studies": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "title": {
              "type": "string"
            },
            "url": {
              "type": "string"
            }
          },
          "required": [
            "title",
            "url"
          ],
          "additionalProperties": false
        }
      }
    },
    "required": [
      "mission_statement",
      "case_studies"
    ],
    "additionalProperties": false
  },
  "instructions": "<string>",
  "factCheck": false,
  "followSubdomains": false,
  "maxPages": 5,
  "maxDepth": 1,
  "pdf": {
    "shouldParse": true
  },
  "includeFrames": false,
  "maxAgeMs": 604800000,
  "waitForMs": 15000,
  "settleAnimations": false,
  "actions": [
    {
      "do": "wait",
      "timeMs": 15000
    }
  ],
  "stopAfterMs": 80000,
  "zdr": "disabled",
  "tags": [
    "production",
    "team-alpha"
  ]
}
EOF

{
  "status": "<string>",
  "url": "<string>",
  "urls_analyzed": [
    "<string>"
  ],
  "data": {},
  "metadata": {
    "numUrls": 123,
    "maxCrawlDepth": 123,
    "numSucceeded": 123,
    "numFailed": 123,
    "numSkipped": 123,
    "numBlocked": 123,
    "actionsApplied": [
      {
        "instruction": "<string>",
        "status": "applied",
        "method": "<string>",
        "targetDescription": "<string>",
        "completionEvidence": "<string>",
        "error": "<string>",
        "durationMs": 123
      }
    ]
  },
  "request_id": "3f1c2a6e-8b4d-4c1e-9f0a-2d7b5e6c8a91",
  "cache_metadata": {
    "status": "hit",
    "age_ms": 1
  },
  "partial": true,
  "key_metadata": {
    "credits_consumed": 123,
    "credits_remaining": 123
  }
}

{
  "message": "<string>",
  "error_code": "INPUT_VALIDATION_ERROR",
  "request_id": "3f1c2a6e-8b4d-4c1e-9f0a-2d7b5e6c8a91",
  "key_metadata": {
    "credits_consumed": 123,
    "credits_remaining": 123
  }
}

{
  "request_id": "3f1c2a6e-8b4d-4c1e-9f0a-2d7b5e6c8a91",
  "message": "<string>",
  "error_code": "INTERNAL_ERROR",
  "required_permission": "logs:read",
  "key_metadata": {
    "credits_consumed": 123,
    "credits_remaining": 123
  }
}

{
  "request_id": "3f1c2a6e-8b4d-4c1e-9f0a-2d7b5e6c8a91",
  "message": "<string>",
  "error_code": "INTERNAL_ERROR",
  "required_permission": "logs:read",
  "key_metadata": {
    "credits_consumed": 123,
    "credits_remaining": 123
  }
}

{
  "request_id": "3f1c2a6e-8b4d-4c1e-9f0a-2d7b5e6c8a91",
  "message": "<string>",
  "error_code": "INTERNAL_ERROR",
  "required_permission": "logs:read",
  "key_metadata": {
    "credits_consumed": 123,
    "credits_remaining": 123
  }
}

{
  "message": "<string>",
  "error_code": "RATE_LIMITED",
  "request_id": "3f1c2a6e-8b4d-4c1e-9f0a-2d7b5e6c8a91",
  "key_metadata": {
    "credits_consumed": 123,
    "credits_remaining": 123
  }
}

{
  "request_id": "3f1c2a6e-8b4d-4c1e-9f0a-2d7b5e6c8a91",
  "message": "<string>",
  "error_code": "INTERNAL_ERROR",
  "required_permission": "logs:read",
  "key_metadata": {
    "credits_consumed": 123,
    "credits_remaining": 123
  }
}

10 credits See the guide for examples and usage.

Authorizations

Authorization

string

header

required

Send Authorization: Bearer <API_KEY>. Keys have full access unless restricted to scopes.

Body

application/json

url

string<uri>

required

The starting website URL to crawl and extract from. Must include http:// or https://.

schema

object

required

JSON Schema (not an example object) for the returned object. Image fields include relevant page image references.

Show child attributes

Example:

{
  "type": "object",
  "properties": {
    "mission_statement": {
      "type": "string",
      "description": "The company's stated mission."
    },
    "case_studies": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "title": { "type": "string" },
          "url": { "type": "string" }
        },
        "required": ["title", "url"],
        "additionalProperties": false
      }
    }
  },
  "required": ["mission_statement", "case_studies"],
  "additionalProperties": false
}

instructions

string

Optional extraction guidance, such as which facts to prioritize or how to interpret fields in the schema.

Maximum string length: 2000

factCheck

boolean

default:false

Require facts stated on the page. Unsupported fields become null or empty.

followSubdomains

boolean

default:false

When true, follow links on subdomains of the starting URL's domain.

maxPages

integer

default:5

Maximum number of pages to analyze for extraction. Hard cap: 50. Defaults to 5.

Required range: 1 <= x <= 50

maxDepth

integer

Optional maximum link depth from the starting URL (0 = only the starting page). If omitted, there is no crawl depth limit.

Required range: x >= 0

pdf

object

PDF parsing options, including whether to parse PDFs and the inclusive page range.

Show child attributes

includeFrames

boolean

default:false

When true, iframe contents are included in Markdown before extraction.

maxAgeMs

integer

default:604800000

Return cached scrape results if a prior scrape for the same parameters is younger than this many milliseconds. Defaults to 7 days (604800000 ms).

Required range: 0 <= x <= 2592000000

waitForMs

integer

Optional browser wait time in milliseconds after initial page load for each crawled page.

Required range: 0 <= x <= 30000

settleAnimations

boolean

default:false

Wait briefly for CSS animations and transitions to settle before reading each page.

actions

(Wait · object | Perform · object | Scroll · object)[]

Browser steps before page discovery. Requires a paid plan; defaults the crawl budget to 110000 ms.

Maximum array length: 5

Browser action discriminated by do. Each variant exposes only its applicable fields.

Wait
Perform
Scroll

Show child attributes

stopAfterMs

integer

default:80000

Soft time budget for the crawl in milliseconds. Min: 10000 (10s). Max: 110000 (110s). Defaults to 80000 (80s), or 110000 (110s) when browser actions are provided.

Required range: 10000 <= x <= 110000

timeoutOpts

object

Request deadline and what to return when it passes.

Show child attributes

zdr

enum<string>

default:disabled

enabled turns on zero data retention. Returns 403 ZDR_NOT_ENABLED unless your organization has ZDR.

Available options:

enabled,

disabled

Response

Successful response

status

string

required

Always ok on success.

url

string

required

The starting URL that was analyzed

urls_analyzed

string[]

required

List of URLs whose Markdown was used for extraction

data

object

required

Extracted data matching the request schema

Show child attributes

metadata

object

required

Show child attributes

request_id

string<uuid>

required

Unique ID of this request, also in X-Request-Id. Include it when contacting support.

Example:

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

cache_metadata

object

required

Whether this response came from cache.

Show child attributes

partial

boolean

True when the timeout ended processing and this response contains only usable results completed so far. Unfinished results are omitted.

key_metadata

object

Credits this request used and your remaining balance.

Show child attributes

Web Data

Brand Data

People & News

Batches

Monitors

Webhook Deliveries

Account

Agent Feedback

Extract structured data

Authorizations

Body

Response