AI Web Scraper
Go to Store
This Actor is deprecated
This Actor is unavailable because the developer has decided to deprecate it. Would you like to try a similar Actor instead?
See alternative ActorsAI Web Scraper
vulnv/ai-web-scraper
Scrape structured data effortlessly - just describe what you need in plain language, and get precise results tailored to your request. Simplify data extraction with a tool designed for ease and accuracy, no coding required.
You can access the AI Web Scraper programmatically from your own applications by using the Apify API. You can choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "1.0",
5 "x-build-id": "eRP4kqYL3wVCFV40c"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/vulnv~ai-web-scraper/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-vulnv-ai-web-scraper",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$ref": "#/components/schemas/inputSchema"
27 }
28 }
29 }
30 },
31 "parameters": [
32 {
33 "name": "token",
34 "in": "query",
35 "required": true,
36 "schema": {
37 "type": "string"
38 },
39 "description": "Enter your Apify token here"
40 }
41 ],
42 "responses": {
43 "200": {
44 "description": "OK"
45 }
46 }
47 }
48 },
49 "/acts/vulnv~ai-web-scraper/runs": {
50 "post": {
51 "operationId": "runs-sync-vulnv-ai-web-scraper",
52 "x-openai-isConsequential": false,
53 "summary": "Executes an Actor and returns information about the initiated run in response.",
54 "tags": [
55 "Run Actor"
56 ],
57 "requestBody": {
58 "required": true,
59 "content": {
60 "application/json": {
61 "schema": {
62 "$ref": "#/components/schemas/inputSchema"
63 }
64 }
65 }
66 },
67 "parameters": [
68 {
69 "name": "token",
70 "in": "query",
71 "required": true,
72 "schema": {
73 "type": "string"
74 },
75 "description": "Enter your Apify token here"
76 }
77 ],
78 "responses": {
79 "200": {
80 "description": "OK",
81 "content": {
82 "application/json": {
83 "schema": {
84 "$ref": "#/components/schemas/runsResponseSchema"
85 }
86 }
87 }
88 }
89 }
90 }
91 },
92 "/acts/vulnv~ai-web-scraper/run-sync": {
93 "post": {
94 "operationId": "run-sync-vulnv-ai-web-scraper",
95 "x-openai-isConsequential": false,
96 "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
97 "tags": [
98 "Run Actor"
99 ],
100 "requestBody": {
101 "required": true,
102 "content": {
103 "application/json": {
104 "schema": {
105 "$ref": "#/components/schemas/inputSchema"
106 }
107 }
108 }
109 },
110 "parameters": [
111 {
112 "name": "token",
113 "in": "query",
114 "required": true,
115 "schema": {
116 "type": "string"
117 },
118 "description": "Enter your Apify token here"
119 }
120 ],
121 "responses": {
122 "200": {
123 "description": "OK"
124 }
125 }
126 }
127 }
128 },
129 "components": {
130 "schemas": {
131 "inputSchema": {
132 "type": "object",
133 "required": [
134 "start_urls",
135 "prompt",
136 "api_key",
137 "model",
138 "max_depth"
139 ],
140 "properties": {
141 "start_urls": {
142 "title": "Start URLs",
143 "type": "array",
144 "description": "URLs to start with",
145 "items": {
146 "type": "object",
147 "required": [
148 "url"
149 ],
150 "properties": {
151 "url": {
152 "type": "string",
153 "title": "URL of a web page",
154 "format": "uri"
155 }
156 }
157 }
158 },
159 "prompt": {
160 "title": "Prompt",
161 "type": "string",
162 "description": "Describe the desired output of the scraper, for example 'Find all articles and their authors'.",
163 "default": "List me all the features with their description."
164 },
165 "api_key": {
166 "title": "OpenAI API Key",
167 "type": "string",
168 "description": "API key for OpenAI"
169 },
170 "model": {
171 "title": "Model",
172 "enum": [
173 "gpt-4o",
174 "gpt-4o-mini",
175 "o1"
176 ],
177 "type": "string",
178 "description": "The model to use for the OpenAI API",
179 "default": "gpt-4o-mini"
180 },
181 "crawler_type": {
182 "title": "Crawler type",
183 "enum": [
184 "playwright",
185 "http"
186 ],
187 "type": "string",
188 "description": "Type of the crawler to use",
189 "default": "http"
190 },
191 "max_depth": {
192 "title": "Maximum depth",
193 "type": "integer",
194 "description": "Depth to which to scrape to",
195 "default": 0
196 },
197 "initial_cookies": {
198 "title": "Initial cookies",
199 "type": "string",
200 "description": "Cookies that will be pre-set to all pages the scraper opens. This is useful for pages that require login. The value is expected to be a JSON array of objects with name and value properties. For example: [{\"name\": \"cookieName\", \"value\": \"cookieValue\"}].\n\nYou can use the EditThisCookie browser extension to copy browser cookies in this format, and paste it here.",
201 "default": "[]"
202 },
203 "proxy_configuration": {
204 "title": "Proxy configuration",
205 "type": "object",
206 "description": "Select proxies to be used by your crawler."
207 },
208 "save_html_to_key_value_store": {
209 "title": "Save HTML to Key-Value store",
210 "type": "boolean",
211 "description": "If enabled, the crawler stores full transformed HTML of all pages found to the default key-value store and saves links to the files as htmlUrl field in the output dataset. Storing HTML in key-value store is preferred to storing it into the dataset with the saveHtml option, because there's no size limit and it's easier for debugging as you can easily view the HTML.",
212 "default": false
213 },
214 "save_markdown_to_key_value_store": {
215 "title": "Save Markdown",
216 "type": "boolean",
217 "description": "If enabled, the crawler converts the transformed HTML of all pages found to Markdown, and stores it under the markdown field in the output dataset.",
218 "default": false
219 }
220 }
221 },
222 "runsResponseSchema": {
223 "type": "object",
224 "properties": {
225 "data": {
226 "type": "object",
227 "properties": {
228 "id": {
229 "type": "string"
230 },
231 "actId": {
232 "type": "string"
233 },
234 "userId": {
235 "type": "string"
236 },
237 "startedAt": {
238 "type": "string",
239 "format": "date-time",
240 "example": "2025-01-08T00:00:00.000Z"
241 },
242 "finishedAt": {
243 "type": "string",
244 "format": "date-time",
245 "example": "2025-01-08T00:00:00.000Z"
246 },
247 "status": {
248 "type": "string",
249 "example": "READY"
250 },
251 "meta": {
252 "type": "object",
253 "properties": {
254 "origin": {
255 "type": "string",
256 "example": "API"
257 },
258 "userAgent": {
259 "type": "string"
260 }
261 }
262 },
263 "stats": {
264 "type": "object",
265 "properties": {
266 "inputBodyLen": {
267 "type": "integer",
268 "example": 2000
269 },
270 "rebootCount": {
271 "type": "integer",
272 "example": 0
273 },
274 "restartCount": {
275 "type": "integer",
276 "example": 0
277 },
278 "resurrectCount": {
279 "type": "integer",
280 "example": 0
281 },
282 "computeUnits": {
283 "type": "integer",
284 "example": 0
285 }
286 }
287 },
288 "options": {
289 "type": "object",
290 "properties": {
291 "build": {
292 "type": "string",
293 "example": "latest"
294 },
295 "timeoutSecs": {
296 "type": "integer",
297 "example": 300
298 },
299 "memoryMbytes": {
300 "type": "integer",
301 "example": 1024
302 },
303 "diskMbytes": {
304 "type": "integer",
305 "example": 2048
306 }
307 }
308 },
309 "buildId": {
310 "type": "string"
311 },
312 "defaultKeyValueStoreId": {
313 "type": "string"
314 },
315 "defaultDatasetId": {
316 "type": "string"
317 },
318 "defaultRequestQueueId": {
319 "type": "string"
320 },
321 "buildNumber": {
322 "type": "string",
323 "example": "1.0.0"
324 },
325 "containerUrl": {
326 "type": "string"
327 },
328 "usage": {
329 "type": "object",
330 "properties": {
331 "ACTOR_COMPUTE_UNITS": {
332 "type": "integer",
333 "example": 0
334 },
335 "DATASET_READS": {
336 "type": "integer",
337 "example": 0
338 },
339 "DATASET_WRITES": {
340 "type": "integer",
341 "example": 0
342 },
343 "KEY_VALUE_STORE_READS": {
344 "type": "integer",
345 "example": 0
346 },
347 "KEY_VALUE_STORE_WRITES": {
348 "type": "integer",
349 "example": 1
350 },
351 "KEY_VALUE_STORE_LISTS": {
352 "type": "integer",
353 "example": 0
354 },
355 "REQUEST_QUEUE_READS": {
356 "type": "integer",
357 "example": 0
358 },
359 "REQUEST_QUEUE_WRITES": {
360 "type": "integer",
361 "example": 0
362 },
363 "DATA_TRANSFER_INTERNAL_GBYTES": {
364 "type": "integer",
365 "example": 0
366 },
367 "DATA_TRANSFER_EXTERNAL_GBYTES": {
368 "type": "integer",
369 "example": 0
370 },
371 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
372 "type": "integer",
373 "example": 0
374 },
375 "PROXY_SERPS": {
376 "type": "integer",
377 "example": 0
378 }
379 }
380 },
381 "usageTotalUsd": {
382 "type": "number",
383 "example": 0.00005
384 },
385 "usageUsd": {
386 "type": "object",
387 "properties": {
388 "ACTOR_COMPUTE_UNITS": {
389 "type": "integer",
390 "example": 0
391 },
392 "DATASET_READS": {
393 "type": "integer",
394 "example": 0
395 },
396 "DATASET_WRITES": {
397 "type": "integer",
398 "example": 0
399 },
400 "KEY_VALUE_STORE_READS": {
401 "type": "integer",
402 "example": 0
403 },
404 "KEY_VALUE_STORE_WRITES": {
405 "type": "number",
406 "example": 0.00005
407 },
408 "KEY_VALUE_STORE_LISTS": {
409 "type": "integer",
410 "example": 0
411 },
412 "REQUEST_QUEUE_READS": {
413 "type": "integer",
414 "example": 0
415 },
416 "REQUEST_QUEUE_WRITES": {
417 "type": "integer",
418 "example": 0
419 },
420 "DATA_TRANSFER_INTERNAL_GBYTES": {
421 "type": "integer",
422 "example": 0
423 },
424 "DATA_TRANSFER_EXTERNAL_GBYTES": {
425 "type": "integer",
426 "example": 0
427 },
428 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
429 "type": "integer",
430 "example": 0
431 },
432 "PROXY_SERPS": {
433 "type": "integer",
434 "example": 0
435 }
436 }
437 }
438 }
439 }
440 }
441 }
442 }
443 }
444}AI Web Scraper OpenAPI definition
OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for AI Web Scraper from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients:
Developer
VulnVMaintained by Community
Categories
