AI Web Scraper - Powered by Crawl4AI
Try for free
Pay $25.00 for 1,000 Results
Go to Store
AI Web Scraper - Powered by Crawl4AI
raizen/ai-web-scraper
Try for free
Pay $25.00 for 1,000 Results
A blazing-fast AI web scraper powered by Crawl4AI. Perfect for LLMs, AI agents, AI automation, model training, sentiment analysis, and content generation. Supports deep crawling, multiple extraction strategies and flexible output (Markdown/JSON). Seamlessly integrates with Make.com, n8n, and Zapier.
Developer
Raizen TechnologyMaintained by Community
Actor Metrics
3 monthly users
No reviews yet
No bookmarks yet
Created in Mar 2025
Modified 6 hours ago
Categories
You can access the AI Web Scraper - Powered by Crawl4AI programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "0.0",
5 "x-build-id": "2HNL6fAhlc7HcHbMw"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/raizen~ai-web-scraper/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-raizen-ai-web-scraper",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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/raizen~ai-web-scraper/runs": {
50 "post": {
51 "operationId": "runs-sync-raizen-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/raizen~ai-web-scraper/run-sync": {
93 "post": {
94 "operationId": "run-sync-raizen-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 "startUrls"
135 ],
136 "properties": {
137 "startUrls": {
138 "title": "URLs to Scrape",
139 "type": "array",
140 "description": "List of webpages to scrape.",
141 "items": {
142 "type": "object",
143 "required": [
144 "url"
145 ],
146 "properties": {
147 "url": {
148 "type": "string",
149 "title": "URL of a web page",
150 "format": "uri"
151 }
152 }
153 }
154 },
155 "extractionStrategy": {
156 "title": "Extraction Strategy",
157 "enum": [
158 "SimpleExtractionStrategy",
159 "LLMExtractionStrategy",
160 "JsonCssExtractionStrategy",
161 "JsonXPathExtractionStrategy"
162 ],
163 "type": "string",
164 "description": "Select how content is extracted.",
165 "default": "SimpleExtractionStrategy"
166 },
167 "crawlStrategy": {
168 "title": "Crawl Strategy",
169 "enum": [
170 "SimpleCrawlStrategy",
171 "BFSDeepCrawlStrategy",
172 "DFSDeepCrawlStrategy",
173 "BestFirstCrawlingStrategy"
174 ],
175 "type": "string",
176 "description": "Select how pages are crawled.",
177 "default": "SimpleCrawlStrategy"
178 },
179 "browserConfig": {
180 "title": "Browser Configuration",
181 "type": "object",
182 "description": "Browser settings as JSON object."
183 },
184 "crawlerConfig": {
185 "title": "Crawler Configuration",
186 "type": "object",
187 "description": "Crawler settings as JSON object."
188 },
189 "deepCrawlConfig": {
190 "title": "Deep Crawl Configuration",
191 "type": "object",
192 "description": "Settings for deep crawling when using BFS, DFS, or Best-First Strategies."
193 },
194 "markdownConfig": {
195 "title": "Markdown Generator Configuration",
196 "type": "object",
197 "description": "Markdown settings as JSON object."
198 },
199 "contentFilterConfig": {
200 "title": "Content Filter Configuration",
201 "type": "object",
202 "description": "Content filter settings as JSON object."
203 },
204 "userAgentConfig": {
205 "title": "User Agent Configuration",
206 "type": "object",
207 "description": "User agent settings for browser requests."
208 },
209 "llmConfig": {
210 "title": "LLM Configuration",
211 "type": "object",
212 "description": "Configure LLM usage for content extraction."
213 },
214 "extractionSchema": {
215 "title": "Extraction Schema",
216 "type": "object",
217 "description": "Define custom extraction rules when using JsonCssExtractionStrategy or JsonXPathExtractionStrategy."
218 },
219 "session_id": {
220 "title": "Session ID",
221 "type": "string",
222 "description": "Use a session ID to persist browser state across multiple requests.",
223 "default": ""
224 }
225 }
226 },
227 "runsResponseSchema": {
228 "type": "object",
229 "properties": {
230 "data": {
231 "type": "object",
232 "properties": {
233 "id": {
234 "type": "string"
235 },
236 "actId": {
237 "type": "string"
238 },
239 "userId": {
240 "type": "string"
241 },
242 "startedAt": {
243 "type": "string",
244 "format": "date-time",
245 "example": "2025-01-08T00:00:00.000Z"
246 },
247 "finishedAt": {
248 "type": "string",
249 "format": "date-time",
250 "example": "2025-01-08T00:00:00.000Z"
251 },
252 "status": {
253 "type": "string",
254 "example": "READY"
255 },
256 "meta": {
257 "type": "object",
258 "properties": {
259 "origin": {
260 "type": "string",
261 "example": "API"
262 },
263 "userAgent": {
264 "type": "string"
265 }
266 }
267 },
268 "stats": {
269 "type": "object",
270 "properties": {
271 "inputBodyLen": {
272 "type": "integer",
273 "example": 2000
274 },
275 "rebootCount": {
276 "type": "integer",
277 "example": 0
278 },
279 "restartCount": {
280 "type": "integer",
281 "example": 0
282 },
283 "resurrectCount": {
284 "type": "integer",
285 "example": 0
286 },
287 "computeUnits": {
288 "type": "integer",
289 "example": 0
290 }
291 }
292 },
293 "options": {
294 "type": "object",
295 "properties": {
296 "build": {
297 "type": "string",
298 "example": "latest"
299 },
300 "timeoutSecs": {
301 "type": "integer",
302 "example": 300
303 },
304 "memoryMbytes": {
305 "type": "integer",
306 "example": 1024
307 },
308 "diskMbytes": {
309 "type": "integer",
310 "example": 2048
311 }
312 }
313 },
314 "buildId": {
315 "type": "string"
316 },
317 "defaultKeyValueStoreId": {
318 "type": "string"
319 },
320 "defaultDatasetId": {
321 "type": "string"
322 },
323 "defaultRequestQueueId": {
324 "type": "string"
325 },
326 "buildNumber": {
327 "type": "string",
328 "example": "1.0.0"
329 },
330 "containerUrl": {
331 "type": "string"
332 },
333 "usage": {
334 "type": "object",
335 "properties": {
336 "ACTOR_COMPUTE_UNITS": {
337 "type": "integer",
338 "example": 0
339 },
340 "DATASET_READS": {
341 "type": "integer",
342 "example": 0
343 },
344 "DATASET_WRITES": {
345 "type": "integer",
346 "example": 0
347 },
348 "KEY_VALUE_STORE_READS": {
349 "type": "integer",
350 "example": 0
351 },
352 "KEY_VALUE_STORE_WRITES": {
353 "type": "integer",
354 "example": 1
355 },
356 "KEY_VALUE_STORE_LISTS": {
357 "type": "integer",
358 "example": 0
359 },
360 "REQUEST_QUEUE_READS": {
361 "type": "integer",
362 "example": 0
363 },
364 "REQUEST_QUEUE_WRITES": {
365 "type": "integer",
366 "example": 0
367 },
368 "DATA_TRANSFER_INTERNAL_GBYTES": {
369 "type": "integer",
370 "example": 0
371 },
372 "DATA_TRANSFER_EXTERNAL_GBYTES": {
373 "type": "integer",
374 "example": 0
375 },
376 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
377 "type": "integer",
378 "example": 0
379 },
380 "PROXY_SERPS": {
381 "type": "integer",
382 "example": 0
383 }
384 }
385 },
386 "usageTotalUsd": {
387 "type": "number",
388 "example": 0.00005
389 },
390 "usageUsd": {
391 "type": "object",
392 "properties": {
393 "ACTOR_COMPUTE_UNITS": {
394 "type": "integer",
395 "example": 0
396 },
397 "DATASET_READS": {
398 "type": "integer",
399 "example": 0
400 },
401 "DATASET_WRITES": {
402 "type": "integer",
403 "example": 0
404 },
405 "KEY_VALUE_STORE_READS": {
406 "type": "integer",
407 "example": 0
408 },
409 "KEY_VALUE_STORE_WRITES": {
410 "type": "number",
411 "example": 0.00005
412 },
413 "KEY_VALUE_STORE_LISTS": {
414 "type": "integer",
415 "example": 0
416 },
417 "REQUEST_QUEUE_READS": {
418 "type": "integer",
419 "example": 0
420 },
421 "REQUEST_QUEUE_WRITES": {
422 "type": "integer",
423 "example": 0
424 },
425 "DATA_TRANSFER_INTERNAL_GBYTES": {
426 "type": "integer",
427 "example": 0
428 },
429 "DATA_TRANSFER_EXTERNAL_GBYTES": {
430 "type": "integer",
431 "example": 0
432 },
433 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
434 "type": "integer",
435 "example": 0
436 },
437 "PROXY_SERPS": {
438 "type": "integer",
439 "example": 0
440 }
441 }
442 }
443 }
444 }
445 }
446 }
447 }
448 }
449}AI Web Scraper - Crawl4AI for LLMs, AI Agents & Automation 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 - Powered by Crawl4AI 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:
