AI-Powered Web Content & Link Extractor
Try for free
Pay $10.00 for 1,000 results
Go to Store
AI-Powered Web Content & Link Extractor
scrapercoder/ai-powered-web-content-link-extractor
Try for free
Pay $10.00 for 1,000 results
Crawls websites to extract clean, structured content for AI/LLM use, ideal for training datasets, knowledge bases, and RAG systems. Json output includes: * text: Normalized page content * links: Extracted sub-URLs
You can access the AI-Powered Web Content & Link Extractor programmatically from your own applications by using the Apify API. You can choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "0.0",
5 "x-build-id": "vNcg1ReCnpGgMJ5AC"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/scrapercoder~ai-powered-web-content-link-extractor/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-scrapercoder-ai-powered-web-content-link-extractor",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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/scrapercoder~ai-powered-web-content-link-extractor/runs": {
50 "post": {
51 "operationId": "runs-sync-scrapercoder-ai-powered-web-content-link-extractor",
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/scrapercoder~ai-powered-web-content-link-extractor/run-sync": {
93 "post": {
94 "operationId": "run-sync-scrapercoder-ai-powered-web-content-link-extractor",
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 ],
136 "properties": {
137 "start_urls": {
138 "title": "Start URLs",
139 "type": "array",
140 "description": "URLs to crawl with optional domain information",
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 "max_concurrent": {
156 "title": "Max Concurrent Requests",
157 "minimum": 1,
158 "maximum": 50,
159 "type": "integer",
160 "description": "Maximum number of concurrent crawls",
161 "default": 5
162 }
163 }
164 },
165 "runsResponseSchema": {
166 "type": "object",
167 "properties": {
168 "data": {
169 "type": "object",
170 "properties": {
171 "id": {
172 "type": "string"
173 },
174 "actId": {
175 "type": "string"
176 },
177 "userId": {
178 "type": "string"
179 },
180 "startedAt": {
181 "type": "string",
182 "format": "date-time",
183 "example": "2025-01-08T00:00:00.000Z"
184 },
185 "finishedAt": {
186 "type": "string",
187 "format": "date-time",
188 "example": "2025-01-08T00:00:00.000Z"
189 },
190 "status": {
191 "type": "string",
192 "example": "READY"
193 },
194 "meta": {
195 "type": "object",
196 "properties": {
197 "origin": {
198 "type": "string",
199 "example": "API"
200 },
201 "userAgent": {
202 "type": "string"
203 }
204 }
205 },
206 "stats": {
207 "type": "object",
208 "properties": {
209 "inputBodyLen": {
210 "type": "integer",
211 "example": 2000
212 },
213 "rebootCount": {
214 "type": "integer",
215 "example": 0
216 },
217 "restartCount": {
218 "type": "integer",
219 "example": 0
220 },
221 "resurrectCount": {
222 "type": "integer",
223 "example": 0
224 },
225 "computeUnits": {
226 "type": "integer",
227 "example": 0
228 }
229 }
230 },
231 "options": {
232 "type": "object",
233 "properties": {
234 "build": {
235 "type": "string",
236 "example": "latest"
237 },
238 "timeoutSecs": {
239 "type": "integer",
240 "example": 300
241 },
242 "memoryMbytes": {
243 "type": "integer",
244 "example": 1024
245 },
246 "diskMbytes": {
247 "type": "integer",
248 "example": 2048
249 }
250 }
251 },
252 "buildId": {
253 "type": "string"
254 },
255 "defaultKeyValueStoreId": {
256 "type": "string"
257 },
258 "defaultDatasetId": {
259 "type": "string"
260 },
261 "defaultRequestQueueId": {
262 "type": "string"
263 },
264 "buildNumber": {
265 "type": "string",
266 "example": "1.0.0"
267 },
268 "containerUrl": {
269 "type": "string"
270 },
271 "usage": {
272 "type": "object",
273 "properties": {
274 "ACTOR_COMPUTE_UNITS": {
275 "type": "integer",
276 "example": 0
277 },
278 "DATASET_READS": {
279 "type": "integer",
280 "example": 0
281 },
282 "DATASET_WRITES": {
283 "type": "integer",
284 "example": 0
285 },
286 "KEY_VALUE_STORE_READS": {
287 "type": "integer",
288 "example": 0
289 },
290 "KEY_VALUE_STORE_WRITES": {
291 "type": "integer",
292 "example": 1
293 },
294 "KEY_VALUE_STORE_LISTS": {
295 "type": "integer",
296 "example": 0
297 },
298 "REQUEST_QUEUE_READS": {
299 "type": "integer",
300 "example": 0
301 },
302 "REQUEST_QUEUE_WRITES": {
303 "type": "integer",
304 "example": 0
305 },
306 "DATA_TRANSFER_INTERNAL_GBYTES": {
307 "type": "integer",
308 "example": 0
309 },
310 "DATA_TRANSFER_EXTERNAL_GBYTES": {
311 "type": "integer",
312 "example": 0
313 },
314 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
315 "type": "integer",
316 "example": 0
317 },
318 "PROXY_SERPS": {
319 "type": "integer",
320 "example": 0
321 }
322 }
323 },
324 "usageTotalUsd": {
325 "type": "number",
326 "example": 0.00005
327 },
328 "usageUsd": {
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": "number",
349 "example": 0.00005
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 }
382 }
383 }
384 }
385 }
386 }
387}AI-Powered Web Content & Link Extractor 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-Powered Web Content & Link Extractor 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
wallnut.aiMaintained by Community
Actor Metrics
10 monthly users
-
2 bookmarks
>99% runs succeeded
Created in Feb 2025
Modified 14 days ago
Categories
