Domain Scraper
Try for free
30 minutes trial then $10.00/month - No credit card required now
Go to Store
Domain Scraper
ib4ngz/domain-scraper
Try for free
30 minutes trial then $10.00/month - No credit card required now
This actor scrapes unique domains from a list of provided URLs. It crawls each page, extracts domains, and stores them in a dataset. The actor respects a defined maximum depth and filters domains based on whether they are ICANN-approved and whether private domains are allowed.
You can access the Domain Scraper programmatically from your own applications by using the Apify API. You can choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "1.3",
5 "x-build-id": "HQAa0EReTIc3h9a9Q"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/ib4ngz~domain-scraper/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-ib4ngz-domain-scraper",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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/ib4ngz~domain-scraper/runs": {
50 "post": {
51 "operationId": "runs-sync-ib4ngz-domain-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/ib4ngz~domain-scraper/run-sync": {
93 "post": {
94 "operationId": "run-sync-ib4ngz-domain-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": "Start URLs",
139 "type": "array",
140 "description": "URLs to start with.",
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 "maxDepth": {
156 "title": "Maximum Depth",
157 "minimum": 1,
158 "type": "integer",
159 "description": "The maximum depth for crawling.",
160 "default": 1
161 },
162 "allowPrivateDomains": {
163 "title": "Allow Private Domains",
164 "type": "boolean",
165 "description": "Whether to allow private domains (default is false).",
166 "default": false
167 },
168 "isIcann": {
169 "title": "ICANN Domains Only",
170 "type": "boolean",
171 "description": "Whether to only process ICANN domains (default is true).",
172 "default": true
173 },
174 "crawlerType": {
175 "title": "Crawler Type",
176 "enum": [
177 "Crawlee + Cheerio",
178 "Crawlee + Puppeteer + Chrome"
179 ],
180 "type": "string",
181 "description": "Select the type of crawler to use.",
182 "default": "Crawlee + Cheerio"
183 },
184 "proxyConfiguration": {
185 "title": "Proxy configuration",
186 "type": "object",
187 "description": "Select proxies to be used by your crawler."
188 },
189 "minConcurrency": {
190 "title": "Minimum Concurrency",
191 "minimum": 1,
192 "type": "integer",
193 "description": "The minimum number of concurrent requests or pages being processed.",
194 "default": 1
195 },
196 "maxConcurrency": {
197 "title": "Maximum Concurrency",
198 "minimum": 1,
199 "type": "integer",
200 "description": "The maximum number of concurrent requests or pages being processed.",
201 "default": 10
202 }
203 }
204 },
205 "runsResponseSchema": {
206 "type": "object",
207 "properties": {
208 "data": {
209 "type": "object",
210 "properties": {
211 "id": {
212 "type": "string"
213 },
214 "actId": {
215 "type": "string"
216 },
217 "userId": {
218 "type": "string"
219 },
220 "startedAt": {
221 "type": "string",
222 "format": "date-time",
223 "example": "2025-01-08T00:00:00.000Z"
224 },
225 "finishedAt": {
226 "type": "string",
227 "format": "date-time",
228 "example": "2025-01-08T00:00:00.000Z"
229 },
230 "status": {
231 "type": "string",
232 "example": "READY"
233 },
234 "meta": {
235 "type": "object",
236 "properties": {
237 "origin": {
238 "type": "string",
239 "example": "API"
240 },
241 "userAgent": {
242 "type": "string"
243 }
244 }
245 },
246 "stats": {
247 "type": "object",
248 "properties": {
249 "inputBodyLen": {
250 "type": "integer",
251 "example": 2000
252 },
253 "rebootCount": {
254 "type": "integer",
255 "example": 0
256 },
257 "restartCount": {
258 "type": "integer",
259 "example": 0
260 },
261 "resurrectCount": {
262 "type": "integer",
263 "example": 0
264 },
265 "computeUnits": {
266 "type": "integer",
267 "example": 0
268 }
269 }
270 },
271 "options": {
272 "type": "object",
273 "properties": {
274 "build": {
275 "type": "string",
276 "example": "latest"
277 },
278 "timeoutSecs": {
279 "type": "integer",
280 "example": 300
281 },
282 "memoryMbytes": {
283 "type": "integer",
284 "example": 1024
285 },
286 "diskMbytes": {
287 "type": "integer",
288 "example": 2048
289 }
290 }
291 },
292 "buildId": {
293 "type": "string"
294 },
295 "defaultKeyValueStoreId": {
296 "type": "string"
297 },
298 "defaultDatasetId": {
299 "type": "string"
300 },
301 "defaultRequestQueueId": {
302 "type": "string"
303 },
304 "buildNumber": {
305 "type": "string",
306 "example": "1.0.0"
307 },
308 "containerUrl": {
309 "type": "string"
310 },
311 "usage": {
312 "type": "object",
313 "properties": {
314 "ACTOR_COMPUTE_UNITS": {
315 "type": "integer",
316 "example": 0
317 },
318 "DATASET_READS": {
319 "type": "integer",
320 "example": 0
321 },
322 "DATASET_WRITES": {
323 "type": "integer",
324 "example": 0
325 },
326 "KEY_VALUE_STORE_READS": {
327 "type": "integer",
328 "example": 0
329 },
330 "KEY_VALUE_STORE_WRITES": {
331 "type": "integer",
332 "example": 1
333 },
334 "KEY_VALUE_STORE_LISTS": {
335 "type": "integer",
336 "example": 0
337 },
338 "REQUEST_QUEUE_READS": {
339 "type": "integer",
340 "example": 0
341 },
342 "REQUEST_QUEUE_WRITES": {
343 "type": "integer",
344 "example": 0
345 },
346 "DATA_TRANSFER_INTERNAL_GBYTES": {
347 "type": "integer",
348 "example": 0
349 },
350 "DATA_TRANSFER_EXTERNAL_GBYTES": {
351 "type": "integer",
352 "example": 0
353 },
354 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
355 "type": "integer",
356 "example": 0
357 },
358 "PROXY_SERPS": {
359 "type": "integer",
360 "example": 0
361 }
362 }
363 },
364 "usageTotalUsd": {
365 "type": "number",
366 "example": 0.00005
367 },
368 "usageUsd": {
369 "type": "object",
370 "properties": {
371 "ACTOR_COMPUTE_UNITS": {
372 "type": "integer",
373 "example": 0
374 },
375 "DATASET_READS": {
376 "type": "integer",
377 "example": 0
378 },
379 "DATASET_WRITES": {
380 "type": "integer",
381 "example": 0
382 },
383 "KEY_VALUE_STORE_READS": {
384 "type": "integer",
385 "example": 0
386 },
387 "KEY_VALUE_STORE_WRITES": {
388 "type": "number",
389 "example": 0.00005
390 },
391 "KEY_VALUE_STORE_LISTS": {
392 "type": "integer",
393 "example": 0
394 },
395 "REQUEST_QUEUE_READS": {
396 "type": "integer",
397 "example": 0
398 },
399 "REQUEST_QUEUE_WRITES": {
400 "type": "integer",
401 "example": 0
402 },
403 "DATA_TRANSFER_INTERNAL_GBYTES": {
404 "type": "integer",
405 "example": 0
406 },
407 "DATA_TRANSFER_EXTERNAL_GBYTES": {
408 "type": "integer",
409 "example": 0
410 },
411 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
412 "type": "integer",
413 "example": 0
414 },
415 "PROXY_SERPS": {
416 "type": "integer",
417 "example": 0
418 }
419 }
420 }
421 }
422 }
423 }
424 }
425 }
426 }
427}Domain 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 Domain 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
Iqbal RMaintained by Community
Actor Metrics
6 monthly users
-
1 star
>99% runs succeeded
Created in Dec 2024
Modified 21 days ago
Categories
