RegExp Scraper
Try for free
30 minutes trial then $25.00/month - No credit card required now
Go to Store
RegExp Scraper
ib4ngz/regexp-scraper
Try for free
30 minutes trial then $25.00/month - No credit card required now
This actor scrapes data from a list of provided URLs using regular expressions for precise and customizable pattern matching. It can handle both static and dynamic web pages and supports depth-based crawling to explore links and extract data from multiple levels of the web.
You can access the RegExp Scraper programmatically from your own applications by using the Apify API. You can choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "1.0",
5 "x-build-id": "E1cjNZGdpdt0U8YAI"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/ib4ngz~regexp-scraper/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-ib4ngz-regexp-scraper",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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~regexp-scraper/runs": {
50 "post": {
51 "operationId": "runs-sync-ib4ngz-regexp-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~regexp-scraper/run-sync": {
93 "post": {
94 "operationId": "run-sync-ib4ngz-regexp-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 "patterns"
136 ],
137 "properties": {
138 "startUrls": {
139 "title": "Start URLs",
140 "type": "array",
141 "description": "URLs to start with.",
142 "items": {
143 "type": "object",
144 "required": [
145 "url"
146 ],
147 "properties": {
148 "url": {
149 "type": "string",
150 "title": "URL of a web page",
151 "format": "uri"
152 }
153 }
154 }
155 },
156 "maxDepth": {
157 "title": "Maximum Depth",
158 "minimum": 1,
159 "type": "integer",
160 "description": "The maximum depth for crawling.",
161 "default": 1
162 },
163 "patterns": {
164 "title": "Regex Patterns",
165 "type": "string",
166 "description": "Patterns to search in the HTML content. Each pattern should be on a new line."
167 },
168 "crawlerType": {
169 "title": "Crawler Type",
170 "enum": [
171 "Crawlee + Cheerio",
172 "Crawlee + Puppeteer + Chrome"
173 ],
174 "type": "string",
175 "description": "Select the type of crawler to use.",
176 "default": "Crawlee + Cheerio"
177 },
178 "proxyConfiguration": {
179 "title": "Proxy configuration",
180 "type": "object",
181 "description": "Select proxies to be used by your crawler."
182 },
183 "minConcurrency": {
184 "title": "Minimum Concurrency",
185 "minimum": 1,
186 "type": "integer",
187 "description": "The minimum number of concurrent requests or pages being processed.",
188 "default": 1
189 },
190 "maxConcurrency": {
191 "title": "Maximum Concurrency",
192 "minimum": 1,
193 "type": "integer",
194 "description": "The maximum number of concurrent requests or pages being processed.",
195 "default": 10
196 }
197 }
198 },
199 "runsResponseSchema": {
200 "type": "object",
201 "properties": {
202 "data": {
203 "type": "object",
204 "properties": {
205 "id": {
206 "type": "string"
207 },
208 "actId": {
209 "type": "string"
210 },
211 "userId": {
212 "type": "string"
213 },
214 "startedAt": {
215 "type": "string",
216 "format": "date-time",
217 "example": "2025-01-08T00:00:00.000Z"
218 },
219 "finishedAt": {
220 "type": "string",
221 "format": "date-time",
222 "example": "2025-01-08T00:00:00.000Z"
223 },
224 "status": {
225 "type": "string",
226 "example": "READY"
227 },
228 "meta": {
229 "type": "object",
230 "properties": {
231 "origin": {
232 "type": "string",
233 "example": "API"
234 },
235 "userAgent": {
236 "type": "string"
237 }
238 }
239 },
240 "stats": {
241 "type": "object",
242 "properties": {
243 "inputBodyLen": {
244 "type": "integer",
245 "example": 2000
246 },
247 "rebootCount": {
248 "type": "integer",
249 "example": 0
250 },
251 "restartCount": {
252 "type": "integer",
253 "example": 0
254 },
255 "resurrectCount": {
256 "type": "integer",
257 "example": 0
258 },
259 "computeUnits": {
260 "type": "integer",
261 "example": 0
262 }
263 }
264 },
265 "options": {
266 "type": "object",
267 "properties": {
268 "build": {
269 "type": "string",
270 "example": "latest"
271 },
272 "timeoutSecs": {
273 "type": "integer",
274 "example": 300
275 },
276 "memoryMbytes": {
277 "type": "integer",
278 "example": 1024
279 },
280 "diskMbytes": {
281 "type": "integer",
282 "example": 2048
283 }
284 }
285 },
286 "buildId": {
287 "type": "string"
288 },
289 "defaultKeyValueStoreId": {
290 "type": "string"
291 },
292 "defaultDatasetId": {
293 "type": "string"
294 },
295 "defaultRequestQueueId": {
296 "type": "string"
297 },
298 "buildNumber": {
299 "type": "string",
300 "example": "1.0.0"
301 },
302 "containerUrl": {
303 "type": "string"
304 },
305 "usage": {
306 "type": "object",
307 "properties": {
308 "ACTOR_COMPUTE_UNITS": {
309 "type": "integer",
310 "example": 0
311 },
312 "DATASET_READS": {
313 "type": "integer",
314 "example": 0
315 },
316 "DATASET_WRITES": {
317 "type": "integer",
318 "example": 0
319 },
320 "KEY_VALUE_STORE_READS": {
321 "type": "integer",
322 "example": 0
323 },
324 "KEY_VALUE_STORE_WRITES": {
325 "type": "integer",
326 "example": 1
327 },
328 "KEY_VALUE_STORE_LISTS": {
329 "type": "integer",
330 "example": 0
331 },
332 "REQUEST_QUEUE_READS": {
333 "type": "integer",
334 "example": 0
335 },
336 "REQUEST_QUEUE_WRITES": {
337 "type": "integer",
338 "example": 0
339 },
340 "DATA_TRANSFER_INTERNAL_GBYTES": {
341 "type": "integer",
342 "example": 0
343 },
344 "DATA_TRANSFER_EXTERNAL_GBYTES": {
345 "type": "integer",
346 "example": 0
347 },
348 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
349 "type": "integer",
350 "example": 0
351 },
352 "PROXY_SERPS": {
353 "type": "integer",
354 "example": 0
355 }
356 }
357 },
358 "usageTotalUsd": {
359 "type": "number",
360 "example": 0.00005
361 },
362 "usageUsd": {
363 "type": "object",
364 "properties": {
365 "ACTOR_COMPUTE_UNITS": {
366 "type": "integer",
367 "example": 0
368 },
369 "DATASET_READS": {
370 "type": "integer",
371 "example": 0
372 },
373 "DATASET_WRITES": {
374 "type": "integer",
375 "example": 0
376 },
377 "KEY_VALUE_STORE_READS": {
378 "type": "integer",
379 "example": 0
380 },
381 "KEY_VALUE_STORE_WRITES": {
382 "type": "number",
383 "example": 0.00005
384 },
385 "KEY_VALUE_STORE_LISTS": {
386 "type": "integer",
387 "example": 0
388 },
389 "REQUEST_QUEUE_READS": {
390 "type": "integer",
391 "example": 0
392 },
393 "REQUEST_QUEUE_WRITES": {
394 "type": "integer",
395 "example": 0
396 },
397 "DATA_TRANSFER_INTERNAL_GBYTES": {
398 "type": "integer",
399 "example": 0
400 },
401 "DATA_TRANSFER_EXTERNAL_GBYTES": {
402 "type": "integer",
403 "example": 0
404 },
405 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
406 "type": "integer",
407 "example": 0
408 },
409 "PROXY_SERPS": {
410 "type": "integer",
411 "example": 0
412 }
413 }
414 }
415 }
416 }
417 }
418 }
419 }
420 }
421}RegExp 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 RegExp 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
1 monthly user
-
1 bookmark
>99% runs succeeded
Created in Jan 2025
Modified a month ago
Categories
