Incremental Web Crawler
Try for free
1 day trial then $10.00/month - No credit card required now
Go to Store
Incremental Web Crawler
flamboyant_leaf/incrementalcrawler-v2
Try for free
1 day trial then $10.00/month - No credit card required now
The Incremental Crawler efficiently fetches URLs of recently added or updated web pages on a target site, optimizing resources by focusing only on new content. Ideal for keeping up with the latest updates, it integrates seamlessly into workflows for content monitoring and analysis.
You can access the Incremental Web Crawler programmatically from your own applications by using the Apify API. You can choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "0.0",
5 "x-build-id": "UCFqAUBwow016Ro6B"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/flamboyant_leaf~incrementalcrawler-v2/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-flamboyant_leaf-incrementalcrawler-v2",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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/flamboyant_leaf~incrementalcrawler-v2/runs": {
50 "post": {
51 "operationId": "runs-sync-flamboyant_leaf-incrementalcrawler-v2",
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/flamboyant_leaf~incrementalcrawler-v2/run-sync": {
93 "post": {
94 "operationId": "run-sync-flamboyant_leaf-incrementalcrawler-v2",
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 "url"
135 ],
136 "properties": {
137 "url": {
138 "title": "URL",
139 "type": "string",
140 "description": "The URL to check for new pages"
141 },
142 "daysAgo": {
143 "title": "Days Ago",
144 "minimum": 1,
145 "maximum": 100,
146 "type": "integer",
147 "description": "Number of days to look back for new URLs",
148 "default": 1
149 },
150 "language": {
151 "title": "Language",
152 "type": "string",
153 "description": "Language for search results",
154 "default": "en"
155 },
156 "country": {
157 "title": "Country",
158 "type": "string",
159 "description": "Country for search results",
160 "default": "us"
161 },
162 "searchDomain": {
163 "title": "Search Domain",
164 "type": "string",
165 "description": "Domain to use for search",
166 "default": "google.com"
167 },
168 "nextRunId": {
169 "title": "Next Run ID",
170 "type": "string",
171 "description": "ID of the next task to run"
172 },
173 "nextRunAttribute": {
174 "title": "Next Run Attribute",
175 "type": "string",
176 "description": "Attribute to replace in the next run (default: startUrls)",
177 "default": "startUrls"
178 },
179 "maxResults": {
180 "title": "Max Results",
181 "minimum": 1,
182 "type": "integer",
183 "description": "Maximum number of results to fetch",
184 "default": 10
185 }
186 }
187 },
188 "runsResponseSchema": {
189 "type": "object",
190 "properties": {
191 "data": {
192 "type": "object",
193 "properties": {
194 "id": {
195 "type": "string"
196 },
197 "actId": {
198 "type": "string"
199 },
200 "userId": {
201 "type": "string"
202 },
203 "startedAt": {
204 "type": "string",
205 "format": "date-time",
206 "example": "2025-01-08T00:00:00.000Z"
207 },
208 "finishedAt": {
209 "type": "string",
210 "format": "date-time",
211 "example": "2025-01-08T00:00:00.000Z"
212 },
213 "status": {
214 "type": "string",
215 "example": "READY"
216 },
217 "meta": {
218 "type": "object",
219 "properties": {
220 "origin": {
221 "type": "string",
222 "example": "API"
223 },
224 "userAgent": {
225 "type": "string"
226 }
227 }
228 },
229 "stats": {
230 "type": "object",
231 "properties": {
232 "inputBodyLen": {
233 "type": "integer",
234 "example": 2000
235 },
236 "rebootCount": {
237 "type": "integer",
238 "example": 0
239 },
240 "restartCount": {
241 "type": "integer",
242 "example": 0
243 },
244 "resurrectCount": {
245 "type": "integer",
246 "example": 0
247 },
248 "computeUnits": {
249 "type": "integer",
250 "example": 0
251 }
252 }
253 },
254 "options": {
255 "type": "object",
256 "properties": {
257 "build": {
258 "type": "string",
259 "example": "latest"
260 },
261 "timeoutSecs": {
262 "type": "integer",
263 "example": 300
264 },
265 "memoryMbytes": {
266 "type": "integer",
267 "example": 1024
268 },
269 "diskMbytes": {
270 "type": "integer",
271 "example": 2048
272 }
273 }
274 },
275 "buildId": {
276 "type": "string"
277 },
278 "defaultKeyValueStoreId": {
279 "type": "string"
280 },
281 "defaultDatasetId": {
282 "type": "string"
283 },
284 "defaultRequestQueueId": {
285 "type": "string"
286 },
287 "buildNumber": {
288 "type": "string",
289 "example": "1.0.0"
290 },
291 "containerUrl": {
292 "type": "string"
293 },
294 "usage": {
295 "type": "object",
296 "properties": {
297 "ACTOR_COMPUTE_UNITS": {
298 "type": "integer",
299 "example": 0
300 },
301 "DATASET_READS": {
302 "type": "integer",
303 "example": 0
304 },
305 "DATASET_WRITES": {
306 "type": "integer",
307 "example": 0
308 },
309 "KEY_VALUE_STORE_READS": {
310 "type": "integer",
311 "example": 0
312 },
313 "KEY_VALUE_STORE_WRITES": {
314 "type": "integer",
315 "example": 1
316 },
317 "KEY_VALUE_STORE_LISTS": {
318 "type": "integer",
319 "example": 0
320 },
321 "REQUEST_QUEUE_READS": {
322 "type": "integer",
323 "example": 0
324 },
325 "REQUEST_QUEUE_WRITES": {
326 "type": "integer",
327 "example": 0
328 },
329 "DATA_TRANSFER_INTERNAL_GBYTES": {
330 "type": "integer",
331 "example": 0
332 },
333 "DATA_TRANSFER_EXTERNAL_GBYTES": {
334 "type": "integer",
335 "example": 0
336 },
337 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
338 "type": "integer",
339 "example": 0
340 },
341 "PROXY_SERPS": {
342 "type": "integer",
343 "example": 0
344 }
345 }
346 },
347 "usageTotalUsd": {
348 "type": "number",
349 "example": 0.00005
350 },
351 "usageUsd": {
352 "type": "object",
353 "properties": {
354 "ACTOR_COMPUTE_UNITS": {
355 "type": "integer",
356 "example": 0
357 },
358 "DATASET_READS": {
359 "type": "integer",
360 "example": 0
361 },
362 "DATASET_WRITES": {
363 "type": "integer",
364 "example": 0
365 },
366 "KEY_VALUE_STORE_READS": {
367 "type": "integer",
368 "example": 0
369 },
370 "KEY_VALUE_STORE_WRITES": {
371 "type": "number",
372 "example": 0.00005
373 },
374 "KEY_VALUE_STORE_LISTS": {
375 "type": "integer",
376 "example": 0
377 },
378 "REQUEST_QUEUE_READS": {
379 "type": "integer",
380 "example": 0
381 },
382 "REQUEST_QUEUE_WRITES": {
383 "type": "integer",
384 "example": 0
385 },
386 "DATA_TRANSFER_INTERNAL_GBYTES": {
387 "type": "integer",
388 "example": 0
389 },
390 "DATA_TRANSFER_EXTERNAL_GBYTES": {
391 "type": "integer",
392 "example": 0
393 },
394 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
395 "type": "integer",
396 "example": 0
397 },
398 "PROXY_SERPS": {
399 "type": "integer",
400 "example": 0
401 }
402 }
403 }
404 }
405 }
406 }
407 }
408 }
409 }
410}Incremental Web Crawler 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 Incremental Web Crawler 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
AIRabbitMaintained by Community
Actor Metrics
4 monthly users
-
4 bookmarks
>99% runs succeeded
Created in Aug 2024
Modified 2 months ago
Categories
