Blog / Dated Content Crawler
Try for free
No credit card required
Go to Store
Blog / Dated Content Crawler
diarmuidr/blog-content-crawler
Try for free
No credit card required
Crawl an entire blog / knowledge base or filter to just the new content. Supporting relevant AI queries by filtering pages by date
Developer
DiarmuidMaintained by Community
Actor Metrics
9 Monthly users
5.0 / 5 (2)
3 bookmarks
97% runs succeeded
Created in Feb 2025
Modified a day ago
Categories
You can access the Blog / Dated Content Crawler 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": "tsnUh6QRR1QGhz9xe"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/diarmuidr~blog-content-crawler/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-diarmuidr-blog-content-crawler",
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 "$ref": "#/components/schemas/inputSchema"
27 }
28 }
29 }
30 },
31 "parameters": [
32 {
33 "name": "token",
34 "in": "query",
35 "required": true,
36 "schema": {
37 "type": "string"
38 },
39 "description": "Enter your Apify token here"
40 }
41 ],
42 "responses": {
43 "200": {
44 "description": "OK"
45 }
46 }
47 }
48 },
49 "/acts/diarmuidr~blog-content-crawler/runs": {
50 "post": {
51 "operationId": "runs-sync-diarmuidr-blog-content-crawler",
52 "x-openai-isConsequential": false,
53 "summary": "Executes an Actor and returns information about the initiated run in response.",
54 "tags": [
55 "Run Actor"
56 ],
57 "requestBody": {
58 "required": true,
59 "content": {
60 "application/json": {
61 "schema": {
62 "$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 "$ref": "#/components/schemas/runsResponseSchema"
85 }
86 }
87 }
88 }
89 }
90 }
91 },
92 "/acts/diarmuidr~blog-content-crawler/run-sync": {
93 "post": {
94 "operationId": "run-sync-diarmuidr-blog-content-crawler",
95 "x-openai-isConsequential": false,
96 "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
97 "tags": [
98 "Run Actor"
99 ],
100 "requestBody": {
101 "required": true,
102 "content": {
103 "application/json": {
104 "schema": {
105 "$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 "startDate": {
156 "title": "Date",
157 "pattern": "^(\\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$",
158 "type": "string",
159 "description": "Optional: Select start date by which to filter pages. Any post published before this date will be excluded. Format in format YYYY-MM-DD"
160 },
161 "relativeStartDate": {
162 "title": "Date",
163 "pattern": "^(\\d+)(\\s*(day|week|month|year)s?)?$",
164 "type": "string",
165 "description": "Optional: Select relative start date by which to filter pages. Any post published before this date will be excluded. This is calculated relative to the time the crawler is run (eg: '2 weeks' would include posts from 2 weeks ago to now). Format in format 'X days' or 'X weeks' or 'X months' or 'X years'. If no time period is passed in, it will be treated as a number of seconds."
166 },
167 "dateSelector": {
168 "title": "Date selector",
169 "type": "string",
170 "description": "Optional: CSS Selector to identify where the date is located on the page. This can make the date filtering more accurate if we don't get it right on the first round. You should use this if there's multiple dates on the page."
171 },
172 "waitForSelector": {
173 "title": "Wait for selector",
174 "type": "string",
175 "description": "CSS Selector to wait for for page load. Useful when content on the page loads asynchronously. This is optional and in most cases won't be needed."
176 },
177 "removeElementsCssSelector": {
178 "title": "Remove HTML elements",
179 "type": "string",
180 "description": "Optional: CSS Selector to identify elements to remove from the page. This is useful for removing elements that are not needed for the content. For example, you can remove the header and footer of the page.",
181 "default": "nav, footer, script, style, noscript, svg, img[src^='data:'],\n[role=\"alert\"],\n[role=\"banner\"],\n[role=\"dialog\"],\n[role=\"alertdialog\"],\n[role=\"region\"][aria-label*=\"skip\" i],\n[aria-modal=\"true\"]"
182 },
183 "requestTimeoutSecs": {
184 "title": "Request Timeout",
185 "minimum": 1,
186 "maximum": 600,
187 "type": "integer",
188 "description": "Optional: How long the crawler will wait for a request to complete. Default is 60 seconds.",
189 "default": 60
190 },
191 "dynamicContentWaitSecs": {
192 "title": "Wait for dynamic content",
193 "minimum": 1,
194 "maximum": 60,
195 "type": "integer",
196 "description": "Optional: Used in conjunction with `waitForSelector`. How long the crawler will wait for the selector to appear. Default is 10 seconds.",
197 "default": 10
198 },
199 "useSitemaps": {
200 "title": "Use Sitemaps",
201 "type": "boolean",
202 "description": "Optional: If checked, the crawler will use the sitemap.xml file to find additional URLs to crawl.",
203 "default": true
204 },
205 "filterByDocumentLastModified": {
206 "title": "Filter by document last modified",
207 "type": "boolean",
208 "description": "Optional: If true, the crawler will include the document's 'last modified' date in the output.",
209 "default": false
210 },
211 "proxyConfiguration": {
212 "title": "Proxy configuration",
213 "type": "object",
214 "description": "Select proxies to be used by your crawler."
215 }
216 }
217 },
218 "runsResponseSchema": {
219 "type": "object",
220 "properties": {
221 "data": {
222 "type": "object",
223 "properties": {
224 "id": {
225 "type": "string"
226 },
227 "actId": {
228 "type": "string"
229 },
230 "userId": {
231 "type": "string"
232 },
233 "startedAt": {
234 "type": "string",
235 "format": "date-time",
236 "example": "2025-01-08T00:00:00.000Z"
237 },
238 "finishedAt": {
239 "type": "string",
240 "format": "date-time",
241 "example": "2025-01-08T00:00:00.000Z"
242 },
243 "status": {
244 "type": "string",
245 "example": "READY"
246 },
247 "meta": {
248 "type": "object",
249 "properties": {
250 "origin": {
251 "type": "string",
252 "example": "API"
253 },
254 "userAgent": {
255 "type": "string"
256 }
257 }
258 },
259 "stats": {
260 "type": "object",
261 "properties": {
262 "inputBodyLen": {
263 "type": "integer",
264 "example": 2000
265 },
266 "rebootCount": {
267 "type": "integer",
268 "example": 0
269 },
270 "restartCount": {
271 "type": "integer",
272 "example": 0
273 },
274 "resurrectCount": {
275 "type": "integer",
276 "example": 0
277 },
278 "computeUnits": {
279 "type": "integer",
280 "example": 0
281 }
282 }
283 },
284 "options": {
285 "type": "object",
286 "properties": {
287 "build": {
288 "type": "string",
289 "example": "latest"
290 },
291 "timeoutSecs": {
292 "type": "integer",
293 "example": 300
294 },
295 "memoryMbytes": {
296 "type": "integer",
297 "example": 1024
298 },
299 "diskMbytes": {
300 "type": "integer",
301 "example": 2048
302 }
303 }
304 },
305 "buildId": {
306 "type": "string"
307 },
308 "defaultKeyValueStoreId": {
309 "type": "string"
310 },
311 "defaultDatasetId": {
312 "type": "string"
313 },
314 "defaultRequestQueueId": {
315 "type": "string"
316 },
317 "buildNumber": {
318 "type": "string",
319 "example": "1.0.0"
320 },
321 "containerUrl": {
322 "type": "string"
323 },
324 "usage": {
325 "type": "object",
326 "properties": {
327 "ACTOR_COMPUTE_UNITS": {
328 "type": "integer",
329 "example": 0
330 },
331 "DATASET_READS": {
332 "type": "integer",
333 "example": 0
334 },
335 "DATASET_WRITES": {
336 "type": "integer",
337 "example": 0
338 },
339 "KEY_VALUE_STORE_READS": {
340 "type": "integer",
341 "example": 0
342 },
343 "KEY_VALUE_STORE_WRITES": {
344 "type": "integer",
345 "example": 1
346 },
347 "KEY_VALUE_STORE_LISTS": {
348 "type": "integer",
349 "example": 0
350 },
351 "REQUEST_QUEUE_READS": {
352 "type": "integer",
353 "example": 0
354 },
355 "REQUEST_QUEUE_WRITES": {
356 "type": "integer",
357 "example": 0
358 },
359 "DATA_TRANSFER_INTERNAL_GBYTES": {
360 "type": "integer",
361 "example": 0
362 },
363 "DATA_TRANSFER_EXTERNAL_GBYTES": {
364 "type": "integer",
365 "example": 0
366 },
367 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
368 "type": "integer",
369 "example": 0
370 },
371 "PROXY_SERPS": {
372 "type": "integer",
373 "example": 0
374 }
375 }
376 },
377 "usageTotalUsd": {
378 "type": "number",
379 "example": 0.00005
380 },
381 "usageUsd": {
382 "type": "object",
383 "properties": {
384 "ACTOR_COMPUTE_UNITS": {
385 "type": "integer",
386 "example": 0
387 },
388 "DATASET_READS": {
389 "type": "integer",
390 "example": 0
391 },
392 "DATASET_WRITES": {
393 "type": "integer",
394 "example": 0
395 },
396 "KEY_VALUE_STORE_READS": {
397 "type": "integer",
398 "example": 0
399 },
400 "KEY_VALUE_STORE_WRITES": {
401 "type": "number",
402 "example": 0.00005
403 },
404 "KEY_VALUE_STORE_LISTS": {
405 "type": "integer",
406 "example": 0
407 },
408 "REQUEST_QUEUE_READS": {
409 "type": "integer",
410 "example": 0
411 },
412 "REQUEST_QUEUE_WRITES": {
413 "type": "integer",
414 "example": 0
415 },
416 "DATA_TRANSFER_INTERNAL_GBYTES": {
417 "type": "integer",
418 "example": 0
419 },
420 "DATA_TRANSFER_EXTERNAL_GBYTES": {
421 "type": "integer",
422 "example": 0
423 },
424 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
425 "type": "integer",
426 "example": 0
427 },
428 "PROXY_SERPS": {
429 "type": "integer",
430 "example": 0
431 }
432 }
433 }
434 }
435 }
436 }
437 }
438 }
439 }
440}Blog / Dated Content 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 Blog / Dated Content 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:
