
Hacker News Data Scraper
3 days trial then $10.00/month - No credit card required now

Hacker News Data Scraper
3 days trial then $10.00/month - No credit card required now
Extract Y Combinator's Hacker News based on any search criteria. Crawl the front page, Show HN, Ask HN, news, job listings, and historical data. Get links, titles, comments, ratings, and more!
You can access the Hacker News Data Scraper programmatically from your own applications by using the Apify API. You can choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "0.0",
5 "x-build-id": "3eMp735kvPWf8dAGz"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/epctex~hackernews-scraper/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-epctex-hackernews-scraper",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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/epctex~hackernews-scraper/runs": {
50 "post": {
51 "operationId": "runs-sync-epctex-hackernews-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/epctex~hackernews-scraper/run-sync": {
93 "post": {
94 "operationId": "run-sync-epctex-hackernews-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 "$ref": "#/components/schemas/inputSchema"
106 }
107 }
108 }
109 },
110 "parameters": [
111 {
112 "name": "token",
113 "in": "query",
114 "required": true,
115 "schema": {
116 "type": "string"
117 },
118 "description": "Enter your Apify token here"
119 }
120 ],
121 "responses": {
122 "200": {
123 "description": "OK"
124 }
125 }
126 }
127 }
128 },
129 "components": {
130 "schemas": {
131 "inputSchema": {
132 "type": "object",
133 "required": [
134 "proxy"
135 ],
136 "properties": {
137 "startUrls": {
138 "title": "Start URLs",
139 "type": "array",
140 "description": "URLs to start with. It should be list or detail URL",
141 "items": {
142 "type": "object",
143 "required": [
144 "url"
145 ],
146 "properties": {
147 "url": {
148 "type": "string",
149 "title": "URL of a web page",
150 "format": "uri"
151 }
152 }
153 }
154 },
155 "mode": {
156 "title": "Mode",
157 "enum": [
158 "FRONTPAGE",
159 "NEWEST",
160 "ASK",
161 "SHOW",
162 "JOBS",
163 "PAST"
164 ],
165 "type": "string",
166 "description": "Select mode of the actor"
167 },
168 "enableCommentHierarchy": {
169 "title": "Enable Comment Hierarchy",
170 "type": "boolean",
171 "description": "Enables comment hierarchy. If disabled, all comments will be on the same level.",
172 "default": false
173 },
174 "maxItems": {
175 "title": "Maximum number of listing items",
176 "type": "integer",
177 "description": "Maximum number of listing items that you want as output. Default is all"
178 },
179 "endPage": {
180 "title": "List end page",
181 "type": "integer",
182 "description": "The page number that you want to end with. By default there is no end page."
183 },
184 "extendOutputFunction": {
185 "title": "Extend output function",
186 "type": "string",
187 "description": "Function that takes a JQuery handle ($) as argument and returns data that will be merged with the default output"
188 },
189 "proxy": {
190 "title": "Proxy configuration",
191 "type": "object",
192 "description": "Select proxies to be used by your crawler."
193 }
194 }
195 },
196 "runsResponseSchema": {
197 "type": "object",
198 "properties": {
199 "data": {
200 "type": "object",
201 "properties": {
202 "id": {
203 "type": "string"
204 },
205 "actId": {
206 "type": "string"
207 },
208 "userId": {
209 "type": "string"
210 },
211 "startedAt": {
212 "type": "string",
213 "format": "date-time",
214 "example": "2025-01-08T00:00:00.000Z"
215 },
216 "finishedAt": {
217 "type": "string",
218 "format": "date-time",
219 "example": "2025-01-08T00:00:00.000Z"
220 },
221 "status": {
222 "type": "string",
223 "example": "READY"
224 },
225 "meta": {
226 "type": "object",
227 "properties": {
228 "origin": {
229 "type": "string",
230 "example": "API"
231 },
232 "userAgent": {
233 "type": "string"
234 }
235 }
236 },
237 "stats": {
238 "type": "object",
239 "properties": {
240 "inputBodyLen": {
241 "type": "integer",
242 "example": 2000
243 },
244 "rebootCount": {
245 "type": "integer",
246 "example": 0
247 },
248 "restartCount": {
249 "type": "integer",
250 "example": 0
251 },
252 "resurrectCount": {
253 "type": "integer",
254 "example": 0
255 },
256 "computeUnits": {
257 "type": "integer",
258 "example": 0
259 }
260 }
261 },
262 "options": {
263 "type": "object",
264 "properties": {
265 "build": {
266 "type": "string",
267 "example": "latest"
268 },
269 "timeoutSecs": {
270 "type": "integer",
271 "example": 300
272 },
273 "memoryMbytes": {
274 "type": "integer",
275 "example": 1024
276 },
277 "diskMbytes": {
278 "type": "integer",
279 "example": 2048
280 }
281 }
282 },
283 "buildId": {
284 "type": "string"
285 },
286 "defaultKeyValueStoreId": {
287 "type": "string"
288 },
289 "defaultDatasetId": {
290 "type": "string"
291 },
292 "defaultRequestQueueId": {
293 "type": "string"
294 },
295 "buildNumber": {
296 "type": "string",
297 "example": "1.0.0"
298 },
299 "containerUrl": {
300 "type": "string"
301 },
302 "usage": {
303 "type": "object",
304 "properties": {
305 "ACTOR_COMPUTE_UNITS": {
306 "type": "integer",
307 "example": 0
308 },
309 "DATASET_READS": {
310 "type": "integer",
311 "example": 0
312 },
313 "DATASET_WRITES": {
314 "type": "integer",
315 "example": 0
316 },
317 "KEY_VALUE_STORE_READS": {
318 "type": "integer",
319 "example": 0
320 },
321 "KEY_VALUE_STORE_WRITES": {
322 "type": "integer",
323 "example": 1
324 },
325 "KEY_VALUE_STORE_LISTS": {
326 "type": "integer",
327 "example": 0
328 },
329 "REQUEST_QUEUE_READS": {
330 "type": "integer",
331 "example": 0
332 },
333 "REQUEST_QUEUE_WRITES": {
334 "type": "integer",
335 "example": 0
336 },
337 "DATA_TRANSFER_INTERNAL_GBYTES": {
338 "type": "integer",
339 "example": 0
340 },
341 "DATA_TRANSFER_EXTERNAL_GBYTES": {
342 "type": "integer",
343 "example": 0
344 },
345 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
346 "type": "integer",
347 "example": 0
348 },
349 "PROXY_SERPS": {
350 "type": "integer",
351 "example": 0
352 }
353 }
354 },
355 "usageTotalUsd": {
356 "type": "number",
357 "example": 0.00005
358 },
359 "usageUsd": {
360 "type": "object",
361 "properties": {
362 "ACTOR_COMPUTE_UNITS": {
363 "type": "integer",
364 "example": 0
365 },
366 "DATASET_READS": {
367 "type": "integer",
368 "example": 0
369 },
370 "DATASET_WRITES": {
371 "type": "integer",
372 "example": 0
373 },
374 "KEY_VALUE_STORE_READS": {
375 "type": "integer",
376 "example": 0
377 },
378 "KEY_VALUE_STORE_WRITES": {
379 "type": "number",
380 "example": 0.00005
381 },
382 "KEY_VALUE_STORE_LISTS": {
383 "type": "integer",
384 "example": 0
385 },
386 "REQUEST_QUEUE_READS": {
387 "type": "integer",
388 "example": 0
389 },
390 "REQUEST_QUEUE_WRITES": {
391 "type": "integer",
392 "example": 0
393 },
394 "DATA_TRANSFER_INTERNAL_GBYTES": {
395 "type": "integer",
396 "example": 0
397 },
398 "DATA_TRANSFER_EXTERNAL_GBYTES": {
399 "type": "integer",
400 "example": 0
401 },
402 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
403 "type": "integer",
404 "example": 0
405 },
406 "PROXY_SERPS": {
407 "type": "integer",
408 "example": 0
409 }
410 }
411 }
412 }
413 }
414 }
415 }
416 }
417 }
418}
Hacker News 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 Hacker News Data 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: