Kaggle Scraper
Try for free
1 day trial then $19.99/month - No credit card required now
Go to Store
Kaggle Scraper
muhammetakkurtt/kaggle-scraper
Try for free
1 day trial then $19.99/month - No credit card required now
Efficiently extracts dataset information from Kaggle based on user-defined search terms. Collects datasets metadata, categories, usability ratings and file information. Customizable scraping depth. Ideal for researchers and data scientists seeking quick insights into Kaggle datasets.
You can access the Kaggle Scraper programmatically from your own applications by using the Apify API. You can choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "0.0",
5 "x-build-id": "DFjZi2IIJRn10ONFC"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/muhammetakkurtt~kaggle-scraper/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-muhammetakkurtt-kaggle-scraper",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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/muhammetakkurtt~kaggle-scraper/runs": {
50 "post": {
51 "operationId": "runs-sync-muhammetakkurtt-kaggle-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/muhammetakkurtt~kaggle-scraper/run-sync": {
93 "post": {
94 "operationId": "run-sync-muhammetakkurtt-kaggle-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 "searchTerm"
135 ],
136 "properties": {
137 "searchTerm": {
138 "title": "Search Term",
139 "type": "string",
140 "description": "Topic to search for datasets on Kaggle",
141 "default": "football"
142 },
143 "totalPages": {
144 "title": "Total Pages",
145 "minimum": 1,
146 "type": "integer",
147 "description": "Total number of pages to scrape (default: 3)",
148 "default": 3
149 }
150 }
151 },
152 "runsResponseSchema": {
153 "type": "object",
154 "properties": {
155 "data": {
156 "type": "object",
157 "properties": {
158 "id": {
159 "type": "string"
160 },
161 "actId": {
162 "type": "string"
163 },
164 "userId": {
165 "type": "string"
166 },
167 "startedAt": {
168 "type": "string",
169 "format": "date-time",
170 "example": "2025-01-08T00:00:00.000Z"
171 },
172 "finishedAt": {
173 "type": "string",
174 "format": "date-time",
175 "example": "2025-01-08T00:00:00.000Z"
176 },
177 "status": {
178 "type": "string",
179 "example": "READY"
180 },
181 "meta": {
182 "type": "object",
183 "properties": {
184 "origin": {
185 "type": "string",
186 "example": "API"
187 },
188 "userAgent": {
189 "type": "string"
190 }
191 }
192 },
193 "stats": {
194 "type": "object",
195 "properties": {
196 "inputBodyLen": {
197 "type": "integer",
198 "example": 2000
199 },
200 "rebootCount": {
201 "type": "integer",
202 "example": 0
203 },
204 "restartCount": {
205 "type": "integer",
206 "example": 0
207 },
208 "resurrectCount": {
209 "type": "integer",
210 "example": 0
211 },
212 "computeUnits": {
213 "type": "integer",
214 "example": 0
215 }
216 }
217 },
218 "options": {
219 "type": "object",
220 "properties": {
221 "build": {
222 "type": "string",
223 "example": "latest"
224 },
225 "timeoutSecs": {
226 "type": "integer",
227 "example": 300
228 },
229 "memoryMbytes": {
230 "type": "integer",
231 "example": 1024
232 },
233 "diskMbytes": {
234 "type": "integer",
235 "example": 2048
236 }
237 }
238 },
239 "buildId": {
240 "type": "string"
241 },
242 "defaultKeyValueStoreId": {
243 "type": "string"
244 },
245 "defaultDatasetId": {
246 "type": "string"
247 },
248 "defaultRequestQueueId": {
249 "type": "string"
250 },
251 "buildNumber": {
252 "type": "string",
253 "example": "1.0.0"
254 },
255 "containerUrl": {
256 "type": "string"
257 },
258 "usage": {
259 "type": "object",
260 "properties": {
261 "ACTOR_COMPUTE_UNITS": {
262 "type": "integer",
263 "example": 0
264 },
265 "DATASET_READS": {
266 "type": "integer",
267 "example": 0
268 },
269 "DATASET_WRITES": {
270 "type": "integer",
271 "example": 0
272 },
273 "KEY_VALUE_STORE_READS": {
274 "type": "integer",
275 "example": 0
276 },
277 "KEY_VALUE_STORE_WRITES": {
278 "type": "integer",
279 "example": 1
280 },
281 "KEY_VALUE_STORE_LISTS": {
282 "type": "integer",
283 "example": 0
284 },
285 "REQUEST_QUEUE_READS": {
286 "type": "integer",
287 "example": 0
288 },
289 "REQUEST_QUEUE_WRITES": {
290 "type": "integer",
291 "example": 0
292 },
293 "DATA_TRANSFER_INTERNAL_GBYTES": {
294 "type": "integer",
295 "example": 0
296 },
297 "DATA_TRANSFER_EXTERNAL_GBYTES": {
298 "type": "integer",
299 "example": 0
300 },
301 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
302 "type": "integer",
303 "example": 0
304 },
305 "PROXY_SERPS": {
306 "type": "integer",
307 "example": 0
308 }
309 }
310 },
311 "usageTotalUsd": {
312 "type": "number",
313 "example": 0.00005
314 },
315 "usageUsd": {
316 "type": "object",
317 "properties": {
318 "ACTOR_COMPUTE_UNITS": {
319 "type": "integer",
320 "example": 0
321 },
322 "DATASET_READS": {
323 "type": "integer",
324 "example": 0
325 },
326 "DATASET_WRITES": {
327 "type": "integer",
328 "example": 0
329 },
330 "KEY_VALUE_STORE_READS": {
331 "type": "integer",
332 "example": 0
333 },
334 "KEY_VALUE_STORE_WRITES": {
335 "type": "number",
336 "example": 0.00005
337 },
338 "KEY_VALUE_STORE_LISTS": {
339 "type": "integer",
340 "example": 0
341 },
342 "REQUEST_QUEUE_READS": {
343 "type": "integer",
344 "example": 0
345 },
346 "REQUEST_QUEUE_WRITES": {
347 "type": "integer",
348 "example": 0
349 },
350 "DATA_TRANSFER_INTERNAL_GBYTES": {
351 "type": "integer",
352 "example": 0
353 },
354 "DATA_TRANSFER_EXTERNAL_GBYTES": {
355 "type": "integer",
356 "example": 0
357 },
358 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
359 "type": "integer",
360 "example": 0
361 },
362 "PROXY_SERPS": {
363 "type": "integer",
364 "example": 0
365 }
366 }
367 }
368 }
369 }
370 }
371 }
372 }
373 }
374}Kaggle 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 Kaggle 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
Muhammet AkkurtMaintained by Community
Actor Metrics
1 monthly user
-
2 stars
>99% runs succeeded
Created in Oct 2024
Modified 3 months ago
Categories
