API / JSON scraper
Try for free
1 day trial then $5.00/month - No credit card required now
Go to Store
API / JSON scraper
pocesar/json-downloader
Try for free
1 day trial then $5.00/month - No credit card required now
Scrape any API / JSON URLs directly to the dataset, and return them in CSV, XML, HTML, or Excel formats. Transform and filter the output. Enables you to follow pagination recursively from the payload without the need to visit the HTML page.
You can access the API / JSON scraper programmatically from your own applications by using the Apify API. You can choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "0.2",
5 "x-build-id": "vnBB67hTutFzEXiE7"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/pocesar~json-downloader/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-pocesar-json-downloader",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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/pocesar~json-downloader/runs": {
50 "post": {
51 "operationId": "runs-sync-pocesar-json-downloader",
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/pocesar~json-downloader/run-sync": {
93 "post": {
94 "operationId": "run-sync-pocesar-json-downloader",
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 "proxyConfig",
136 "filterMap"
137 ],
138 "properties": {
139 "startUrls": {
140 "title": "URLs",
141 "type": "array",
142 "description": "URLs that return application/json as response",
143 "items": {
144 "type": "object",
145 "required": [
146 "url"
147 ],
148 "properties": {
149 "url": {
150 "type": "string",
151 "title": "URL of a web page",
152 "format": "uri"
153 }
154 }
155 }
156 },
157 "filterMap": {
158 "title": "Filter / map output",
159 "type": "string",
160 "description": "Filter and/or map the output before pushing to the dataset. Check the README for more information",
161 "default": "async ({ request, response, addRequest, flattenObjectKeys, context, Apify, _, moment, data, input, customData }) => {\n return { url: request.url, data };\n}"
162 },
163 "handleError": {
164 "title": "Error handler",
165 "type": "string",
166 "description": "Called when errors happen. For more information, see the README",
167 "default": "async ({ error, request, response, addRequest, _, moment, Apify, input, context }) => {\n \n}"
168 },
169 "customData": {
170 "title": "Custom data",
171 "type": "object",
172 "description": "Any custom data to be available inside the filter map function",
173 "default": {}
174 },
175 "maxRequestsPerCrawl": {
176 "title": "Max number of results",
177 "type": "integer",
178 "description": "Leave empty for no limit"
179 },
180 "proxyConfig": {
181 "title": "Proxy",
182 "type": "object",
183 "description": "Proxies are required to download data from the given input URLs",
184 "default": {
185 "useApifyProxy": true
186 }
187 },
188 "force": {
189 "title": "Force parsing",
190 "type": "boolean",
191 "description": "Force parsing the content regardless of the JSON header.",
192 "default": false
193 },
194 "maxRequestRetries": {
195 "title": "Max request retries",
196 "type": "integer",
197 "description": "How many times failed requests should be retried.",
198 "default": 4
199 },
200 "debugLog": {
201 "title": "Enable debug",
202 "type": "boolean",
203 "description": "Display debug messages",
204 "default": false
205 }
206 }
207 },
208 "runsResponseSchema": {
209 "type": "object",
210 "properties": {
211 "data": {
212 "type": "object",
213 "properties": {
214 "id": {
215 "type": "string"
216 },
217 "actId": {
218 "type": "string"
219 },
220 "userId": {
221 "type": "string"
222 },
223 "startedAt": {
224 "type": "string",
225 "format": "date-time",
226 "example": "2025-01-08T00:00:00.000Z"
227 },
228 "finishedAt": {
229 "type": "string",
230 "format": "date-time",
231 "example": "2025-01-08T00:00:00.000Z"
232 },
233 "status": {
234 "type": "string",
235 "example": "READY"
236 },
237 "meta": {
238 "type": "object",
239 "properties": {
240 "origin": {
241 "type": "string",
242 "example": "API"
243 },
244 "userAgent": {
245 "type": "string"
246 }
247 }
248 },
249 "stats": {
250 "type": "object",
251 "properties": {
252 "inputBodyLen": {
253 "type": "integer",
254 "example": 2000
255 },
256 "rebootCount": {
257 "type": "integer",
258 "example": 0
259 },
260 "restartCount": {
261 "type": "integer",
262 "example": 0
263 },
264 "resurrectCount": {
265 "type": "integer",
266 "example": 0
267 },
268 "computeUnits": {
269 "type": "integer",
270 "example": 0
271 }
272 }
273 },
274 "options": {
275 "type": "object",
276 "properties": {
277 "build": {
278 "type": "string",
279 "example": "latest"
280 },
281 "timeoutSecs": {
282 "type": "integer",
283 "example": 300
284 },
285 "memoryMbytes": {
286 "type": "integer",
287 "example": 1024
288 },
289 "diskMbytes": {
290 "type": "integer",
291 "example": 2048
292 }
293 }
294 },
295 "buildId": {
296 "type": "string"
297 },
298 "defaultKeyValueStoreId": {
299 "type": "string"
300 },
301 "defaultDatasetId": {
302 "type": "string"
303 },
304 "defaultRequestQueueId": {
305 "type": "string"
306 },
307 "buildNumber": {
308 "type": "string",
309 "example": "1.0.0"
310 },
311 "containerUrl": {
312 "type": "string"
313 },
314 "usage": {
315 "type": "object",
316 "properties": {
317 "ACTOR_COMPUTE_UNITS": {
318 "type": "integer",
319 "example": 0
320 },
321 "DATASET_READS": {
322 "type": "integer",
323 "example": 0
324 },
325 "DATASET_WRITES": {
326 "type": "integer",
327 "example": 0
328 },
329 "KEY_VALUE_STORE_READS": {
330 "type": "integer",
331 "example": 0
332 },
333 "KEY_VALUE_STORE_WRITES": {
334 "type": "integer",
335 "example": 1
336 },
337 "KEY_VALUE_STORE_LISTS": {
338 "type": "integer",
339 "example": 0
340 },
341 "REQUEST_QUEUE_READS": {
342 "type": "integer",
343 "example": 0
344 },
345 "REQUEST_QUEUE_WRITES": {
346 "type": "integer",
347 "example": 0
348 },
349 "DATA_TRANSFER_INTERNAL_GBYTES": {
350 "type": "integer",
351 "example": 0
352 },
353 "DATA_TRANSFER_EXTERNAL_GBYTES": {
354 "type": "integer",
355 "example": 0
356 },
357 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
358 "type": "integer",
359 "example": 0
360 },
361 "PROXY_SERPS": {
362 "type": "integer",
363 "example": 0
364 }
365 }
366 },
367 "usageTotalUsd": {
368 "type": "number",
369 "example": 0.00005
370 },
371 "usageUsd": {
372 "type": "object",
373 "properties": {
374 "ACTOR_COMPUTE_UNITS": {
375 "type": "integer",
376 "example": 0
377 },
378 "DATASET_READS": {
379 "type": "integer",
380 "example": 0
381 },
382 "DATASET_WRITES": {
383 "type": "integer",
384 "example": 0
385 },
386 "KEY_VALUE_STORE_READS": {
387 "type": "integer",
388 "example": 0
389 },
390 "KEY_VALUE_STORE_WRITES": {
391 "type": "number",
392 "example": 0.00005
393 },
394 "KEY_VALUE_STORE_LISTS": {
395 "type": "integer",
396 "example": 0
397 },
398 "REQUEST_QUEUE_READS": {
399 "type": "integer",
400 "example": 0
401 },
402 "REQUEST_QUEUE_WRITES": {
403 "type": "integer",
404 "example": 0
405 },
406 "DATA_TRANSFER_INTERNAL_GBYTES": {
407 "type": "integer",
408 "example": 0
409 },
410 "DATA_TRANSFER_EXTERNAL_GBYTES": {
411 "type": "integer",
412 "example": 0
413 },
414 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
415 "type": "integer",
416 "example": 0
417 },
418 "PROXY_SERPS": {
419 "type": "integer",
420 "example": 0
421 }
422 }
423 }
424 }
425 }
426 }
427 }
428 }
429 }
430}API / JSON 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 API / JSON 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
Paulo CesarMaintained by Community
Actor Metrics
14 monthly users
-
6 stars
>99% runs succeeded
Created in May 2022
Modified a year ago
Categories
