Parsera
Try for free
This Actor is paid per event
Go to Store
Parsera
parsera-labs/parsera
Try for free
This Actor is paid per event
Extract Data from ANY website with Parsera.org
Developer
Parsera LabsMaintained by Community
Actor Metrics
4 Monthly users
No reviews yet
4 bookmarks
>99% runs succeeded
56 days response time
Created in Nov 2024
Modified 15 days ago
Categories
You can access the Parsera 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": "1.0",
5 "x-build-id": "WqlgafsYdTt5zjHYK"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/parsera-labs~parsera/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-parsera-labs-parsera",
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 "$ref": "#/components/schemas/inputSchema"
27 }
28 }
29 }
30 },
31 "parameters": [
32 {
33 "name": "token",
34 "in": "query",
35 "required": true,
36 "schema": {
37 "type": "string"
38 },
39 "description": "Enter your Apify token here"
40 }
41 ],
42 "responses": {
43 "200": {
44 "description": "OK"
45 }
46 }
47 }
48 },
49 "/acts/parsera-labs~parsera/runs": {
50 "post": {
51 "operationId": "runs-sync-parsera-labs-parsera",
52 "x-openai-isConsequential": false,
53 "summary": "Executes an Actor and returns information about the initiated run in response.",
54 "tags": [
55 "Run Actor"
56 ],
57 "requestBody": {
58 "required": true,
59 "content": {
60 "application/json": {
61 "schema": {
62 "$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 "$ref": "#/components/schemas/runsResponseSchema"
85 }
86 }
87 }
88 }
89 }
90 }
91 },
92 "/acts/parsera-labs~parsera/run-sync": {
93 "post": {
94 "operationId": "run-sync-parsera-labs-parsera",
95 "x-openai-isConsequential": false,
96 "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
97 "tags": [
98 "Run Actor"
99 ],
100 "requestBody": {
101 "required": true,
102 "content": {
103 "application/json": {
104 "schema": {
105 "$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 "attributes"
136 ],
137 "properties": {
138 "url": {
139 "title": "Target URL",
140 "pattern": "^https?://[^\\s/$.?#].[^\\s]*$",
141 "type": "string",
142 "description": "The webpage URL to extract data from"
143 },
144 "attributes": {
145 "title": "Extraction Attributes",
146 "type": "array",
147 "description": "Define what data to extract from the webpage"
148 },
149 "precisionMode": {
150 "title": "Precision Mode",
151 "type": "boolean",
152 "description": "Enable for more accurate but more expensive extraction",
153 "default": false
154 },
155 "proxyCountry": {
156 "title": "Proxy Location",
157 "enum": [
158 "random",
159 "Afghanistan",
160 "Albania",
161 "Algeria",
162 "Argentina",
163 "Armenia",
164 "Aruba",
165 "Australia",
166 "Austria",
167 "Azerbaijan",
168 "Bahamas",
169 "Bahrain",
170 "Bangladesh",
171 "Belarus",
172 "Belgium",
173 "BosniaandHerzegovina",
174 "Brazil",
175 "BritishVirginIslands",
176 "Brunei",
177 "Bulgaria",
178 "Cambodia",
179 "Cameroon",
180 "Canada",
181 "Chile",
182 "China",
183 "Colombia",
184 "CostaRica",
185 "Croatia",
186 "Cuba",
187 "Cyprus",
188 "Chechia",
189 "Denmark",
190 "DominicanRepublic",
191 "Ecuador",
192 "Egypt",
193 "ElSalvador",
194 "Estonia",
195 "Ethiopia",
196 "Finland",
197 "France",
198 "Georgia",
199 "Germany",
200 "Ghana",
201 "Greece",
202 "Guatemala",
203 "Guyana",
204 "HashemiteKingdomofJordan",
205 "HongKong",
206 "Hungary",
207 "India",
208 "Indonesia",
209 "Iran",
210 "Iraq",
211 "Ireland",
212 "Israel",
213 "Italy",
214 "Jamaica",
215 "Japan",
216 "Kazakhstan",
217 "Kenya",
218 "Kosovo",
219 "Kuwait",
220 "Latvia",
221 "Liechtenstein",
222 "Luxembourg",
223 "Macedonia",
224 "Madagascar",
225 "Malaysia",
226 "Mauritius",
227 "Mexico",
228 "Mongolia",
229 "Montenegro",
230 "Morocco",
231 "Mozambique",
232 "Myanmar",
233 "Nepal",
234 "Netherlands",
235 "NewZealand",
236 "Nigeria",
237 "Norway",
238 "Oman",
239 "Pakistan",
240 "Palestine",
241 "Panama",
242 "PapuaNewGuinea",
243 "Paraguay",
244 "Peru",
245 "Philippines",
246 "Poland",
247 "Portugal",
248 "PuertoRico",
249 "Qatar",
250 "RepublicOfLithuania",
251 "RepublicOfMoldova",
252 "Romania",
253 "Russia",
254 "SaudiArabia",
255 "Senegal",
256 "Serbia",
257 "Seychelles",
258 "Singapore",
259 "Slovakia",
260 "Slovenia",
261 "Somalia",
262 "SouthAfrica",
263 "SouthKorea",
264 "Spain",
265 "SriLanka",
266 "Sudan",
267 "Suriname",
268 "Sweden",
269 "Switzerland",
270 "Syria",
271 "Taiwan",
272 "Tajikistan",
273 "Thailand",
274 "TrinidadandTobago",
275 "Tunisia",
276 "Turkey",
277 "Uganda",
278 "Ukraine",
279 "UnitedArabEmirates",
280 "UnitedKingdom",
281 "UnitedStates",
282 "Uzbekistan",
283 "Venezuela",
284 "Vietnam",
285 "Zambia"
286 ],
287 "type": "string",
288 "description": "Country for the proxy IP (optional)"
289 },
290 "cookies": {
291 "title": "Custom Cookies",
292 "type": "array",
293 "description": "Custom cookies to use for the request (optional)"
294 }
295 }
296 },
297 "runsResponseSchema": {
298 "type": "object",
299 "properties": {
300 "data": {
301 "type": "object",
302 "properties": {
303 "id": {
304 "type": "string"
305 },
306 "actId": {
307 "type": "string"
308 },
309 "userId": {
310 "type": "string"
311 },
312 "startedAt": {
313 "type": "string",
314 "format": "date-time",
315 "example": "2025-01-08T00:00:00.000Z"
316 },
317 "finishedAt": {
318 "type": "string",
319 "format": "date-time",
320 "example": "2025-01-08T00:00:00.000Z"
321 },
322 "status": {
323 "type": "string",
324 "example": "READY"
325 },
326 "meta": {
327 "type": "object",
328 "properties": {
329 "origin": {
330 "type": "string",
331 "example": "API"
332 },
333 "userAgent": {
334 "type": "string"
335 }
336 }
337 },
338 "stats": {
339 "type": "object",
340 "properties": {
341 "inputBodyLen": {
342 "type": "integer",
343 "example": 2000
344 },
345 "rebootCount": {
346 "type": "integer",
347 "example": 0
348 },
349 "restartCount": {
350 "type": "integer",
351 "example": 0
352 },
353 "resurrectCount": {
354 "type": "integer",
355 "example": 0
356 },
357 "computeUnits": {
358 "type": "integer",
359 "example": 0
360 }
361 }
362 },
363 "options": {
364 "type": "object",
365 "properties": {
366 "build": {
367 "type": "string",
368 "example": "latest"
369 },
370 "timeoutSecs": {
371 "type": "integer",
372 "example": 300
373 },
374 "memoryMbytes": {
375 "type": "integer",
376 "example": 1024
377 },
378 "diskMbytes": {
379 "type": "integer",
380 "example": 2048
381 }
382 }
383 },
384 "buildId": {
385 "type": "string"
386 },
387 "defaultKeyValueStoreId": {
388 "type": "string"
389 },
390 "defaultDatasetId": {
391 "type": "string"
392 },
393 "defaultRequestQueueId": {
394 "type": "string"
395 },
396 "buildNumber": {
397 "type": "string",
398 "example": "1.0.0"
399 },
400 "containerUrl": {
401 "type": "string"
402 },
403 "usage": {
404 "type": "object",
405 "properties": {
406 "ACTOR_COMPUTE_UNITS": {
407 "type": "integer",
408 "example": 0
409 },
410 "DATASET_READS": {
411 "type": "integer",
412 "example": 0
413 },
414 "DATASET_WRITES": {
415 "type": "integer",
416 "example": 0
417 },
418 "KEY_VALUE_STORE_READS": {
419 "type": "integer",
420 "example": 0
421 },
422 "KEY_VALUE_STORE_WRITES": {
423 "type": "integer",
424 "example": 1
425 },
426 "KEY_VALUE_STORE_LISTS": {
427 "type": "integer",
428 "example": 0
429 },
430 "REQUEST_QUEUE_READS": {
431 "type": "integer",
432 "example": 0
433 },
434 "REQUEST_QUEUE_WRITES": {
435 "type": "integer",
436 "example": 0
437 },
438 "DATA_TRANSFER_INTERNAL_GBYTES": {
439 "type": "integer",
440 "example": 0
441 },
442 "DATA_TRANSFER_EXTERNAL_GBYTES": {
443 "type": "integer",
444 "example": 0
445 },
446 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
447 "type": "integer",
448 "example": 0
449 },
450 "PROXY_SERPS": {
451 "type": "integer",
452 "example": 0
453 }
454 }
455 },
456 "usageTotalUsd": {
457 "type": "number",
458 "example": 0.00005
459 },
460 "usageUsd": {
461 "type": "object",
462 "properties": {
463 "ACTOR_COMPUTE_UNITS": {
464 "type": "integer",
465 "example": 0
466 },
467 "DATASET_READS": {
468 "type": "integer",
469 "example": 0
470 },
471 "DATASET_WRITES": {
472 "type": "integer",
473 "example": 0
474 },
475 "KEY_VALUE_STORE_READS": {
476 "type": "integer",
477 "example": 0
478 },
479 "KEY_VALUE_STORE_WRITES": {
480 "type": "number",
481 "example": 0.00005
482 },
483 "KEY_VALUE_STORE_LISTS": {
484 "type": "integer",
485 "example": 0
486 },
487 "REQUEST_QUEUE_READS": {
488 "type": "integer",
489 "example": 0
490 },
491 "REQUEST_QUEUE_WRITES": {
492 "type": "integer",
493 "example": 0
494 },
495 "DATA_TRANSFER_INTERNAL_GBYTES": {
496 "type": "integer",
497 "example": 0
498 },
499 "DATA_TRANSFER_EXTERNAL_GBYTES": {
500 "type": "integer",
501 "example": 0
502 },
503 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
504 "type": "integer",
505 "example": 0
506 },
507 "PROXY_SERPS": {
508 "type": "integer",
509 "example": 0
510 }
511 }
512 }
513 }
514 }
515 }
516 }
517 }
518 }
519}Parsera 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 Parsera 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:
