Web Scraping API
Pricing
$5.00 / 1,000 pages
Go to Store
Web Scraping API
Web Scraping API that quickly and reliably scrapes any website—no selectors required. Premium proxies, CAPTCHA solving, JavaScript rendering, and automated structured data extraction are all included. It’s just 0.5¢ per page, with no minimum spend.
5.0 (2)
Pricing
$5.00 / 1,000 pages
15
Monthly users
147
Runs succeeded
>99%
Response time
7.5 hours
Last modified
11 hours ago
You can access the Web Scraping API programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "3.8",
5 "x-build-id": "qNNN9ckugZU6wA1WW"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/zeeb0t~web-scraping-api---scrape-any-website/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-zeeb0t-web-scraping-api---scrape-any-website",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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/zeeb0t~web-scraping-api---scrape-any-website/runs": {
50 "post": {
51 "operationId": "runs-sync-zeeb0t-web-scraping-api---scrape-any-website",
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/zeeb0t~web-scraping-api---scrape-any-website/run-sync": {
93 "post": {
94 "operationId": "run-sync-zeeb0t-web-scraping-api---scrape-any-website",
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 "properties": {
134 "endpoint": {
135 "title": "Endpoint Name",
136 "enum": [
137 "scrape",
138 "links",
139 "next",
140 "search"
141 ],
142 "type": "string",
143 "description": "Which API endpoint to call. Choose from 'scrape', 'links', 'next', or 'search'. Defaults to 'scrape' if not provided."
144 },
145 "output_preference": {
146 "title": "Output Preference",
147 "enum": [
148 "json",
149 "tabular"
150 ],
151 "type": "string",
152 "description": "What is your output preference? For programmatic integrations choose 'json' (default). To view the data in a table or for CSV export, choose 'tabular'."
153 },
154 "url": {
155 "title": "URL of the page",
156 "type": "string",
157 "description": "The URL of the webpage you want to extract data from. (Used by endpoints: 'scrape', 'links', 'next'.)"
158 },
159 "fields": {
160 "title": "Data Extraction Fields",
161 "type": "object",
162 "description": "A JSON object describing the data you want extracted. (Used by endpoint: 'scrape'.)"
163 },
164 "description": {
165 "title": "Description of Links",
166 "type": "string",
167 "description": "A short text indicating the type of links to extract, e.g. 'individual product urls'. (Used by endpoint: 'links'.)"
168 },
169 "google_domain": {
170 "title": "Google Search Domain",
171 "type": "string",
172 "description": "Domain for Google search, e.g., 'www.google.com', 'www.google.com.au', etc. (Used by endpoint: 'search'.)"
173 },
174 "query": {
175 "title": "Search Query",
176 "type": "string",
177 "description": "The search phrase you'd like to search for in Google. (Used by endpoint: 'search'.)"
178 },
179 "page": {
180 "title": "Google Search Page",
181 "type": "integer",
182 "description": "Which page of Google search results to fetch. (Used by endpoint: 'search'.)"
183 },
184 "method": {
185 "title": "(Deprecated) API Method Name",
186 "type": "string",
187 "description": "Legacy name for the API method; no longer required or used."
188 },
189 "output": {
190 "title": "(Deprecated) API Output Structure",
191 "type": "string",
192 "description": "Previously used for specifying the /scrape output JSON. Replaced by 'fields'."
193 },
194 "proxy_country": {
195 "title": "(Deprecated) Proxy Country",
196 "type": "string",
197 "description": "Previously used for specifying a premium proxy geolocation. No longer supported."
198 }
199 }
200 },
201 "runsResponseSchema": {
202 "type": "object",
203 "properties": {
204 "data": {
205 "type": "object",
206 "properties": {
207 "id": {
208 "type": "string"
209 },
210 "actId": {
211 "type": "string"
212 },
213 "userId": {
214 "type": "string"
215 },
216 "startedAt": {
217 "type": "string",
218 "format": "date-time",
219 "example": "2025-01-08T00:00:00.000Z"
220 },
221 "finishedAt": {
222 "type": "string",
223 "format": "date-time",
224 "example": "2025-01-08T00:00:00.000Z"
225 },
226 "status": {
227 "type": "string",
228 "example": "READY"
229 },
230 "meta": {
231 "type": "object",
232 "properties": {
233 "origin": {
234 "type": "string",
235 "example": "API"
236 },
237 "userAgent": {
238 "type": "string"
239 }
240 }
241 },
242 "stats": {
243 "type": "object",
244 "properties": {
245 "inputBodyLen": {
246 "type": "integer",
247 "example": 2000
248 },
249 "rebootCount": {
250 "type": "integer",
251 "example": 0
252 },
253 "restartCount": {
254 "type": "integer",
255 "example": 0
256 },
257 "resurrectCount": {
258 "type": "integer",
259 "example": 0
260 },
261 "computeUnits": {
262 "type": "integer",
263 "example": 0
264 }
265 }
266 },
267 "options": {
268 "type": "object",
269 "properties": {
270 "build": {
271 "type": "string",
272 "example": "latest"
273 },
274 "timeoutSecs": {
275 "type": "integer",
276 "example": 300
277 },
278 "memoryMbytes": {
279 "type": "integer",
280 "example": 1024
281 },
282 "diskMbytes": {
283 "type": "integer",
284 "example": 2048
285 }
286 }
287 },
288 "buildId": {
289 "type": "string"
290 },
291 "defaultKeyValueStoreId": {
292 "type": "string"
293 },
294 "defaultDatasetId": {
295 "type": "string"
296 },
297 "defaultRequestQueueId": {
298 "type": "string"
299 },
300 "buildNumber": {
301 "type": "string",
302 "example": "1.0.0"
303 },
304 "containerUrl": {
305 "type": "string"
306 },
307 "usage": {
308 "type": "object",
309 "properties": {
310 "ACTOR_COMPUTE_UNITS": {
311 "type": "integer",
312 "example": 0
313 },
314 "DATASET_READS": {
315 "type": "integer",
316 "example": 0
317 },
318 "DATASET_WRITES": {
319 "type": "integer",
320 "example": 0
321 },
322 "KEY_VALUE_STORE_READS": {
323 "type": "integer",
324 "example": 0
325 },
326 "KEY_VALUE_STORE_WRITES": {
327 "type": "integer",
328 "example": 1
329 },
330 "KEY_VALUE_STORE_LISTS": {
331 "type": "integer",
332 "example": 0
333 },
334 "REQUEST_QUEUE_READS": {
335 "type": "integer",
336 "example": 0
337 },
338 "REQUEST_QUEUE_WRITES": {
339 "type": "integer",
340 "example": 0
341 },
342 "DATA_TRANSFER_INTERNAL_GBYTES": {
343 "type": "integer",
344 "example": 0
345 },
346 "DATA_TRANSFER_EXTERNAL_GBYTES": {
347 "type": "integer",
348 "example": 0
349 },
350 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
351 "type": "integer",
352 "example": 0
353 },
354 "PROXY_SERPS": {
355 "type": "integer",
356 "example": 0
357 }
358 }
359 },
360 "usageTotalUsd": {
361 "type": "number",
362 "example": 0.00005
363 },
364 "usageUsd": {
365 "type": "object",
366 "properties": {
367 "ACTOR_COMPUTE_UNITS": {
368 "type": "integer",
369 "example": 0
370 },
371 "DATASET_READS": {
372 "type": "integer",
373 "example": 0
374 },
375 "DATASET_WRITES": {
376 "type": "integer",
377 "example": 0
378 },
379 "KEY_VALUE_STORE_READS": {
380 "type": "integer",
381 "example": 0
382 },
383 "KEY_VALUE_STORE_WRITES": {
384 "type": "number",
385 "example": 0.00005
386 },
387 "KEY_VALUE_STORE_LISTS": {
388 "type": "integer",
389 "example": 0
390 },
391 "REQUEST_QUEUE_READS": {
392 "type": "integer",
393 "example": 0
394 },
395 "REQUEST_QUEUE_WRITES": {
396 "type": "integer",
397 "example": 0
398 },
399 "DATA_TRANSFER_INTERNAL_GBYTES": {
400 "type": "integer",
401 "example": 0
402 },
403 "DATA_TRANSFER_EXTERNAL_GBYTES": {
404 "type": "integer",
405 "example": 0
406 },
407 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
408 "type": "integer",
409 "example": 0
410 },
411 "PROXY_SERPS": {
412 "type": "integer",
413 "example": 0
414 }
415 }
416 }
417 }
418 }
419 }
420 }
421 }
422 }
423}Web Scraping API 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 Web Scraping API 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:
Pricing
Pricing model
Pay per resultThis Actor is paid per result. You are not charged for the Apify platform usage, but only a fixed price for each dataset of 1,000 items in the Actor outputs.
Price per 1,000 items
$5.00
