Website Content Extractor
Pricing
$9.00/month + usage
Go to Store
Website Content Extractor
fastidious_drawer/website-content-extractor
This extractor lets you extract content from any website with a single or multiple URLs. Use selectors to choose specific sections like the body and exclude elements like headers or navigation. It also extracts images and links, providing data in JSON and DataTable formats for easy processing.
0.0 (0)
Pricing
$9.00/month + usage
0
Monthly users
8
Runs succeeded
>99%
Last modified
3 hours ago
You can access the Website Content Extractor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "0.0",
5 "x-build-id": "6NdOPWT6oreBFCrU4"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/fastidious_drawer~website-content-extractor/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-fastidious_drawer-website-content-extractor",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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/fastidious_drawer~website-content-extractor/runs": {
50 "post": {
51 "operationId": "runs-sync-fastidious_drawer-website-content-extractor",
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/fastidious_drawer~website-content-extractor/run-sync": {
93 "post": {
94 "operationId": "run-sync-fastidious_drawer-website-content-extractor",
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 "urls"
135 ],
136 "properties": {
137 "urls": {
138 "title": "Target URL",
139 "type": "array",
140 "description": "The website URL to extract content from.",
141 "default": [
142 "https://apify.com"
143 ],
144 "items": {
145 "type": "string"
146 }
147 },
148 "selectors": {
149 "title": "CSS Selectors",
150 "type": "array",
151 "description": "List of CSS selectors to extract specific content.",
152 "default": [],
153 "items": {
154 "type": "string"
155 }
156 },
157 "excludeSelectors": {
158 "title": "Exclude CSS Selectors",
159 "type": "array",
160 "description": "List of CSS selectors to exclude from extraction (e.g., nav, header, footer).",
161 "default": [],
162 "items": {
163 "type": "string"
164 }
165 },
166 "extractImages": {
167 "title": "Extract Images",
168 "type": "boolean",
169 "description": "Whether to extract images from the website.",
170 "default": false
171 },
172 "extractLinks": {
173 "title": "Extract Links",
174 "type": "boolean",
175 "description": "Whether to extract links from the website.",
176 "default": false
177 },
178 "maxPages": {
179 "title": "Maximum Pages to Crawl",
180 "minimum": 1,
181 "type": "integer",
182 "description": "Limits the number of pages to extract content from.",
183 "default": 10
184 }
185 }
186 },
187 "runsResponseSchema": {
188 "type": "object",
189 "properties": {
190 "data": {
191 "type": "object",
192 "properties": {
193 "id": {
194 "type": "string"
195 },
196 "actId": {
197 "type": "string"
198 },
199 "userId": {
200 "type": "string"
201 },
202 "startedAt": {
203 "type": "string",
204 "format": "date-time",
205 "example": "2025-01-08T00:00:00.000Z"
206 },
207 "finishedAt": {
208 "type": "string",
209 "format": "date-time",
210 "example": "2025-01-08T00:00:00.000Z"
211 },
212 "status": {
213 "type": "string",
214 "example": "READY"
215 },
216 "meta": {
217 "type": "object",
218 "properties": {
219 "origin": {
220 "type": "string",
221 "example": "API"
222 },
223 "userAgent": {
224 "type": "string"
225 }
226 }
227 },
228 "stats": {
229 "type": "object",
230 "properties": {
231 "inputBodyLen": {
232 "type": "integer",
233 "example": 2000
234 },
235 "rebootCount": {
236 "type": "integer",
237 "example": 0
238 },
239 "restartCount": {
240 "type": "integer",
241 "example": 0
242 },
243 "resurrectCount": {
244 "type": "integer",
245 "example": 0
246 },
247 "computeUnits": {
248 "type": "integer",
249 "example": 0
250 }
251 }
252 },
253 "options": {
254 "type": "object",
255 "properties": {
256 "build": {
257 "type": "string",
258 "example": "latest"
259 },
260 "timeoutSecs": {
261 "type": "integer",
262 "example": 300
263 },
264 "memoryMbytes": {
265 "type": "integer",
266 "example": 1024
267 },
268 "diskMbytes": {
269 "type": "integer",
270 "example": 2048
271 }
272 }
273 },
274 "buildId": {
275 "type": "string"
276 },
277 "defaultKeyValueStoreId": {
278 "type": "string"
279 },
280 "defaultDatasetId": {
281 "type": "string"
282 },
283 "defaultRequestQueueId": {
284 "type": "string"
285 },
286 "buildNumber": {
287 "type": "string",
288 "example": "1.0.0"
289 },
290 "containerUrl": {
291 "type": "string"
292 },
293 "usage": {
294 "type": "object",
295 "properties": {
296 "ACTOR_COMPUTE_UNITS": {
297 "type": "integer",
298 "example": 0
299 },
300 "DATASET_READS": {
301 "type": "integer",
302 "example": 0
303 },
304 "DATASET_WRITES": {
305 "type": "integer",
306 "example": 0
307 },
308 "KEY_VALUE_STORE_READS": {
309 "type": "integer",
310 "example": 0
311 },
312 "KEY_VALUE_STORE_WRITES": {
313 "type": "integer",
314 "example": 1
315 },
316 "KEY_VALUE_STORE_LISTS": {
317 "type": "integer",
318 "example": 0
319 },
320 "REQUEST_QUEUE_READS": {
321 "type": "integer",
322 "example": 0
323 },
324 "REQUEST_QUEUE_WRITES": {
325 "type": "integer",
326 "example": 0
327 },
328 "DATA_TRANSFER_INTERNAL_GBYTES": {
329 "type": "integer",
330 "example": 0
331 },
332 "DATA_TRANSFER_EXTERNAL_GBYTES": {
333 "type": "integer",
334 "example": 0
335 },
336 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
337 "type": "integer",
338 "example": 0
339 },
340 "PROXY_SERPS": {
341 "type": "integer",
342 "example": 0
343 }
344 }
345 },
346 "usageTotalUsd": {
347 "type": "number",
348 "example": 0.00005
349 },
350 "usageUsd": {
351 "type": "object",
352 "properties": {
353 "ACTOR_COMPUTE_UNITS": {
354 "type": "integer",
355 "example": 0
356 },
357 "DATASET_READS": {
358 "type": "integer",
359 "example": 0
360 },
361 "DATASET_WRITES": {
362 "type": "integer",
363 "example": 0
364 },
365 "KEY_VALUE_STORE_READS": {
366 "type": "integer",
367 "example": 0
368 },
369 "KEY_VALUE_STORE_WRITES": {
370 "type": "number",
371 "example": 0.00005
372 },
373 "KEY_VALUE_STORE_LISTS": {
374 "type": "integer",
375 "example": 0
376 },
377 "REQUEST_QUEUE_READS": {
378 "type": "integer",
379 "example": 0
380 },
381 "REQUEST_QUEUE_WRITES": {
382 "type": "integer",
383 "example": 0
384 },
385 "DATA_TRANSFER_INTERNAL_GBYTES": {
386 "type": "integer",
387 "example": 0
388 },
389 "DATA_TRANSFER_EXTERNAL_GBYTES": {
390 "type": "integer",
391 "example": 0
392 },
393 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
394 "type": "integer",
395 "example": 0
396 },
397 "PROXY_SERPS": {
398 "type": "integer",
399 "example": 0
400 }
401 }
402 }
403 }
404 }
405 }
406 }
407 }
408 }
409}Website Content 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 Website Content Extractor 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
RentalTo use this Actor, you have to pay a monthly rental fee to the developer. The rent is subtracted from your prepaid usage every month after the free trial period. You also pay for the Apify platform usage.
Free trial
1 day
Price
$9.00
