
News Website Crawler & Article Extractor
Pricing
$20.00/month + usage

News Website Crawler & Article Extractor
Scrape all articles from any news website. Extract full text, metadata, keywords, and summaries. Ideal for content analysis, research, and news aggregation.
0.0 (0)
Pricing
$20.00/month + usage
2
Monthly users
20
Runs succeeded
>99%
Response time
13 days
Last modified
13 days ago
You can access the News Website Crawler & Article Extractor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "0.0",
5 "x-build-id": "udB8A3tssavN6to1m"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/xtech~news-source-crawler/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-xtech-news-source-crawler",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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/xtech~news-source-crawler/runs": {
50 "post": {
51 "operationId": "runs-sync-xtech-news-source-crawler",
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/xtech~news-source-crawler/run-sync": {
93 "post": {
94 "operationId": "run-sync-xtech-news-source-crawler",
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 "$ref": "#/components/schemas/inputSchema"
106 }
107 }
108 }
109 },
110 "parameters": [
111 {
112 "name": "token",
113 "in": "query",
114 "required": true,
115 "schema": {
116 "type": "string"
117 },
118 "description": "Enter your Apify token here"
119 }
120 ],
121 "responses": {
122 "200": {
123 "description": "OK"
124 }
125 }
126 }
127 }
128 },
129 "components": {
130 "schemas": {
131 "inputSchema": {
132 "type": "object",
133 "required": [
134 "url"
135 ],
136 "properties": {
137 "url": {
138 "title": "News Source URL",
139 "pattern": "^https?://.+$",
140 "type": "string",
141 "description": "The URL of the news website you want to crawl (e.g., https://www.cnn.com)."
142 },
143 "maxArticles": {
144 "title": "Maximum Articles",
145 "minimum": 1,
146 "type": "integer",
147 "description": "The maximum number of articles to scrape. Leave blank for no limit.",
148 "default": 100
149 },
150 "language": {
151 "title": "Language",
152 "maxLength": 2,
153 "type": "string",
154 "description": "The language of the articles as a 2-letter ISO code (e.g., 'en', 'es').",
155 "default": "en"
156 },
157 "keywordSearch": {
158 "title": "Keyword Search [Optional]",
159 "type": "string",
160 "description": "Filter articles containing specific keywords. Leave blank to get all articles. For advanced searches, you can use AND, OR, NOT operators (e.g., 'climate AND (change OR crisis) NOT politics')."
161 },
162 "extractSummary": {
163 "title": "Extract Summary & Keywords",
164 "type": "boolean",
165 "description": "Generate article summaries and keywords using NLP.",
166 "default": true
167 },
168 "includeImages": {
169 "title": "Include Images",
170 "type": "boolean",
171 "description": "Whether to include image URLs in the results.",
172 "default": true
173 },
174 "minWordCount": {
175 "title": "Minimum Word Count",
176 "minimum": 0,
177 "type": "integer",
178 "description": "Skip articles that have fewer words than this number. Use 0 for no minimum.",
179 "default": 0
180 },
181 "advancedOptions": {
182 "title": "Advanced Options",
183 "type": "object",
184 "description": "Additional configuration options for advanced users."
185 },
186 "proxyConfiguration": {
187 "title": "Proxy Configuration",
188 "type": "object",
189 "description": "Proxy settings. Use Apify Proxy for automatic proxy management.",
190 "default": {}
191 }
192 }
193 },
194 "runsResponseSchema": {
195 "type": "object",
196 "properties": {
197 "data": {
198 "type": "object",
199 "properties": {
200 "id": {
201 "type": "string"
202 },
203 "actId": {
204 "type": "string"
205 },
206 "userId": {
207 "type": "string"
208 },
209 "startedAt": {
210 "type": "string",
211 "format": "date-time",
212 "example": "2025-01-08T00:00:00.000Z"
213 },
214 "finishedAt": {
215 "type": "string",
216 "format": "date-time",
217 "example": "2025-01-08T00:00:00.000Z"
218 },
219 "status": {
220 "type": "string",
221 "example": "READY"
222 },
223 "meta": {
224 "type": "object",
225 "properties": {
226 "origin": {
227 "type": "string",
228 "example": "API"
229 },
230 "userAgent": {
231 "type": "string"
232 }
233 }
234 },
235 "stats": {
236 "type": "object",
237 "properties": {
238 "inputBodyLen": {
239 "type": "integer",
240 "example": 2000
241 },
242 "rebootCount": {
243 "type": "integer",
244 "example": 0
245 },
246 "restartCount": {
247 "type": "integer",
248 "example": 0
249 },
250 "resurrectCount": {
251 "type": "integer",
252 "example": 0
253 },
254 "computeUnits": {
255 "type": "integer",
256 "example": 0
257 }
258 }
259 },
260 "options": {
261 "type": "object",
262 "properties": {
263 "build": {
264 "type": "string",
265 "example": "latest"
266 },
267 "timeoutSecs": {
268 "type": "integer",
269 "example": 300
270 },
271 "memoryMbytes": {
272 "type": "integer",
273 "example": 1024
274 },
275 "diskMbytes": {
276 "type": "integer",
277 "example": 2048
278 }
279 }
280 },
281 "buildId": {
282 "type": "string"
283 },
284 "defaultKeyValueStoreId": {
285 "type": "string"
286 },
287 "defaultDatasetId": {
288 "type": "string"
289 },
290 "defaultRequestQueueId": {
291 "type": "string"
292 },
293 "buildNumber": {
294 "type": "string",
295 "example": "1.0.0"
296 },
297 "containerUrl": {
298 "type": "string"
299 },
300 "usage": {
301 "type": "object",
302 "properties": {
303 "ACTOR_COMPUTE_UNITS": {
304 "type": "integer",
305 "example": 0
306 },
307 "DATASET_READS": {
308 "type": "integer",
309 "example": 0
310 },
311 "DATASET_WRITES": {
312 "type": "integer",
313 "example": 0
314 },
315 "KEY_VALUE_STORE_READS": {
316 "type": "integer",
317 "example": 0
318 },
319 "KEY_VALUE_STORE_WRITES": {
320 "type": "integer",
321 "example": 1
322 },
323 "KEY_VALUE_STORE_LISTS": {
324 "type": "integer",
325 "example": 0
326 },
327 "REQUEST_QUEUE_READS": {
328 "type": "integer",
329 "example": 0
330 },
331 "REQUEST_QUEUE_WRITES": {
332 "type": "integer",
333 "example": 0
334 },
335 "DATA_TRANSFER_INTERNAL_GBYTES": {
336 "type": "integer",
337 "example": 0
338 },
339 "DATA_TRANSFER_EXTERNAL_GBYTES": {
340 "type": "integer",
341 "example": 0
342 },
343 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
344 "type": "integer",
345 "example": 0
346 },
347 "PROXY_SERPS": {
348 "type": "integer",
349 "example": 0
350 }
351 }
352 },
353 "usageTotalUsd": {
354 "type": "number",
355 "example": 0.00005
356 },
357 "usageUsd": {
358 "type": "object",
359 "properties": {
360 "ACTOR_COMPUTE_UNITS": {
361 "type": "integer",
362 "example": 0
363 },
364 "DATASET_READS": {
365 "type": "integer",
366 "example": 0
367 },
368 "DATASET_WRITES": {
369 "type": "integer",
370 "example": 0
371 },
372 "KEY_VALUE_STORE_READS": {
373 "type": "integer",
374 "example": 0
375 },
376 "KEY_VALUE_STORE_WRITES": {
377 "type": "number",
378 "example": 0.00005
379 },
380 "KEY_VALUE_STORE_LISTS": {
381 "type": "integer",
382 "example": 0
383 },
384 "REQUEST_QUEUE_READS": {
385 "type": "integer",
386 "example": 0
387 },
388 "REQUEST_QUEUE_WRITES": {
389 "type": "integer",
390 "example": 0
391 },
392 "DATA_TRANSFER_INTERNAL_GBYTES": {
393 "type": "integer",
394 "example": 0
395 },
396 "DATA_TRANSFER_EXTERNAL_GBYTES": {
397 "type": "integer",
398 "example": 0
399 },
400 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
401 "type": "integer",
402 "example": 0
403 },
404 "PROXY_SERPS": {
405 "type": "integer",
406 "example": 0
407 }
408 }
409 }
410 }
411 }
412 }
413 }
414 }
415 }
416}
News Website Crawler & Article 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 News Website Crawler & Article 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
2 hours
Price
$20.00