News Website Crawler & Article Extractor
Under maintenance
Try for free
2 hours trial then $20.00/month - No credit card required now
Go to Store
This Actor is under maintenance.
This Actor may be unreliable while under maintenance. Would you like to try a similar Actor instead?
See alternative ActorsNews Website Crawler & Article Extractor
xtech/news-source-crawler
Try for free
2 hours trial then $20.00/month - No credit card required now
Scrape all articles from any news website. Extract full text, metadata, keywords, and summaries. Ideal for content analysis, research, and news aggregation.
You can access the News Website Crawler & Article Extractor programmatically from your own applications by using the Apify API. You can choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "0.0",
5 "x-build-id": "DBAZdkz7TaVNRaNC3"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/xtech~news-source-crawler/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-xtech-news-source-crawler",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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 "language": {
144 "title": "Article Language",
145 "maxLength": 2,
146 "type": "string",
147 "description": "The language of the articles as a 2-letter ISO code (e.g., 'en', 'es'). Default: 'en'.",
148 "default": "en"
149 },
150 "maxArticles": {
151 "title": "Maximum Articles to Scrape",
152 "minimum": 1,
153 "type": "integer",
154 "description": "The maximum number of articles to scrape. Leave blank for no limit."
155 },
156 "proxyConfiguration": {
157 "title": "Proxy Configuration",
158 "type": "object",
159 "description": "Proxy settings. Use Apify Proxy for automatic proxy management.",
160 "default": {}
161 }
162 }
163 },
164 "runsResponseSchema": {
165 "type": "object",
166 "properties": {
167 "data": {
168 "type": "object",
169 "properties": {
170 "id": {
171 "type": "string"
172 },
173 "actId": {
174 "type": "string"
175 },
176 "userId": {
177 "type": "string"
178 },
179 "startedAt": {
180 "type": "string",
181 "format": "date-time",
182 "example": "2025-01-08T00:00:00.000Z"
183 },
184 "finishedAt": {
185 "type": "string",
186 "format": "date-time",
187 "example": "2025-01-08T00:00:00.000Z"
188 },
189 "status": {
190 "type": "string",
191 "example": "READY"
192 },
193 "meta": {
194 "type": "object",
195 "properties": {
196 "origin": {
197 "type": "string",
198 "example": "API"
199 },
200 "userAgent": {
201 "type": "string"
202 }
203 }
204 },
205 "stats": {
206 "type": "object",
207 "properties": {
208 "inputBodyLen": {
209 "type": "integer",
210 "example": 2000
211 },
212 "rebootCount": {
213 "type": "integer",
214 "example": 0
215 },
216 "restartCount": {
217 "type": "integer",
218 "example": 0
219 },
220 "resurrectCount": {
221 "type": "integer",
222 "example": 0
223 },
224 "computeUnits": {
225 "type": "integer",
226 "example": 0
227 }
228 }
229 },
230 "options": {
231 "type": "object",
232 "properties": {
233 "build": {
234 "type": "string",
235 "example": "latest"
236 },
237 "timeoutSecs": {
238 "type": "integer",
239 "example": 300
240 },
241 "memoryMbytes": {
242 "type": "integer",
243 "example": 1024
244 },
245 "diskMbytes": {
246 "type": "integer",
247 "example": 2048
248 }
249 }
250 },
251 "buildId": {
252 "type": "string"
253 },
254 "defaultKeyValueStoreId": {
255 "type": "string"
256 },
257 "defaultDatasetId": {
258 "type": "string"
259 },
260 "defaultRequestQueueId": {
261 "type": "string"
262 },
263 "buildNumber": {
264 "type": "string",
265 "example": "1.0.0"
266 },
267 "containerUrl": {
268 "type": "string"
269 },
270 "usage": {
271 "type": "object",
272 "properties": {
273 "ACTOR_COMPUTE_UNITS": {
274 "type": "integer",
275 "example": 0
276 },
277 "DATASET_READS": {
278 "type": "integer",
279 "example": 0
280 },
281 "DATASET_WRITES": {
282 "type": "integer",
283 "example": 0
284 },
285 "KEY_VALUE_STORE_READS": {
286 "type": "integer",
287 "example": 0
288 },
289 "KEY_VALUE_STORE_WRITES": {
290 "type": "integer",
291 "example": 1
292 },
293 "KEY_VALUE_STORE_LISTS": {
294 "type": "integer",
295 "example": 0
296 },
297 "REQUEST_QUEUE_READS": {
298 "type": "integer",
299 "example": 0
300 },
301 "REQUEST_QUEUE_WRITES": {
302 "type": "integer",
303 "example": 0
304 },
305 "DATA_TRANSFER_INTERNAL_GBYTES": {
306 "type": "integer",
307 "example": 0
308 },
309 "DATA_TRANSFER_EXTERNAL_GBYTES": {
310 "type": "integer",
311 "example": 0
312 },
313 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
314 "type": "integer",
315 "example": 0
316 },
317 "PROXY_SERPS": {
318 "type": "integer",
319 "example": 0
320 }
321 }
322 },
323 "usageTotalUsd": {
324 "type": "number",
325 "example": 0.00005
326 },
327 "usageUsd": {
328 "type": "object",
329 "properties": {
330 "ACTOR_COMPUTE_UNITS": {
331 "type": "integer",
332 "example": 0
333 },
334 "DATASET_READS": {
335 "type": "integer",
336 "example": 0
337 },
338 "DATASET_WRITES": {
339 "type": "integer",
340 "example": 0
341 },
342 "KEY_VALUE_STORE_READS": {
343 "type": "integer",
344 "example": 0
345 },
346 "KEY_VALUE_STORE_WRITES": {
347 "type": "number",
348 "example": 0.00005
349 },
350 "KEY_VALUE_STORE_LISTS": {
351 "type": "integer",
352 "example": 0
353 },
354 "REQUEST_QUEUE_READS": {
355 "type": "integer",
356 "example": 0
357 },
358 "REQUEST_QUEUE_WRITES": {
359 "type": "integer",
360 "example": 0
361 },
362 "DATA_TRANSFER_INTERNAL_GBYTES": {
363 "type": "integer",
364 "example": 0
365 },
366 "DATA_TRANSFER_EXTERNAL_GBYTES": {
367 "type": "integer",
368 "example": 0
369 },
370 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
371 "type": "integer",
372 "example": 0
373 },
374 "PROXY_SERPS": {
375 "type": "integer",
376 "example": 0
377 }
378 }
379 }
380 }
381 }
382 }
383 }
384 }
385 }
386}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:
Developer
XtechMaintained by Community
Actor Metrics
8 monthly users
-
1 bookmark
>99% runs succeeded
Created in Feb 2025
Modified 8 days ago
Categories
