Fast News Scraper
Try for free
3 days trial then $29.00/month - No credit card required now
Go to Store
Fast News Scraper
timgreen/fast-news-scraper
Try for free
3 days trial then $29.00/month - No credit card required now
Extract full article text and metadata from popular news sites like The New York Times, Bloomberg, Reuters, BBC, CNBC, and Wired. Scrape thousands of articles in just a few minutes. Scape a single site or provide a list of article URLs to scrape.
Tim GreenYou can access the Fast News Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "0.0",
5 "x-build-id": "f9rpOYwogqK7cxAEc"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/timgreen~fast-news-scraper/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-timgreen-fast-news-scraper",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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/timgreen~fast-news-scraper/runs": {
50 "post": {
51 "operationId": "runs-sync-timgreen-fast-news-scraper",
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/timgreen~fast-news-scraper/run-sync": {
93 "post": {
94 "operationId": "run-sync-timgreen-fast-news-scraper",
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 "proxy"
135 ],
136 "properties": {
137 "site": {
138 "title": "Site",
139 "enum": [
140 "nytimes.com",
141 "washingtonpost.com",
142 "bloomberg.com",
143 "cnn.com",
144 "bbc.com",
145 "reuters.com",
146 "seekingalpha.com/market-news",
147 "wired.com",
148 "cnbc.com"
149 ],
150 "type": "string",
151 "description": "The website to scrape. It must be one of the supported options. To request a website that's not supported, create an issue in the Issues tab.",
152 "default": "cnn.com"
153 },
154 "query": {
155 "title": "Query",
156 "type": "string",
157 "description": "The search term for the website. Not all websites support this, and some allow an empty value. See the README for more details.",
158 "default": ""
159 },
160 "sort": {
161 "title": "Sort by",
162 "enum": [
163 "date",
164 "relevance"
165 ],
166 "type": "string",
167 "description": "Sort by date or relevance. Not all websites support both. See the README for more details.",
168 "default": "date"
169 },
170 "maxItems": {
171 "title": "Max Items",
172 "type": "integer",
173 "description": "The approximate maximium number of articles to return.",
174 "default": 500
175 },
176 "articleURLs": {
177 "title": "Article URLs",
178 "type": "array",
179 "description": "A list of article URLs from which to extract data. If any URLs are provided, site, query, and sort will be ignored and only those URLs will be scraped.",
180 "items": {
181 "type": "object",
182 "required": [
183 "url"
184 ],
185 "properties": {
186 "url": {
187 "type": "string",
188 "title": "URL of a web page",
189 "format": "uri"
190 }
191 }
192 }
193 },
194 "datasetName": {
195 "title": "Dataset Name",
196 "type": "string",
197 "description": "If set, results will be stored in the name dataset"
198 },
199 "requestQueueName": {
200 "title": "Request Queue Name",
201 "type": "string",
202 "description": "If set, requests will be stored in the name queue. This is useful for not pulling the same articles multiple times."
203 },
204 "beginDate": {
205 "title": "Begin Date",
206 "type": "string",
207 "description": "ONLY SUPPORTED FOR SOME WEBSITES. Extract articles on or after this date."
208 },
209 "endDate": {
210 "title": "End Date",
211 "type": "string",
212 "description": "ONLY SUPPORTED FOR SOME WEBSITES. Extract articles on or before this date."
213 },
214 "proxy": {
215 "title": "Proxy configuration",
216 "type": "object",
217 "description": "Select proxies to be used by your crawler."
218 }
219 }
220 },
221 "runsResponseSchema": {
222 "type": "object",
223 "properties": {
224 "data": {
225 "type": "object",
226 "properties": {
227 "id": {
228 "type": "string"
229 },
230 "actId": {
231 "type": "string"
232 },
233 "userId": {
234 "type": "string"
235 },
236 "startedAt": {
237 "type": "string",
238 "format": "date-time",
239 "example": "2025-01-08T00:00:00.000Z"
240 },
241 "finishedAt": {
242 "type": "string",
243 "format": "date-time",
244 "example": "2025-01-08T00:00:00.000Z"
245 },
246 "status": {
247 "type": "string",
248 "example": "READY"
249 },
250 "meta": {
251 "type": "object",
252 "properties": {
253 "origin": {
254 "type": "string",
255 "example": "API"
256 },
257 "userAgent": {
258 "type": "string"
259 }
260 }
261 },
262 "stats": {
263 "type": "object",
264 "properties": {
265 "inputBodyLen": {
266 "type": "integer",
267 "example": 2000
268 },
269 "rebootCount": {
270 "type": "integer",
271 "example": 0
272 },
273 "restartCount": {
274 "type": "integer",
275 "example": 0
276 },
277 "resurrectCount": {
278 "type": "integer",
279 "example": 0
280 },
281 "computeUnits": {
282 "type": "integer",
283 "example": 0
284 }
285 }
286 },
287 "options": {
288 "type": "object",
289 "properties": {
290 "build": {
291 "type": "string",
292 "example": "latest"
293 },
294 "timeoutSecs": {
295 "type": "integer",
296 "example": 300
297 },
298 "memoryMbytes": {
299 "type": "integer",
300 "example": 1024
301 },
302 "diskMbytes": {
303 "type": "integer",
304 "example": 2048
305 }
306 }
307 },
308 "buildId": {
309 "type": "string"
310 },
311 "defaultKeyValueStoreId": {
312 "type": "string"
313 },
314 "defaultDatasetId": {
315 "type": "string"
316 },
317 "defaultRequestQueueId": {
318 "type": "string"
319 },
320 "buildNumber": {
321 "type": "string",
322 "example": "1.0.0"
323 },
324 "containerUrl": {
325 "type": "string"
326 },
327 "usage": {
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": "integer",
348 "example": 1
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 "usageTotalUsd": {
381 "type": "number",
382 "example": 0.00005
383 },
384 "usageUsd": {
385 "type": "object",
386 "properties": {
387 "ACTOR_COMPUTE_UNITS": {
388 "type": "integer",
389 "example": 0
390 },
391 "DATASET_READS": {
392 "type": "integer",
393 "example": 0
394 },
395 "DATASET_WRITES": {
396 "type": "integer",
397 "example": 0
398 },
399 "KEY_VALUE_STORE_READS": {
400 "type": "integer",
401 "example": 0
402 },
403 "KEY_VALUE_STORE_WRITES": {
404 "type": "number",
405 "example": 0.00005
406 },
407 "KEY_VALUE_STORE_LISTS": {
408 "type": "integer",
409 "example": 0
410 },
411 "REQUEST_QUEUE_READS": {
412 "type": "integer",
413 "example": 0
414 },
415 "REQUEST_QUEUE_WRITES": {
416 "type": "integer",
417 "example": 0
418 },
419 "DATA_TRANSFER_INTERNAL_GBYTES": {
420 "type": "integer",
421 "example": 0
422 },
423 "DATA_TRANSFER_EXTERNAL_GBYTES": {
424 "type": "integer",
425 "example": 0
426 },
427 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
428 "type": "integer",
429 "example": 0
430 },
431 "PROXY_SERPS": {
432 "type": "integer",
433 "example": 0
434 }
435 }
436 }
437 }
438 }
439 }
440 }
441 }
442 }
443}Fast News Scraper 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 Fast News Scraper 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:
