The Hill Scraper
Go to Store
This Actor is deprecated
This Actor is unavailable because the developer has decided to deprecate it. Would you like to try a similar Actor instead?
See alternative ActorsThe Hill Scraper
hanatsai/the-hill-scraper
Scrape news data from thehill.com with this unofficial API. Extract articles, monitor their popularity and performance and automate the fight against fake news. Filter the results by authors, topics, categories, or publication dates. Preview or download the results in your preferred format.
You can access the The Hill Scraper 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": "1.0",
5 "x-build-id": "WNDnjd4aO4EA8XfBQ"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/hanatsai~the-hill-scraper/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-hanatsai-the-hill-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 "$ref": "#/components/schemas/inputSchema"
27 }
28 }
29 }
30 },
31 "parameters": [
32 {
33 "name": "token",
34 "in": "query",
35 "required": true,
36 "schema": {
37 "type": "string"
38 },
39 "description": "Enter your Apify token here"
40 }
41 ],
42 "responses": {
43 "200": {
44 "description": "OK"
45 }
46 }
47 }
48 },
49 "/acts/hanatsai~the-hill-scraper/runs": {
50 "post": {
51 "operationId": "runs-sync-hanatsai-the-hill-scraper",
52 "x-openai-isConsequential": false,
53 "summary": "Executes an Actor and returns information about the initiated run in response.",
54 "tags": [
55 "Run Actor"
56 ],
57 "requestBody": {
58 "required": true,
59 "content": {
60 "application/json": {
61 "schema": {
62 "$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 "$ref": "#/components/schemas/runsResponseSchema"
85 }
86 }
87 }
88 }
89 }
90 }
91 },
92 "/acts/hanatsai~the-hill-scraper/run-sync": {
93 "post": {
94 "operationId": "run-sync-hanatsai-the-hill-scraper",
95 "x-openai-isConsequential": false,
96 "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
97 "tags": [
98 "Run Actor"
99 ],
100 "requestBody": {
101 "required": true,
102 "content": {
103 "application/json": {
104 "schema": {
105 "$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 "startUrls"
135 ],
136 "properties": {
137 "startUrls": {
138 "title": "Start URLs",
139 "type": "array",
140 "description": "Can be main page URL or any category URLs. Article pages are found and enqueued from these.",
141 "items": {
142 "type": "object",
143 "required": [
144 "url"
145 ],
146 "properties": {
147 "url": {
148 "type": "string",
149 "title": "URL of a web page",
150 "format": "uri"
151 }
152 }
153 }
154 },
155 "maxArticlesPerCrawl": {
156 "title": "Maximum number of articles",
157 "type": "integer",
158 "description": "Maximum number of valid articles scraped. The crawler will stop automatically after reaching this number."
159 },
160 "dateFrom": {
161 "title": "Date from",
162 "type": "string",
163 "description": "Only articles from this day to present will be scraped. If empty, all articles will be scraped. Format is YYYY-MM-DD, e.g. 2019-12-31, or Number type e.g. 1 week or 20 days"
164 },
165 "onlyNewArticlesPerDomain": {
166 "title": "Only new articles",
167 "type": "boolean",
168 "description": "If true, will scrape only new articles each time you run it. All URLs you scraped are compared with saved ones. Scraped articles are saved in one dataset per each domain, datasets are named 'ARTICLES-SCRAPED-domain'",
169 "default": false
170 }
171 }
172 },
173 "runsResponseSchema": {
174 "type": "object",
175 "properties": {
176 "data": {
177 "type": "object",
178 "properties": {
179 "id": {
180 "type": "string"
181 },
182 "actId": {
183 "type": "string"
184 },
185 "userId": {
186 "type": "string"
187 },
188 "startedAt": {
189 "type": "string",
190 "format": "date-time",
191 "example": "2025-01-08T00:00:00.000Z"
192 },
193 "finishedAt": {
194 "type": "string",
195 "format": "date-time",
196 "example": "2025-01-08T00:00:00.000Z"
197 },
198 "status": {
199 "type": "string",
200 "example": "READY"
201 },
202 "meta": {
203 "type": "object",
204 "properties": {
205 "origin": {
206 "type": "string",
207 "example": "API"
208 },
209 "userAgent": {
210 "type": "string"
211 }
212 }
213 },
214 "stats": {
215 "type": "object",
216 "properties": {
217 "inputBodyLen": {
218 "type": "integer",
219 "example": 2000
220 },
221 "rebootCount": {
222 "type": "integer",
223 "example": 0
224 },
225 "restartCount": {
226 "type": "integer",
227 "example": 0
228 },
229 "resurrectCount": {
230 "type": "integer",
231 "example": 0
232 },
233 "computeUnits": {
234 "type": "integer",
235 "example": 0
236 }
237 }
238 },
239 "options": {
240 "type": "object",
241 "properties": {
242 "build": {
243 "type": "string",
244 "example": "latest"
245 },
246 "timeoutSecs": {
247 "type": "integer",
248 "example": 300
249 },
250 "memoryMbytes": {
251 "type": "integer",
252 "example": 1024
253 },
254 "diskMbytes": {
255 "type": "integer",
256 "example": 2048
257 }
258 }
259 },
260 "buildId": {
261 "type": "string"
262 },
263 "defaultKeyValueStoreId": {
264 "type": "string"
265 },
266 "defaultDatasetId": {
267 "type": "string"
268 },
269 "defaultRequestQueueId": {
270 "type": "string"
271 },
272 "buildNumber": {
273 "type": "string",
274 "example": "1.0.0"
275 },
276 "containerUrl": {
277 "type": "string"
278 },
279 "usage": {
280 "type": "object",
281 "properties": {
282 "ACTOR_COMPUTE_UNITS": {
283 "type": "integer",
284 "example": 0
285 },
286 "DATASET_READS": {
287 "type": "integer",
288 "example": 0
289 },
290 "DATASET_WRITES": {
291 "type": "integer",
292 "example": 0
293 },
294 "KEY_VALUE_STORE_READS": {
295 "type": "integer",
296 "example": 0
297 },
298 "KEY_VALUE_STORE_WRITES": {
299 "type": "integer",
300 "example": 1
301 },
302 "KEY_VALUE_STORE_LISTS": {
303 "type": "integer",
304 "example": 0
305 },
306 "REQUEST_QUEUE_READS": {
307 "type": "integer",
308 "example": 0
309 },
310 "REQUEST_QUEUE_WRITES": {
311 "type": "integer",
312 "example": 0
313 },
314 "DATA_TRANSFER_INTERNAL_GBYTES": {
315 "type": "integer",
316 "example": 0
317 },
318 "DATA_TRANSFER_EXTERNAL_GBYTES": {
319 "type": "integer",
320 "example": 0
321 },
322 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
323 "type": "integer",
324 "example": 0
325 },
326 "PROXY_SERPS": {
327 "type": "integer",
328 "example": 0
329 }
330 }
331 },
332 "usageTotalUsd": {
333 "type": "number",
334 "example": 0.00005
335 },
336 "usageUsd": {
337 "type": "object",
338 "properties": {
339 "ACTOR_COMPUTE_UNITS": {
340 "type": "integer",
341 "example": 0
342 },
343 "DATASET_READS": {
344 "type": "integer",
345 "example": 0
346 },
347 "DATASET_WRITES": {
348 "type": "integer",
349 "example": 0
350 },
351 "KEY_VALUE_STORE_READS": {
352 "type": "integer",
353 "example": 0
354 },
355 "KEY_VALUE_STORE_WRITES": {
356 "type": "number",
357 "example": 0.00005
358 },
359 "KEY_VALUE_STORE_LISTS": {
360 "type": "integer",
361 "example": 0
362 },
363 "REQUEST_QUEUE_READS": {
364 "type": "integer",
365 "example": 0
366 },
367 "REQUEST_QUEUE_WRITES": {
368 "type": "integer",
369 "example": 0
370 },
371 "DATA_TRANSFER_INTERNAL_GBYTES": {
372 "type": "integer",
373 "example": 0
374 },
375 "DATA_TRANSFER_EXTERNAL_GBYTES": {
376 "type": "integer",
377 "example": 0
378 },
379 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
380 "type": "integer",
381 "example": 0
382 },
383 "PROXY_SERPS": {
384 "type": "integer",
385 "example": 0
386 }
387 }
388 }
389 }
390 }
391 }
392 }
393 }
394 }
395}The Hill 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 The Hill 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:
Hana Tsai
