Articles Extractor
Try for free
3 days trial then $15.00/month - No credit card required now
Go to Store
Articles Extractor
web.harvester/articles-extractor
Try for free
3 days trial then $15.00/month - No credit card required now
The Article Extractor is an enterprise-grade web scraping solution designed specifically for extracting structured data from news articles, blog posts, and online publications. Our advanced HTML parsing engine delivers unmatched accuracy in content extraction across thousands of websites.
Developer
Web HarvesterMaintained by Community
Actor Metrics
34 monthly users
5.0 / 5 (2)
17 bookmarks
>99% runs succeeded
Created in Jun 2023
Modified 21 hours ago
You can access the Articles Extractor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "0.0",
5 "x-build-id": "uYJLOMkUwxyiZfa7n"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/web.harvester~articles-extractor/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-web.harvester-articles-extractor",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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/web.harvester~articles-extractor/runs": {
50 "post": {
51 "operationId": "runs-sync-web.harvester-articles-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/web.harvester~articles-extractor/run-sync": {
93 "post": {
94 "operationId": "run-sync-web.harvester-articles-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 "properties": {
134 "startUrls": {
135 "title": "Start URLs",
136 "type": "array",
137 "description": "List of Article URLs to extract",
138 "default": [],
139 "items": {
140 "type": "object",
141 "required": [
142 "url"
143 ],
144 "properties": {
145 "url": {
146 "type": "string",
147 "title": "URL of a web page",
148 "format": "uri"
149 }
150 }
151 }
152 },
153 "alternativeParser": {
154 "title": "Use alternative parser",
155 "type": "boolean",
156 "description": "Enable to use the alternative content parser which preserves more formatting. Might be better for some websites.",
157 "default": false
158 },
159 "saveArticleHtml": {
160 "title": "Save article HTML",
161 "type": "boolean",
162 "description": "If checked, it saves only the article section of the HTML for each article.",
163 "default": false
164 },
165 "savePageHtml": {
166 "title": "Save full page HTML",
167 "type": "boolean",
168 "description": "If checked, it saves the whole HTML for each article.",
169 "default": false
170 },
171 "customHeaders": {
172 "title": "Custom headers (Manual)",
173 "type": "object",
174 "description": "Custom headers to be added to each request."
175 },
176 "useHeaderGenerator": {
177 "title": "Use header generator (Random)",
178 "type": "boolean",
179 "description": "If checked, it uses the header generator to generate random headers for each request.",
180 "default": false
181 },
182 "headerGeneratorOptions": {
183 "title": "Header generator options (Can be left empty)",
184 "type": "object",
185 "description": "Configure options for the header generator including devices and browsers to emulate. This helps in generating realistic browser headers for your requests."
186 },
187 "proxyConfiguration": {
188 "title": "Proxy configuration (Residential Proxies are recommended)",
189 "type": "object",
190 "description": "This is required if you want to use Apify Proxy.",
191 "default": {
192 "useApifyProxy": true,
193 "apifyProxyGroups": [
194 "RESIDENTIAL"
195 ]
196 }
197 }
198 }
199 },
200 "runsResponseSchema": {
201 "type": "object",
202 "properties": {
203 "data": {
204 "type": "object",
205 "properties": {
206 "id": {
207 "type": "string"
208 },
209 "actId": {
210 "type": "string"
211 },
212 "userId": {
213 "type": "string"
214 },
215 "startedAt": {
216 "type": "string",
217 "format": "date-time",
218 "example": "2025-01-08T00:00:00.000Z"
219 },
220 "finishedAt": {
221 "type": "string",
222 "format": "date-time",
223 "example": "2025-01-08T00:00:00.000Z"
224 },
225 "status": {
226 "type": "string",
227 "example": "READY"
228 },
229 "meta": {
230 "type": "object",
231 "properties": {
232 "origin": {
233 "type": "string",
234 "example": "API"
235 },
236 "userAgent": {
237 "type": "string"
238 }
239 }
240 },
241 "stats": {
242 "type": "object",
243 "properties": {
244 "inputBodyLen": {
245 "type": "integer",
246 "example": 2000
247 },
248 "rebootCount": {
249 "type": "integer",
250 "example": 0
251 },
252 "restartCount": {
253 "type": "integer",
254 "example": 0
255 },
256 "resurrectCount": {
257 "type": "integer",
258 "example": 0
259 },
260 "computeUnits": {
261 "type": "integer",
262 "example": 0
263 }
264 }
265 },
266 "options": {
267 "type": "object",
268 "properties": {
269 "build": {
270 "type": "string",
271 "example": "latest"
272 },
273 "timeoutSecs": {
274 "type": "integer",
275 "example": 300
276 },
277 "memoryMbytes": {
278 "type": "integer",
279 "example": 1024
280 },
281 "diskMbytes": {
282 "type": "integer",
283 "example": 2048
284 }
285 }
286 },
287 "buildId": {
288 "type": "string"
289 },
290 "defaultKeyValueStoreId": {
291 "type": "string"
292 },
293 "defaultDatasetId": {
294 "type": "string"
295 },
296 "defaultRequestQueueId": {
297 "type": "string"
298 },
299 "buildNumber": {
300 "type": "string",
301 "example": "1.0.0"
302 },
303 "containerUrl": {
304 "type": "string"
305 },
306 "usage": {
307 "type": "object",
308 "properties": {
309 "ACTOR_COMPUTE_UNITS": {
310 "type": "integer",
311 "example": 0
312 },
313 "DATASET_READS": {
314 "type": "integer",
315 "example": 0
316 },
317 "DATASET_WRITES": {
318 "type": "integer",
319 "example": 0
320 },
321 "KEY_VALUE_STORE_READS": {
322 "type": "integer",
323 "example": 0
324 },
325 "KEY_VALUE_STORE_WRITES": {
326 "type": "integer",
327 "example": 1
328 },
329 "KEY_VALUE_STORE_LISTS": {
330 "type": "integer",
331 "example": 0
332 },
333 "REQUEST_QUEUE_READS": {
334 "type": "integer",
335 "example": 0
336 },
337 "REQUEST_QUEUE_WRITES": {
338 "type": "integer",
339 "example": 0
340 },
341 "DATA_TRANSFER_INTERNAL_GBYTES": {
342 "type": "integer",
343 "example": 0
344 },
345 "DATA_TRANSFER_EXTERNAL_GBYTES": {
346 "type": "integer",
347 "example": 0
348 },
349 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
350 "type": "integer",
351 "example": 0
352 },
353 "PROXY_SERPS": {
354 "type": "integer",
355 "example": 0
356 }
357 }
358 },
359 "usageTotalUsd": {
360 "type": "number",
361 "example": 0.00005
362 },
363 "usageUsd": {
364 "type": "object",
365 "properties": {
366 "ACTOR_COMPUTE_UNITS": {
367 "type": "integer",
368 "example": 0
369 },
370 "DATASET_READS": {
371 "type": "integer",
372 "example": 0
373 },
374 "DATASET_WRITES": {
375 "type": "integer",
376 "example": 0
377 },
378 "KEY_VALUE_STORE_READS": {
379 "type": "integer",
380 "example": 0
381 },
382 "KEY_VALUE_STORE_WRITES": {
383 "type": "number",
384 "example": 0.00005
385 },
386 "KEY_VALUE_STORE_LISTS": {
387 "type": "integer",
388 "example": 0
389 },
390 "REQUEST_QUEUE_READS": {
391 "type": "integer",
392 "example": 0
393 },
394 "REQUEST_QUEUE_WRITES": {
395 "type": "integer",
396 "example": 0
397 },
398 "DATA_TRANSFER_INTERNAL_GBYTES": {
399 "type": "integer",
400 "example": 0
401 },
402 "DATA_TRANSFER_EXTERNAL_GBYTES": {
403 "type": "integer",
404 "example": 0
405 },
406 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
407 "type": "integer",
408 "example": 0
409 },
410 "PROXY_SERPS": {
411 "type": "integer",
412 "example": 0
413 }
414 }
415 }
416 }
417 }
418 }
419 }
420 }
421 }
422}Articles 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 Articles 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:
