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 $15.00/month - No credit card required now
A fast and powerful tool for extracting article data from URLs. It uses advanced scraping techniques to parse HTML and extract relevant information such as the article title, author, publication date, and content. Download your data in any format (JSON, CSV, XML, RSS, HTML Table).
You can access the Articles Extractor programmatically from your own applications by using the Apify API. You can choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "0.0",
5 "x-build-id": "Sm2JV8vYbTuF9PIy5"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/web.harvester~articles-extractor/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-web.harvester-articles-extractor",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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 "saveArticleHtml": {
154 "title": "Save article HTML",
155 "type": "boolean",
156 "description": "If checked, it saves only the article section of the HTML for each article.",
157 "default": false
158 },
159 "savePageHtml": {
160 "title": "Save full page HTML",
161 "type": "boolean",
162 "description": "If checked, it saves the whole HTML for each article.",
163 "default": false
164 },
165 "newContentParser": {
166 "title": "(New!) Use new content parser",
167 "type": "boolean",
168 "description": "If checked, it uses the new content parser. If unchecked, it uses the old one.",
169 "default": false
170 },
171 "customHeaders": {
172 "title": "Custom headers",
173 "type": "object",
174 "description": "Custom headers to be added to each request."
175 },
176 "proxyConfiguration": {
177 "title": "Proxy configuration",
178 "type": "object",
179 "description": "This is required if you want to use Apify Proxy.",
180 "default": {
181 "useApifyProxy": true
182 }
183 }
184 }
185 },
186 "runsResponseSchema": {
187 "type": "object",
188 "properties": {
189 "data": {
190 "type": "object",
191 "properties": {
192 "id": {
193 "type": "string"
194 },
195 "actId": {
196 "type": "string"
197 },
198 "userId": {
199 "type": "string"
200 },
201 "startedAt": {
202 "type": "string",
203 "format": "date-time",
204 "example": "2025-01-08T00:00:00.000Z"
205 },
206 "finishedAt": {
207 "type": "string",
208 "format": "date-time",
209 "example": "2025-01-08T00:00:00.000Z"
210 },
211 "status": {
212 "type": "string",
213 "example": "READY"
214 },
215 "meta": {
216 "type": "object",
217 "properties": {
218 "origin": {
219 "type": "string",
220 "example": "API"
221 },
222 "userAgent": {
223 "type": "string"
224 }
225 }
226 },
227 "stats": {
228 "type": "object",
229 "properties": {
230 "inputBodyLen": {
231 "type": "integer",
232 "example": 2000
233 },
234 "rebootCount": {
235 "type": "integer",
236 "example": 0
237 },
238 "restartCount": {
239 "type": "integer",
240 "example": 0
241 },
242 "resurrectCount": {
243 "type": "integer",
244 "example": 0
245 },
246 "computeUnits": {
247 "type": "integer",
248 "example": 0
249 }
250 }
251 },
252 "options": {
253 "type": "object",
254 "properties": {
255 "build": {
256 "type": "string",
257 "example": "latest"
258 },
259 "timeoutSecs": {
260 "type": "integer",
261 "example": 300
262 },
263 "memoryMbytes": {
264 "type": "integer",
265 "example": 1024
266 },
267 "diskMbytes": {
268 "type": "integer",
269 "example": 2048
270 }
271 }
272 },
273 "buildId": {
274 "type": "string"
275 },
276 "defaultKeyValueStoreId": {
277 "type": "string"
278 },
279 "defaultDatasetId": {
280 "type": "string"
281 },
282 "defaultRequestQueueId": {
283 "type": "string"
284 },
285 "buildNumber": {
286 "type": "string",
287 "example": "1.0.0"
288 },
289 "containerUrl": {
290 "type": "string"
291 },
292 "usage": {
293 "type": "object",
294 "properties": {
295 "ACTOR_COMPUTE_UNITS": {
296 "type": "integer",
297 "example": 0
298 },
299 "DATASET_READS": {
300 "type": "integer",
301 "example": 0
302 },
303 "DATASET_WRITES": {
304 "type": "integer",
305 "example": 0
306 },
307 "KEY_VALUE_STORE_READS": {
308 "type": "integer",
309 "example": 0
310 },
311 "KEY_VALUE_STORE_WRITES": {
312 "type": "integer",
313 "example": 1
314 },
315 "KEY_VALUE_STORE_LISTS": {
316 "type": "integer",
317 "example": 0
318 },
319 "REQUEST_QUEUE_READS": {
320 "type": "integer",
321 "example": 0
322 },
323 "REQUEST_QUEUE_WRITES": {
324 "type": "integer",
325 "example": 0
326 },
327 "DATA_TRANSFER_INTERNAL_GBYTES": {
328 "type": "integer",
329 "example": 0
330 },
331 "DATA_TRANSFER_EXTERNAL_GBYTES": {
332 "type": "integer",
333 "example": 0
334 },
335 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
336 "type": "integer",
337 "example": 0
338 },
339 "PROXY_SERPS": {
340 "type": "integer",
341 "example": 0
342 }
343 }
344 },
345 "usageTotalUsd": {
346 "type": "number",
347 "example": 0.00005
348 },
349 "usageUsd": {
350 "type": "object",
351 "properties": {
352 "ACTOR_COMPUTE_UNITS": {
353 "type": "integer",
354 "example": 0
355 },
356 "DATASET_READS": {
357 "type": "integer",
358 "example": 0
359 },
360 "DATASET_WRITES": {
361 "type": "integer",
362 "example": 0
363 },
364 "KEY_VALUE_STORE_READS": {
365 "type": "integer",
366 "example": 0
367 },
368 "KEY_VALUE_STORE_WRITES": {
369 "type": "number",
370 "example": 0.00005
371 },
372 "KEY_VALUE_STORE_LISTS": {
373 "type": "integer",
374 "example": 0
375 },
376 "REQUEST_QUEUE_READS": {
377 "type": "integer",
378 "example": 0
379 },
380 "REQUEST_QUEUE_WRITES": {
381 "type": "integer",
382 "example": 0
383 },
384 "DATA_TRANSFER_INTERNAL_GBYTES": {
385 "type": "integer",
386 "example": 0
387 },
388 "DATA_TRANSFER_EXTERNAL_GBYTES": {
389 "type": "integer",
390 "example": 0
391 },
392 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
393 "type": "integer",
394 "example": 0
395 },
396 "PROXY_SERPS": {
397 "type": "integer",
398 "example": 0
399 }
400 }
401 }
402 }
403 }
404 }
405 }
406 }
407 }
408}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:
Developer
Web HarvesterMaintained by Community
Actor Metrics
39 monthly users
-
14 bookmarks
>99% runs succeeded
Created in Jun 2023
Modified 4 months ago
