Article Text Extractor
Try for free
No credit card required
Go to Store
Article Text Extractor
mtrunkat/article-text-extractor
Try for free
No credit card required
Simply extracts article texts and other meta info from the given URL. Uses https://github.com/ageitgey/node-unfluff which is a NodeJS implementation of https://github.com/grangier/python-goose.
You can access the Article Text 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": "0.1",
5 "x-build-id": "Fu3DfLv8d6paSTyxG"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/mtrunkat~article-text-extractor/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-mtrunkat-article-text-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 "$ref": "#/components/schemas/inputSchema"
27 }
28 }
29 }
30 },
31 "parameters": [
32 {
33 "name": "token",
34 "in": "query",
35 "required": true,
36 "schema": {
37 "type": "string"
38 },
39 "description": "Enter your Apify token here"
40 }
41 ],
42 "responses": {
43 "200": {
44 "description": "OK"
45 }
46 }
47 }
48 },
49 "/acts/mtrunkat~article-text-extractor/runs": {
50 "post": {
51 "operationId": "runs-sync-mtrunkat-article-text-extractor",
52 "x-openai-isConsequential": false,
53 "summary": "Executes an Actor and returns information about the initiated run in response.",
54 "tags": [
55 "Run Actor"
56 ],
57 "requestBody": {
58 "required": true,
59 "content": {
60 "application/json": {
61 "schema": {
62 "$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 "$ref": "#/components/schemas/runsResponseSchema"
85 }
86 }
87 }
88 }
89 }
90 }
91 },
92 "/acts/mtrunkat~article-text-extractor/run-sync": {
93 "post": {
94 "operationId": "run-sync-mtrunkat-article-text-extractor",
95 "x-openai-isConsequential": false,
96 "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
97 "tags": [
98 "Run Actor"
99 ],
100 "requestBody": {
101 "required": true,
102 "content": {
103 "application/json": {
104 "schema": {
105 "$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 "required": [
134 "url"
135 ],
136 "properties": {
137 "url": {
138 "title": "Article URL",
139 "type": "string",
140 "description": "Fill the article URL, from which you want to extract data."
141 }
142 }
143 },
144 "runsResponseSchema": {
145 "type": "object",
146 "properties": {
147 "data": {
148 "type": "object",
149 "properties": {
150 "id": {
151 "type": "string"
152 },
153 "actId": {
154 "type": "string"
155 },
156 "userId": {
157 "type": "string"
158 },
159 "startedAt": {
160 "type": "string",
161 "format": "date-time",
162 "example": "2025-01-08T00:00:00.000Z"
163 },
164 "finishedAt": {
165 "type": "string",
166 "format": "date-time",
167 "example": "2025-01-08T00:00:00.000Z"
168 },
169 "status": {
170 "type": "string",
171 "example": "READY"
172 },
173 "meta": {
174 "type": "object",
175 "properties": {
176 "origin": {
177 "type": "string",
178 "example": "API"
179 },
180 "userAgent": {
181 "type": "string"
182 }
183 }
184 },
185 "stats": {
186 "type": "object",
187 "properties": {
188 "inputBodyLen": {
189 "type": "integer",
190 "example": 2000
191 },
192 "rebootCount": {
193 "type": "integer",
194 "example": 0
195 },
196 "restartCount": {
197 "type": "integer",
198 "example": 0
199 },
200 "resurrectCount": {
201 "type": "integer",
202 "example": 0
203 },
204 "computeUnits": {
205 "type": "integer",
206 "example": 0
207 }
208 }
209 },
210 "options": {
211 "type": "object",
212 "properties": {
213 "build": {
214 "type": "string",
215 "example": "latest"
216 },
217 "timeoutSecs": {
218 "type": "integer",
219 "example": 300
220 },
221 "memoryMbytes": {
222 "type": "integer",
223 "example": 1024
224 },
225 "diskMbytes": {
226 "type": "integer",
227 "example": 2048
228 }
229 }
230 },
231 "buildId": {
232 "type": "string"
233 },
234 "defaultKeyValueStoreId": {
235 "type": "string"
236 },
237 "defaultDatasetId": {
238 "type": "string"
239 },
240 "defaultRequestQueueId": {
241 "type": "string"
242 },
243 "buildNumber": {
244 "type": "string",
245 "example": "1.0.0"
246 },
247 "containerUrl": {
248 "type": "string"
249 },
250 "usage": {
251 "type": "object",
252 "properties": {
253 "ACTOR_COMPUTE_UNITS": {
254 "type": "integer",
255 "example": 0
256 },
257 "DATASET_READS": {
258 "type": "integer",
259 "example": 0
260 },
261 "DATASET_WRITES": {
262 "type": "integer",
263 "example": 0
264 },
265 "KEY_VALUE_STORE_READS": {
266 "type": "integer",
267 "example": 0
268 },
269 "KEY_VALUE_STORE_WRITES": {
270 "type": "integer",
271 "example": 1
272 },
273 "KEY_VALUE_STORE_LISTS": {
274 "type": "integer",
275 "example": 0
276 },
277 "REQUEST_QUEUE_READS": {
278 "type": "integer",
279 "example": 0
280 },
281 "REQUEST_QUEUE_WRITES": {
282 "type": "integer",
283 "example": 0
284 },
285 "DATA_TRANSFER_INTERNAL_GBYTES": {
286 "type": "integer",
287 "example": 0
288 },
289 "DATA_TRANSFER_EXTERNAL_GBYTES": {
290 "type": "integer",
291 "example": 0
292 },
293 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
294 "type": "integer",
295 "example": 0
296 },
297 "PROXY_SERPS": {
298 "type": "integer",
299 "example": 0
300 }
301 }
302 },
303 "usageTotalUsd": {
304 "type": "number",
305 "example": 0.00005
306 },
307 "usageUsd": {
308 "type": "object",
309 "properties": {
310 "ACTOR_COMPUTE_UNITS": {
311 "type": "integer",
312 "example": 0
313 },
314 "DATASET_READS": {
315 "type": "integer",
316 "example": 0
317 },
318 "DATASET_WRITES": {
319 "type": "integer",
320 "example": 0
321 },
322 "KEY_VALUE_STORE_READS": {
323 "type": "integer",
324 "example": 0
325 },
326 "KEY_VALUE_STORE_WRITES": {
327 "type": "number",
328 "example": 0.00005
329 },
330 "KEY_VALUE_STORE_LISTS": {
331 "type": "integer",
332 "example": 0
333 },
334 "REQUEST_QUEUE_READS": {
335 "type": "integer",
336 "example": 0
337 },
338 "REQUEST_QUEUE_WRITES": {
339 "type": "integer",
340 "example": 0
341 },
342 "DATA_TRANSFER_INTERNAL_GBYTES": {
343 "type": "integer",
344 "example": 0
345 },
346 "DATA_TRANSFER_EXTERNAL_GBYTES": {
347 "type": "integer",
348 "example": 0
349 },
350 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
351 "type": "integer",
352 "example": 0
353 },
354 "PROXY_SERPS": {
355 "type": "integer",
356 "example": 0
357 }
358 }
359 }
360 }
361 }
362 }
363 }
364 }
365 }
366}Article Text 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 Article Text 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
Marek TrunkátMaintained by Community
Actor Metrics
35 monthly users
-
12 bookmarks
>99% runs succeeded
Created in Mar 2018
Modified a year ago
Categories
