Wordpress Post Scraper - NEW
Try for free
2 hours trial then $5.00/month - No credit card required now
Go to Store
Wordpress Post Scraper - NEW
eloquent_mountain/wordpress-post-scraper---new
Try for free
2 hours trial then $5.00/month - No credit card required now
This actor scrapes WordPress blog posts of one or more websites, cleans the HTML content, and pushes flattened JSON data (collects all data it can find in the post). It uses Selenium to handle pages requiring JavaScript rendering.
You can access the Wordpress Post Scraper - NEW programmatically from your own applications by using the Apify API. You can choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "0.0",
5 "x-build-id": "jeGePBDvewgGTTc9q"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/eloquent_mountain~wordpress-post-scraper---new/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-eloquent_mountain-wordpress-post-scraper---new",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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/eloquent_mountain~wordpress-post-scraper---new/runs": {
50 "post": {
51 "operationId": "runs-sync-eloquent_mountain-wordpress-post-scraper---new",
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/eloquent_mountain~wordpress-post-scraper---new/run-sync": {
93 "post": {
94 "operationId": "run-sync-eloquent_mountain-wordpress-post-scraper---new",
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 "start_urls"
135 ],
136 "properties": {
137 "start_urls": {
138 "title": "List of WordPress URLs",
139 "type": "array",
140 "description": "List of WordPress websites to scrape",
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 "scrape_mode": {
156 "title": "Data to scrape",
157 "enum": [
158 "posts",
159 "media",
160 "categories",
161 "comments"
162 ],
163 "type": "string",
164 "description": "Choose the data you wish to scrape.",
165 "default": "posts"
166 },
167 "max_results": {
168 "title": "Maximum number of results ('all' to scrape all posts)",
169 "type": "string",
170 "description": "Maximum number of posts to scrape per website. Use 'all' to scrape all posts.",
171 "default": "20"
172 }
173 }
174 },
175 "runsResponseSchema": {
176 "type": "object",
177 "properties": {
178 "data": {
179 "type": "object",
180 "properties": {
181 "id": {
182 "type": "string"
183 },
184 "actId": {
185 "type": "string"
186 },
187 "userId": {
188 "type": "string"
189 },
190 "startedAt": {
191 "type": "string",
192 "format": "date-time",
193 "example": "2025-01-08T00:00:00.000Z"
194 },
195 "finishedAt": {
196 "type": "string",
197 "format": "date-time",
198 "example": "2025-01-08T00:00:00.000Z"
199 },
200 "status": {
201 "type": "string",
202 "example": "READY"
203 },
204 "meta": {
205 "type": "object",
206 "properties": {
207 "origin": {
208 "type": "string",
209 "example": "API"
210 },
211 "userAgent": {
212 "type": "string"
213 }
214 }
215 },
216 "stats": {
217 "type": "object",
218 "properties": {
219 "inputBodyLen": {
220 "type": "integer",
221 "example": 2000
222 },
223 "rebootCount": {
224 "type": "integer",
225 "example": 0
226 },
227 "restartCount": {
228 "type": "integer",
229 "example": 0
230 },
231 "resurrectCount": {
232 "type": "integer",
233 "example": 0
234 },
235 "computeUnits": {
236 "type": "integer",
237 "example": 0
238 }
239 }
240 },
241 "options": {
242 "type": "object",
243 "properties": {
244 "build": {
245 "type": "string",
246 "example": "latest"
247 },
248 "timeoutSecs": {
249 "type": "integer",
250 "example": 300
251 },
252 "memoryMbytes": {
253 "type": "integer",
254 "example": 1024
255 },
256 "diskMbytes": {
257 "type": "integer",
258 "example": 2048
259 }
260 }
261 },
262 "buildId": {
263 "type": "string"
264 },
265 "defaultKeyValueStoreId": {
266 "type": "string"
267 },
268 "defaultDatasetId": {
269 "type": "string"
270 },
271 "defaultRequestQueueId": {
272 "type": "string"
273 },
274 "buildNumber": {
275 "type": "string",
276 "example": "1.0.0"
277 },
278 "containerUrl": {
279 "type": "string"
280 },
281 "usage": {
282 "type": "object",
283 "properties": {
284 "ACTOR_COMPUTE_UNITS": {
285 "type": "integer",
286 "example": 0
287 },
288 "DATASET_READS": {
289 "type": "integer",
290 "example": 0
291 },
292 "DATASET_WRITES": {
293 "type": "integer",
294 "example": 0
295 },
296 "KEY_VALUE_STORE_READS": {
297 "type": "integer",
298 "example": 0
299 },
300 "KEY_VALUE_STORE_WRITES": {
301 "type": "integer",
302 "example": 1
303 },
304 "KEY_VALUE_STORE_LISTS": {
305 "type": "integer",
306 "example": 0
307 },
308 "REQUEST_QUEUE_READS": {
309 "type": "integer",
310 "example": 0
311 },
312 "REQUEST_QUEUE_WRITES": {
313 "type": "integer",
314 "example": 0
315 },
316 "DATA_TRANSFER_INTERNAL_GBYTES": {
317 "type": "integer",
318 "example": 0
319 },
320 "DATA_TRANSFER_EXTERNAL_GBYTES": {
321 "type": "integer",
322 "example": 0
323 },
324 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
325 "type": "integer",
326 "example": 0
327 },
328 "PROXY_SERPS": {
329 "type": "integer",
330 "example": 0
331 }
332 }
333 },
334 "usageTotalUsd": {
335 "type": "number",
336 "example": 0.00005
337 },
338 "usageUsd": {
339 "type": "object",
340 "properties": {
341 "ACTOR_COMPUTE_UNITS": {
342 "type": "integer",
343 "example": 0
344 },
345 "DATASET_READS": {
346 "type": "integer",
347 "example": 0
348 },
349 "DATASET_WRITES": {
350 "type": "integer",
351 "example": 0
352 },
353 "KEY_VALUE_STORE_READS": {
354 "type": "integer",
355 "example": 0
356 },
357 "KEY_VALUE_STORE_WRITES": {
358 "type": "number",
359 "example": 0.00005
360 },
361 "KEY_VALUE_STORE_LISTS": {
362 "type": "integer",
363 "example": 0
364 },
365 "REQUEST_QUEUE_READS": {
366 "type": "integer",
367 "example": 0
368 },
369 "REQUEST_QUEUE_WRITES": {
370 "type": "integer",
371 "example": 0
372 },
373 "DATA_TRANSFER_INTERNAL_GBYTES": {
374 "type": "integer",
375 "example": 0
376 },
377 "DATA_TRANSFER_EXTERNAL_GBYTES": {
378 "type": "integer",
379 "example": 0
380 },
381 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
382 "type": "integer",
383 "example": 0
384 },
385 "PROXY_SERPS": {
386 "type": "integer",
387 "example": 0
388 }
389 }
390 }
391 }
392 }
393 }
394 }
395 }
396 }
397}Wordpress Post Scraper - NEW 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 Wordpress Post Scraper - NEW 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
PacoMaintained by Community
Actor Metrics
15 monthly users
-
4 bookmarks
>99% runs succeeded
19 hours response time
Created in Oct 2024
Modified 25 days ago
Categories
