Website Content to Markdown Scraper for LLM Training
Deprecated
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 ActorsWebsite Content to Markdown Scraper for LLM Training
easyapi/website-content-to-markdown-scraper-for-llm-training
π Transform web content into clean, LLM-ready Markdown! π Scrape multiple pages, extract main content, and convert to Markdown format. Perfect for AI researchers, data scientists, and LLM developers. Fast, efficient, and customizable. Supercharge your AI training data today! πππ§
You can access the Website Content to Markdown Scraper for LLM Training programmatically from your own applications by using the Apify API. You can choose the language preference from below. To use the Apify API, youβll 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": "vjCYgY2DSwDJaDyVT"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/easyapi~website-content-to-markdown-scraper-for-llm-training/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-easyapi-website-content-to-markdown-scraper-for-llm-training",
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 "$ref": "#/components/schemas/inputSchema"
27 }
28 }
29 }
30 },
31 "parameters": [
32 {
33 "name": "token",
34 "in": "query",
35 "required": true,
36 "schema": {
37 "type": "string"
38 },
39 "description": "Enter your Apify token here"
40 }
41 ],
42 "responses": {
43 "200": {
44 "description": "OK"
45 }
46 }
47 }
48 },
49 "/acts/easyapi~website-content-to-markdown-scraper-for-llm-training/runs": {
50 "post": {
51 "operationId": "runs-sync-easyapi-website-content-to-markdown-scraper-for-llm-training",
52 "x-openai-isConsequential": false,
53 "summary": "Executes an Actor and returns information about the initiated run in response.",
54 "tags": [
55 "Run Actor"
56 ],
57 "requestBody": {
58 "required": true,
59 "content": {
60 "application/json": {
61 "schema": {
62 "$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 "$ref": "#/components/schemas/runsResponseSchema"
85 }
86 }
87 }
88 }
89 }
90 }
91 },
92 "/acts/easyapi~website-content-to-markdown-scraper-for-llm-training/run-sync": {
93 "post": {
94 "operationId": "run-sync-easyapi-website-content-to-markdown-scraper-for-llm-training",
95 "x-openai-isConsequential": false,
96 "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
97 "tags": [
98 "Run Actor"
99 ],
100 "requestBody": {
101 "required": true,
102 "content": {
103 "application/json": {
104 "schema": {
105 "$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": "π Start URLs",
139 "type": "array",
140 "description": "List of URLs to start scraping from",
141 "default": [
142 "https://www.apify.com"
143 ],
144 "items": {
145 "type": "string"
146 }
147 },
148 "maxDepth": {
149 "title": "πΈοΈ Max Crawl Depth",
150 "minimum": 1,
151 "type": "integer",
152 "description": "Maximum depth of links to follow",
153 "default": 1
154 },
155 "sameDomain": {
156 "title": "π Stay on Same Domain",
157 "type": "boolean",
158 "description": "Whether to stay on the same domain while crawling",
159 "default": true
160 },
161 "maxResults": {
162 "title": "π’ Maximum Results",
163 "minimum": 1,
164 "type": "integer",
165 "description": "Maximum number of pages to scrape",
166 "default": 10
167 }
168 }
169 },
170 "runsResponseSchema": {
171 "type": "object",
172 "properties": {
173 "data": {
174 "type": "object",
175 "properties": {
176 "id": {
177 "type": "string"
178 },
179 "actId": {
180 "type": "string"
181 },
182 "userId": {
183 "type": "string"
184 },
185 "startedAt": {
186 "type": "string",
187 "format": "date-time",
188 "example": "2025-01-08T00:00:00.000Z"
189 },
190 "finishedAt": {
191 "type": "string",
192 "format": "date-time",
193 "example": "2025-01-08T00:00:00.000Z"
194 },
195 "status": {
196 "type": "string",
197 "example": "READY"
198 },
199 "meta": {
200 "type": "object",
201 "properties": {
202 "origin": {
203 "type": "string",
204 "example": "API"
205 },
206 "userAgent": {
207 "type": "string"
208 }
209 }
210 },
211 "stats": {
212 "type": "object",
213 "properties": {
214 "inputBodyLen": {
215 "type": "integer",
216 "example": 2000
217 },
218 "rebootCount": {
219 "type": "integer",
220 "example": 0
221 },
222 "restartCount": {
223 "type": "integer",
224 "example": 0
225 },
226 "resurrectCount": {
227 "type": "integer",
228 "example": 0
229 },
230 "computeUnits": {
231 "type": "integer",
232 "example": 0
233 }
234 }
235 },
236 "options": {
237 "type": "object",
238 "properties": {
239 "build": {
240 "type": "string",
241 "example": "latest"
242 },
243 "timeoutSecs": {
244 "type": "integer",
245 "example": 300
246 },
247 "memoryMbytes": {
248 "type": "integer",
249 "example": 1024
250 },
251 "diskMbytes": {
252 "type": "integer",
253 "example": 2048
254 }
255 }
256 },
257 "buildId": {
258 "type": "string"
259 },
260 "defaultKeyValueStoreId": {
261 "type": "string"
262 },
263 "defaultDatasetId": {
264 "type": "string"
265 },
266 "defaultRequestQueueId": {
267 "type": "string"
268 },
269 "buildNumber": {
270 "type": "string",
271 "example": "1.0.0"
272 },
273 "containerUrl": {
274 "type": "string"
275 },
276 "usage": {
277 "type": "object",
278 "properties": {
279 "ACTOR_COMPUTE_UNITS": {
280 "type": "integer",
281 "example": 0
282 },
283 "DATASET_READS": {
284 "type": "integer",
285 "example": 0
286 },
287 "DATASET_WRITES": {
288 "type": "integer",
289 "example": 0
290 },
291 "KEY_VALUE_STORE_READS": {
292 "type": "integer",
293 "example": 0
294 },
295 "KEY_VALUE_STORE_WRITES": {
296 "type": "integer",
297 "example": 1
298 },
299 "KEY_VALUE_STORE_LISTS": {
300 "type": "integer",
301 "example": 0
302 },
303 "REQUEST_QUEUE_READS": {
304 "type": "integer",
305 "example": 0
306 },
307 "REQUEST_QUEUE_WRITES": {
308 "type": "integer",
309 "example": 0
310 },
311 "DATA_TRANSFER_INTERNAL_GBYTES": {
312 "type": "integer",
313 "example": 0
314 },
315 "DATA_TRANSFER_EXTERNAL_GBYTES": {
316 "type": "integer",
317 "example": 0
318 },
319 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
320 "type": "integer",
321 "example": 0
322 },
323 "PROXY_SERPS": {
324 "type": "integer",
325 "example": 0
326 }
327 }
328 },
329 "usageTotalUsd": {
330 "type": "number",
331 "example": 0.00005
332 },
333 "usageUsd": {
334 "type": "object",
335 "properties": {
336 "ACTOR_COMPUTE_UNITS": {
337 "type": "integer",
338 "example": 0
339 },
340 "DATASET_READS": {
341 "type": "integer",
342 "example": 0
343 },
344 "DATASET_WRITES": {
345 "type": "integer",
346 "example": 0
347 },
348 "KEY_VALUE_STORE_READS": {
349 "type": "integer",
350 "example": 0
351 },
352 "KEY_VALUE_STORE_WRITES": {
353 "type": "number",
354 "example": 0.00005
355 },
356 "KEY_VALUE_STORE_LISTS": {
357 "type": "integer",
358 "example": 0
359 },
360 "REQUEST_QUEUE_READS": {
361 "type": "integer",
362 "example": 0
363 },
364 "REQUEST_QUEUE_WRITES": {
365 "type": "integer",
366 "example": 0
367 },
368 "DATA_TRANSFER_INTERNAL_GBYTES": {
369 "type": "integer",
370 "example": 0
371 },
372 "DATA_TRANSFER_EXTERNAL_GBYTES": {
373 "type": "integer",
374 "example": 0
375 },
376 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
377 "type": "integer",
378 "example": 0
379 },
380 "PROXY_SERPS": {
381 "type": "integer",
382 "example": 0
383 }
384 }
385 }
386 }
387 }
388 }
389 }
390 }
391 }
392}Website Content to Markdown Scraper for LLM Training 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 Website Content to Markdown Scraper for LLM Training from the options below:
If youβd like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients:
Developer
EasyApiMaintained by Community
Categories
