Website Media Link Scraper
Try for free
Pay $5.00 for 1,000 results
Go to Store
Website Media Link Scraper
thenetaji/website-media-link-scraper
Try for free
Pay $5.00 for 1,000 results
Extract video, audio, and image links from websites with this efficient web crawler. Uses lightweight HTTP requests to discover media URLs across entire sites without browser overhead. Fast, reliable, and resource-friendly.
You can access the Website Media Link Scraper programmatically from your own applications by using the Apify API. You can choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "1.0",
5 "x-build-id": "0Z3rM8Qe6ZX1ecAgd"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/thenetaji~website-media-link-scraper/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-thenetaji-website-media-link-scraper",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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/thenetaji~website-media-link-scraper/runs": {
50 "post": {
51 "operationId": "runs-sync-thenetaji-website-media-link-scraper",
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/thenetaji~website-media-link-scraper/run-sync": {
93 "post": {
94 "operationId": "run-sync-thenetaji-website-media-link-scraper",
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 "mediaType"
136 ],
137 "properties": {
138 "startUrls": {
139 "title": "Start URLs",
140 "type": "array",
141 "description": "List of URLs to start crawling from",
142 "default": [
143 {
144 "url": "https://apify.com/"
145 }
146 ],
147 "items": {
148 "type": "object",
149 "required": [
150 "url"
151 ],
152 "properties": {
153 "url": {
154 "type": "string",
155 "title": "URL of a web page",
156 "format": "uri"
157 }
158 }
159 }
160 },
161 "mediaType": {
162 "title": "Media Type",
163 "enum": [
164 "video",
165 "audio",
166 "image",
167 "all"
168 ],
169 "type": "string",
170 "description": "The type of media links to extract from the crawled pages",
171 "default": "all"
172 },
173 "maxCrawlDepth": {
174 "title": "Maximum Crawl Depth",
175 "minimum": 1,
176 "maximum": 10,
177 "type": "integer",
178 "description": "Maximum depth to crawl from the start URLs (higher values may significantly increase run time)",
179 "default": 2
180 },
181 "maxConcurrency": {
182 "title": "Max Concurrency",
183 "minimum": 1,
184 "maximum": 50,
185 "type": "integer",
186 "description": "Maximum number of pages to crawl concurrently",
187 "default": 10
188 },
189 "maxUrlsToCrawl": {
190 "title": "Max number of results",
191 "minimum": 10,
192 "type": "integer",
193 "description": "Maximum number of urls to crawl",
194 "default": 100
195 },
196 "maxRequestRetries": {
197 "title": "Max Request Retries",
198 "minimum": 0,
199 "maximum": 5,
200 "type": "integer",
201 "description": "Maximum number of times to retry a request if it fails",
202 "default": 3
203 },
204 "useProxy": {
205 "title": "Use Proxy",
206 "type": "object",
207 "description": "Whether to use Apify Proxy for making requests (recommended for most websites)",
208 "default": {
209 "useApifyProxy": false,
210 "apifyProxyGroups": []
211 }
212 }
213 }
214 },
215 "runsResponseSchema": {
216 "type": "object",
217 "properties": {
218 "data": {
219 "type": "object",
220 "properties": {
221 "id": {
222 "type": "string"
223 },
224 "actId": {
225 "type": "string"
226 },
227 "userId": {
228 "type": "string"
229 },
230 "startedAt": {
231 "type": "string",
232 "format": "date-time",
233 "example": "2025-01-08T00:00:00.000Z"
234 },
235 "finishedAt": {
236 "type": "string",
237 "format": "date-time",
238 "example": "2025-01-08T00:00:00.000Z"
239 },
240 "status": {
241 "type": "string",
242 "example": "READY"
243 },
244 "meta": {
245 "type": "object",
246 "properties": {
247 "origin": {
248 "type": "string",
249 "example": "API"
250 },
251 "userAgent": {
252 "type": "string"
253 }
254 }
255 },
256 "stats": {
257 "type": "object",
258 "properties": {
259 "inputBodyLen": {
260 "type": "integer",
261 "example": 2000
262 },
263 "rebootCount": {
264 "type": "integer",
265 "example": 0
266 },
267 "restartCount": {
268 "type": "integer",
269 "example": 0
270 },
271 "resurrectCount": {
272 "type": "integer",
273 "example": 0
274 },
275 "computeUnits": {
276 "type": "integer",
277 "example": 0
278 }
279 }
280 },
281 "options": {
282 "type": "object",
283 "properties": {
284 "build": {
285 "type": "string",
286 "example": "latest"
287 },
288 "timeoutSecs": {
289 "type": "integer",
290 "example": 300
291 },
292 "memoryMbytes": {
293 "type": "integer",
294 "example": 1024
295 },
296 "diskMbytes": {
297 "type": "integer",
298 "example": 2048
299 }
300 }
301 },
302 "buildId": {
303 "type": "string"
304 },
305 "defaultKeyValueStoreId": {
306 "type": "string"
307 },
308 "defaultDatasetId": {
309 "type": "string"
310 },
311 "defaultRequestQueueId": {
312 "type": "string"
313 },
314 "buildNumber": {
315 "type": "string",
316 "example": "1.0.0"
317 },
318 "containerUrl": {
319 "type": "string"
320 },
321 "usage": {
322 "type": "object",
323 "properties": {
324 "ACTOR_COMPUTE_UNITS": {
325 "type": "integer",
326 "example": 0
327 },
328 "DATASET_READS": {
329 "type": "integer",
330 "example": 0
331 },
332 "DATASET_WRITES": {
333 "type": "integer",
334 "example": 0
335 },
336 "KEY_VALUE_STORE_READS": {
337 "type": "integer",
338 "example": 0
339 },
340 "KEY_VALUE_STORE_WRITES": {
341 "type": "integer",
342 "example": 1
343 },
344 "KEY_VALUE_STORE_LISTS": {
345 "type": "integer",
346 "example": 0
347 },
348 "REQUEST_QUEUE_READS": {
349 "type": "integer",
350 "example": 0
351 },
352 "REQUEST_QUEUE_WRITES": {
353 "type": "integer",
354 "example": 0
355 },
356 "DATA_TRANSFER_INTERNAL_GBYTES": {
357 "type": "integer",
358 "example": 0
359 },
360 "DATA_TRANSFER_EXTERNAL_GBYTES": {
361 "type": "integer",
362 "example": 0
363 },
364 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
365 "type": "integer",
366 "example": 0
367 },
368 "PROXY_SERPS": {
369 "type": "integer",
370 "example": 0
371 }
372 }
373 },
374 "usageTotalUsd": {
375 "type": "number",
376 "example": 0.00005
377 },
378 "usageUsd": {
379 "type": "object",
380 "properties": {
381 "ACTOR_COMPUTE_UNITS": {
382 "type": "integer",
383 "example": 0
384 },
385 "DATASET_READS": {
386 "type": "integer",
387 "example": 0
388 },
389 "DATASET_WRITES": {
390 "type": "integer",
391 "example": 0
392 },
393 "KEY_VALUE_STORE_READS": {
394 "type": "integer",
395 "example": 0
396 },
397 "KEY_VALUE_STORE_WRITES": {
398 "type": "number",
399 "example": 0.00005
400 },
401 "KEY_VALUE_STORE_LISTS": {
402 "type": "integer",
403 "example": 0
404 },
405 "REQUEST_QUEUE_READS": {
406 "type": "integer",
407 "example": 0
408 },
409 "REQUEST_QUEUE_WRITES": {
410 "type": "integer",
411 "example": 0
412 },
413 "DATA_TRANSFER_INTERNAL_GBYTES": {
414 "type": "integer",
415 "example": 0
416 },
417 "DATA_TRANSFER_EXTERNAL_GBYTES": {
418 "type": "integer",
419 "example": 0
420 },
421 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
422 "type": "integer",
423 "example": 0
424 },
425 "PROXY_SERPS": {
426 "type": "integer",
427 "example": 0
428 }
429 }
430 }
431 }
432 }
433 }
434 }
435 }
436 }
437}Website Media Link Scraper 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 Media Link Scraper 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
thenetajiMaintained by Community
Actor Metrics
2 monthly users
-
1 bookmark
>99% runs succeeded
Created in Mar 2025
Modified a day ago
Categories
