Download HTML from URLs
Try for free
No credit card required
Go to Store
Download HTML from URLs
mtrunkat/url-list-download-html
Try for free
No credit card required
This actor takes a list of URLs and downloads HTML of each page.
You can access the Download HTML from URLs 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": "baMQc88RapiL0wcfv"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/mtrunkat~url-list-download-html/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-mtrunkat-url-list-download-html",
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 "$ref": "#/components/schemas/inputSchema"
27 }
28 }
29 }
30 },
31 "parameters": [
32 {
33 "name": "token",
34 "in": "query",
35 "required": true,
36 "schema": {
37 "type": "string"
38 },
39 "description": "Enter your Apify token here"
40 }
41 ],
42 "responses": {
43 "200": {
44 "description": "OK"
45 }
46 }
47 }
48 },
49 "/acts/mtrunkat~url-list-download-html/runs": {
50 "post": {
51 "operationId": "runs-sync-mtrunkat-url-list-download-html",
52 "x-openai-isConsequential": false,
53 "summary": "Executes an Actor and returns information about the initiated run in response.",
54 "tags": [
55 "Run Actor"
56 ],
57 "requestBody": {
58 "required": true,
59 "content": {
60 "application/json": {
61 "schema": {
62 "$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 "$ref": "#/components/schemas/runsResponseSchema"
85 }
86 }
87 }
88 }
89 }
90 }
91 },
92 "/acts/mtrunkat~url-list-download-html/run-sync": {
93 "post": {
94 "operationId": "run-sync-mtrunkat-url-list-download-html",
95 "x-openai-isConsequential": false,
96 "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
97 "tags": [
98 "Run Actor"
99 ],
100 "requestBody": {
101 "required": true,
102 "content": {
103 "application/json": {
104 "schema": {
105 "$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 "requestListSources",
135 "proxyConfiguration"
136 ],
137 "properties": {
138 "requestListSources": {
139 "title": "Start URLs",
140 "minItems": 1,
141 "type": "array",
142 "description": "URLs to start with",
143 "items": {
144 "type": "object",
145 "required": [
146 "url"
147 ],
148 "properties": {
149 "url": {
150 "type": "string",
151 "title": "URL of a web page",
152 "format": "uri"
153 }
154 }
155 }
156 },
157 "proxyConfiguration": {
158 "title": "Proxy configuration",
159 "type": "object",
160 "description": "Choose to use no proxy, Apify Proxy, or provide custom proxy URLs.",
161 "default": {}
162 },
163 "handlePageTimeoutSecs": {
164 "title": "Page timeout",
165 "minimum": 1,
166 "maximum": 360,
167 "type": "integer",
168 "description": "Maximum time the scraper will spend processing one page.",
169 "default": 60
170 },
171 "maxRequestRetries": {
172 "title": "Maximum request retries",
173 "type": "integer",
174 "description": "How many retries before giving up.",
175 "default": 1
176 },
177 "useChrome": {
178 "title": "Use Chrome",
179 "type": "boolean",
180 "description": "The scraper will use a real Chrome browser instead of a Chromium masking as Chrome. Using this option may help with bypassing certain anti-scraping protections, but risks that the scraper will be unstable or not work at all.",
181 "default": false
182 }
183 }
184 },
185 "runsResponseSchema": {
186 "type": "object",
187 "properties": {
188 "data": {
189 "type": "object",
190 "properties": {
191 "id": {
192 "type": "string"
193 },
194 "actId": {
195 "type": "string"
196 },
197 "userId": {
198 "type": "string"
199 },
200 "startedAt": {
201 "type": "string",
202 "format": "date-time",
203 "example": "2025-01-08T00:00:00.000Z"
204 },
205 "finishedAt": {
206 "type": "string",
207 "format": "date-time",
208 "example": "2025-01-08T00:00:00.000Z"
209 },
210 "status": {
211 "type": "string",
212 "example": "READY"
213 },
214 "meta": {
215 "type": "object",
216 "properties": {
217 "origin": {
218 "type": "string",
219 "example": "API"
220 },
221 "userAgent": {
222 "type": "string"
223 }
224 }
225 },
226 "stats": {
227 "type": "object",
228 "properties": {
229 "inputBodyLen": {
230 "type": "integer",
231 "example": 2000
232 },
233 "rebootCount": {
234 "type": "integer",
235 "example": 0
236 },
237 "restartCount": {
238 "type": "integer",
239 "example": 0
240 },
241 "resurrectCount": {
242 "type": "integer",
243 "example": 0
244 },
245 "computeUnits": {
246 "type": "integer",
247 "example": 0
248 }
249 }
250 },
251 "options": {
252 "type": "object",
253 "properties": {
254 "build": {
255 "type": "string",
256 "example": "latest"
257 },
258 "timeoutSecs": {
259 "type": "integer",
260 "example": 300
261 },
262 "memoryMbytes": {
263 "type": "integer",
264 "example": 1024
265 },
266 "diskMbytes": {
267 "type": "integer",
268 "example": 2048
269 }
270 }
271 },
272 "buildId": {
273 "type": "string"
274 },
275 "defaultKeyValueStoreId": {
276 "type": "string"
277 },
278 "defaultDatasetId": {
279 "type": "string"
280 },
281 "defaultRequestQueueId": {
282 "type": "string"
283 },
284 "buildNumber": {
285 "type": "string",
286 "example": "1.0.0"
287 },
288 "containerUrl": {
289 "type": "string"
290 },
291 "usage": {
292 "type": "object",
293 "properties": {
294 "ACTOR_COMPUTE_UNITS": {
295 "type": "integer",
296 "example": 0
297 },
298 "DATASET_READS": {
299 "type": "integer",
300 "example": 0
301 },
302 "DATASET_WRITES": {
303 "type": "integer",
304 "example": 0
305 },
306 "KEY_VALUE_STORE_READS": {
307 "type": "integer",
308 "example": 0
309 },
310 "KEY_VALUE_STORE_WRITES": {
311 "type": "integer",
312 "example": 1
313 },
314 "KEY_VALUE_STORE_LISTS": {
315 "type": "integer",
316 "example": 0
317 },
318 "REQUEST_QUEUE_READS": {
319 "type": "integer",
320 "example": 0
321 },
322 "REQUEST_QUEUE_WRITES": {
323 "type": "integer",
324 "example": 0
325 },
326 "DATA_TRANSFER_INTERNAL_GBYTES": {
327 "type": "integer",
328 "example": 0
329 },
330 "DATA_TRANSFER_EXTERNAL_GBYTES": {
331 "type": "integer",
332 "example": 0
333 },
334 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
335 "type": "integer",
336 "example": 0
337 },
338 "PROXY_SERPS": {
339 "type": "integer",
340 "example": 0
341 }
342 }
343 },
344 "usageTotalUsd": {
345 "type": "number",
346 "example": 0.00005
347 },
348 "usageUsd": {
349 "type": "object",
350 "properties": {
351 "ACTOR_COMPUTE_UNITS": {
352 "type": "integer",
353 "example": 0
354 },
355 "DATASET_READS": {
356 "type": "integer",
357 "example": 0
358 },
359 "DATASET_WRITES": {
360 "type": "integer",
361 "example": 0
362 },
363 "KEY_VALUE_STORE_READS": {
364 "type": "integer",
365 "example": 0
366 },
367 "KEY_VALUE_STORE_WRITES": {
368 "type": "number",
369 "example": 0.00005
370 },
371 "KEY_VALUE_STORE_LISTS": {
372 "type": "integer",
373 "example": 0
374 },
375 "REQUEST_QUEUE_READS": {
376 "type": "integer",
377 "example": 0
378 },
379 "REQUEST_QUEUE_WRITES": {
380 "type": "integer",
381 "example": 0
382 },
383 "DATA_TRANSFER_INTERNAL_GBYTES": {
384 "type": "integer",
385 "example": 0
386 },
387 "DATA_TRANSFER_EXTERNAL_GBYTES": {
388 "type": "integer",
389 "example": 0
390 },
391 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
392 "type": "integer",
393 "example": 0
394 },
395 "PROXY_SERPS": {
396 "type": "integer",
397 "example": 0
398 }
399 }
400 }
401 }
402 }
403 }
404 }
405 }
406 }
407}Download HTML from URLs 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 Download HTML from URLs 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
88 monthly users
-
17 stars
>99% runs succeeded
Created in Feb 2018
Modified 10 months ago
Categories
