2 hours trial then $15.00/month - No credit card required now

Virtuals.io Scraper

memo23/apify-virtuals-cheerio

2 hours trial then $15.00/month - No credit card required now

Unlock unparalleled insights into Virtuals.io with our scraper! Easily extract data for both Sentient and Prototype agents, analyze tokenomics, and store data persistently for comprehensive research.

You can access the Virtuals.io 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": "0.0",
5    "x-build-id": "N8YR5F3AqBnR5zdms"
6  },
7  "servers": [
8    {
9      "url": "https://api.apify.com/v2"
10    }
11  ],
12  "paths": {
13    "/acts/memo23~apify-virtuals-cheerio/run-sync-get-dataset-items": {
14      "post": {
15        "operationId": "run-sync-get-dataset-items-memo23-apify-virtuals-cheerio",
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                "$ref": "#/components/schemas/inputSchema"
27              }
28            }
29          }
30        },
31        "parameters": [
32          {
33            "name": "token",
34            "in": "query",
35            "required": true,
36            "schema": {
37              "type": "string"
38            },
39            "description": "Enter your Apify token here"
40          }
41        ],
42        "responses": {
43          "200": {
44            "description": "OK"
45          }
46        }
47      }
48    },
49    "/acts/memo23~apify-virtuals-cheerio/runs": {
50      "post": {
51        "operationId": "runs-sync-memo23-apify-virtuals-cheerio",
52        "x-openai-isConsequential": false,
53        "summary": "Executes an Actor and returns information about the initiated run in response.",
54        "tags": [
55          "Run Actor"
56        ],
57        "requestBody": {
58          "required": true,
59          "content": {
60            "application/json": {
61              "schema": {
62                "$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                  "$ref": "#/components/schemas/runsResponseSchema"
85                }
86              }
87            }
88          }
89        }
90      }
91    },
92    "/acts/memo23~apify-virtuals-cheerio/run-sync": {
93      "post": {
94        "operationId": "run-sync-memo23-apify-virtuals-cheerio",
95        "x-openai-isConsequential": false,
96        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
97        "tags": [
98          "Run Actor"
99        ],
100        "requestBody": {
101          "required": true,
102          "content": {
103            "application/json": {
104              "schema": {
105                "$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          "agents"
135        ],
136        "properties": {
137          "agents": {
138            "title": "State",
139            "enum": [
140              "sentient",
141              "prototype"
142            ],
143            "type": "string",
144            "description": "Select your city[state]",
145            "default": "sentient"
146          },
147          "maxItems": {
148            "title": "Max number of items per crawl/scrape",
149            "type": "integer",
150            "description": "Maximum number of items that will be scraped.",
151            "default": 10000
152          },
153          "maxConcurrency": {
154            "title": "Max Concurrency",
155            "type": "integer",
156            "description": "Maximum number of pages that can be processed at the same time.",
157            "default": 10
158          },
159          "minConcurrency": {
160            "title": "Min Concurrency",
161            "type": "integer",
162            "description": "Minimum number of pages that will be processed at the same time.",
163            "default": 1
164          },
165          "maxRequestRetries": {
166            "title": "Max Request Retries",
167            "type": "integer",
168            "description": "Number of times the crawler will retry a failed request before giving up.",
169            "default": 100
170          },
171          "storeName": {
172            "title": "Name your storage for listings (deduplication and long-term retention), it can only contain letters 'a' through 'z', the digits '0' through '9', and the hyphen ('-') but only in the middle of the string (e.g. 'my-value-1')",
173            "pattern": "^[a-z0-9]+(-[a-z0-9]+)*$",
174            "type": "string",
175            "description": "Assign a custom name to the Key-Value Store where your scraped listings will be saved. This ensures:\n 1. **Data Deduplication**: Prevents duplicate entries in the storage. \n 2. **Persistent Storage**: Enables long-term retention of listings, beyond default storage limits.\n 3. **Project Management**: Separate datasets by using unique names for different projects or analyses.\n 4. **Data Reuse**: Easily reference and reuse stored data without overwriting.\n (If left blank, the default storage will be used with standard retention limits.)"
176          },
177          "proxy": {
178            "title": "Proxy configuration",
179            "type": "object",
180            "description": "Specifies proxy servers that will be used by the scraper in order to hide its origin.<br><br>For details, see <a href='https://apify.com/apify/web-scraper#proxy-configuration' target='_blank' rel='noopener'>Proxy configuration</a> in README.",
181            "default": {
182              "useApifyProxy": true,
183              "apifyProxyGroups": [
184                "RESIDENTIAL"
185              ]
186            }
187          }
188        }
189      },
190      "runsResponseSchema": {
191        "type": "object",
192        "properties": {
193          "data": {
194            "type": "object",
195            "properties": {
196              "id": {
197                "type": "string"
198              },
199              "actId": {
200                "type": "string"
201              },
202              "userId": {
203                "type": "string"
204              },
205              "startedAt": {
206                "type": "string",
207                "format": "date-time",
208                "example": "2025-01-08T00:00:00.000Z"
209              },
210              "finishedAt": {
211                "type": "string",
212                "format": "date-time",
213                "example": "2025-01-08T00:00:00.000Z"
214              },
215              "status": {
216                "type": "string",
217                "example": "READY"
218              },
219              "meta": {
220                "type": "object",
221                "properties": {
222                  "origin": {
223                    "type": "string",
224                    "example": "API"
225                  },
226                  "userAgent": {
227                    "type": "string"
228                  }
229                }
230              },
231              "stats": {
232                "type": "object",
233                "properties": {
234                  "inputBodyLen": {
235                    "type": "integer",
236                    "example": 2000
237                  },
238                  "rebootCount": {
239                    "type": "integer",
240                    "example": 0
241                  },
242                  "restartCount": {
243                    "type": "integer",
244                    "example": 0
245                  },
246                  "resurrectCount": {
247                    "type": "integer",
248                    "example": 0
249                  },
250                  "computeUnits": {
251                    "type": "integer",
252                    "example": 0
253                  }
254                }
255              },
256              "options": {
257                "type": "object",
258                "properties": {
259                  "build": {
260                    "type": "string",
261                    "example": "latest"
262                  },
263                  "timeoutSecs": {
264                    "type": "integer",
265                    "example": 300
266                  },
267                  "memoryMbytes": {
268                    "type": "integer",
269                    "example": 1024
270                  },
271                  "diskMbytes": {
272                    "type": "integer",
273                    "example": 2048
274                  }
275                }
276              },
277              "buildId": {
278                "type": "string"
279              },
280              "defaultKeyValueStoreId": {
281                "type": "string"
282              },
283              "defaultDatasetId": {
284                "type": "string"
285              },
286              "defaultRequestQueueId": {
287                "type": "string"
288              },
289              "buildNumber": {
290                "type": "string",
291                "example": "1.0.0"
292              },
293              "containerUrl": {
294                "type": "string"
295              },
296              "usage": {
297                "type": "object",
298                "properties": {
299                  "ACTOR_COMPUTE_UNITS": {
300                    "type": "integer",
301                    "example": 0
302                  },
303                  "DATASET_READS": {
304                    "type": "integer",
305                    "example": 0
306                  },
307                  "DATASET_WRITES": {
308                    "type": "integer",
309                    "example": 0
310                  },
311                  "KEY_VALUE_STORE_READS": {
312                    "type": "integer",
313                    "example": 0
314                  },
315                  "KEY_VALUE_STORE_WRITES": {
316                    "type": "integer",
317                    "example": 1
318                  },
319                  "KEY_VALUE_STORE_LISTS": {
320                    "type": "integer",
321                    "example": 0
322                  },
323                  "REQUEST_QUEUE_READS": {
324                    "type": "integer",
325                    "example": 0
326                  },
327                  "REQUEST_QUEUE_WRITES": {
328                    "type": "integer",
329                    "example": 0
330                  },
331                  "DATA_TRANSFER_INTERNAL_GBYTES": {
332                    "type": "integer",
333                    "example": 0
334                  },
335                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
336                    "type": "integer",
337                    "example": 0
338                  },
339                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
340                    "type": "integer",
341                    "example": 0
342                  },
343                  "PROXY_SERPS": {
344                    "type": "integer",
345                    "example": 0
346                  }
347                }
348              },
349              "usageTotalUsd": {
350                "type": "number",
351                "example": 0.00005
352              },
353              "usageUsd": {
354                "type": "object",
355                "properties": {
356                  "ACTOR_COMPUTE_UNITS": {
357                    "type": "integer",
358                    "example": 0
359                  },
360                  "DATASET_READS": {
361                    "type": "integer",
362                    "example": 0
363                  },
364                  "DATASET_WRITES": {
365                    "type": "integer",
366                    "example": 0
367                  },
368                  "KEY_VALUE_STORE_READS": {
369                    "type": "integer",
370                    "example": 0
371                  },
372                  "KEY_VALUE_STORE_WRITES": {
373                    "type": "number",
374                    "example": 0.00005
375                  },
376                  "KEY_VALUE_STORE_LISTS": {
377                    "type": "integer",
378                    "example": 0
379                  },
380                  "REQUEST_QUEUE_READS": {
381                    "type": "integer",
382                    "example": 0
383                  },
384                  "REQUEST_QUEUE_WRITES": {
385                    "type": "integer",
386                    "example": 0
387                  },
388                  "DATA_TRANSFER_INTERNAL_GBYTES": {
389                    "type": "integer",
390                    "example": 0
391                  },
392                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
393                    "type": "integer",
394                    "example": 0
395                  },
396                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
397                    "type": "integer",
398                    "example": 0
399                  },
400                  "PROXY_SERPS": {
401                    "type": "integer",
402                    "example": 0
403                  }
404                }
405              }
406            }
407          }
408        }
409      }
410    }
411  }
412}

Virtuals.io 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 Virtuals.io Scraper from the options below:

OpenAPI.json

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:

Virtuals.io Scraper API in Python

Virtuals.io Scraper API in JavaScript

Virtuals.io Scraper API through CLI

Virtuals.io Scraper API

Developer

Muhamed Didovic

Actor Metrics

2 monthly users
0 No bookmarks yet
>99% runs succeeded
Created in Jan 2025
Modified 2 days ago

Categories

Website Content Crawler

apify/website-content-crawler

Crawl websites and extract text content to feed AI models, LLM applications, vector databases, or RAG pipelines. The Actor supports rich formatting using Markdown, cleans the HTML, downloads files, and integrates well with 🦜🔗 LangChain, LlamaIndex, and the wider LLM ecosystem.

Apify

36.7k

📩📍 Google Maps Email Extractor

lukaskrivka/google-maps-with-contact-details

Extract Google Maps contact details. Scrape websites of Google Maps places for contact details and get email addresses, website, location, address, zipcode, phone number, social media links. Export scraped data, run the scraper via API, schedule and monitor runs or integrate with other tools.

Lukáš Křivka

15.8k

487

Instagram Scraper

apify/instagram-scraper

Scrape and download Instagram posts, profiles, places, hashtags, photos, and comments. Get data from Instagram using one or more Instagram URLs or search queries. Export scraped data, run the scraper via API, schedule and monitor runs or integrate with other tools.

Apify

74.3k

Facebook Posts Scraper

apify/facebook-posts-scraper

Extract data from hundreds of Facebook posts from one or multiple Facebook pages and profiles. Get post URL, post text, page or profile URL, timestamp, number of likes, shares, comments, and more. Download the data in JSON, CSV, and Excel and use it in apps, spreadsheets, and reports.

Apify

18.3k

284

Google Maps Extractor

compass/google-maps-extractor

Extract data from hundreds of places fast. Scrape Google Maps by keyword, category, location, URLs & other filters. Get addresses, contact info, opening hours, popular times, prices, menus & more. Export scraped data, run the scraper via API, schedule and monitor runs, or integrate with other tools.

Compass

29.6k

737

Contact Details Scraper

vdrmota/contact-info-scraper

Free email extractor and lead scraper to extract and download emails, phone numbers, Facebook, Twitter, LinkedIn, and Instagram profiles from any website. Extract contact information at scale from lists of URLs and download the data as Excel, CSV, JSON, HTML, and XML.

Vojta Drmota

28k

322

Cheerio Scraper

apify/cheerio-scraper

Crawls websites using raw HTTP requests, parses the HTML with the Cheerio library, and extracts data from the pages using a Node.js code. Supports both recursive crawling and lists of URLs. This actor is a high-performance alternative to apify/web-scraper for websites that do not require JavaScript.

Apify

6.4k

120

Instagram Post Scraper

apify/instagram-post-scraper

Scrape Instagram posts. Just add one or more Instagram usernames and get your data in seconds including text, hashtags, mentions, comments, images, URLs, likes, locations, and metadata. Export scraped data, run the scraper via API, schedule and monitor runs or integrate with other tools.

Apify

25.9k

268

Web Scraper

apify/web-scraper

Crawls arbitrary websites using the Chrome browser and extracts structured data from web pages using a provided JavaScript function. The Actor supports both recursive crawling and lists of URLs, and automatically manages concurrency for maximum performance.

Apify

76.2k

457

Instagram Profile Scraper

apify/instagram-profile-scraper

Scrape all Instagram profile info. Just add one or more Instagram usernames and extract number of followers&follows, URLs, bio, posts, likes, counts, related profiles, captions, highlight reels. Export scraped data, run the scraper via API, schedule and monitor runs or integrate with other tools.

Apify

43.1k

330