Pay $10.00 for 1,000 scrapes

Web Scraping API - Scrape Any Website

zeeb0t/web-scraping-api---scrape-any-website

Pay $10.00 for 1,000 scrapes

Easily capture data from any website with a single API. Forget xPath, manual updates, and broken scrapers—our web scraping API handles it all.

You can access the Web Scraping API - Scrape Any Website 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": "2.0",
5    "x-build-id": "u6X85JpXjxVcMgtgX"
6  },
7  "servers": [
8    {
9      "url": "https://api.apify.com/v2"
10    }
11  ],
12  "paths": {
13    "/acts/zeeb0t~web-scraping-api---scrape-any-website/run-sync-get-dataset-items": {
14      "post": {
15        "operationId": "run-sync-get-dataset-items-zeeb0t-web-scraping-api---scrape-any-website",
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                "$ref": "#/components/schemas/inputSchema"
27              }
28            }
29          }
30        },
31        "parameters": [
32          {
33            "name": "token",
34            "in": "query",
35            "required": true,
36            "schema": {
37              "type": "string"
38            },
39            "description": "Enter your Apify token here"
40          }
41        ],
42        "responses": {
43          "200": {
44            "description": "OK"
45          }
46        }
47      }
48    },
49    "/acts/zeeb0t~web-scraping-api---scrape-any-website/runs": {
50      "post": {
51        "operationId": "runs-sync-zeeb0t-web-scraping-api---scrape-any-website",
52        "x-openai-isConsequential": false,
53        "summary": "Executes an Actor and returns information about the initiated run in response.",
54        "tags": [
55          "Run Actor"
56        ],
57        "requestBody": {
58          "required": true,
59          "content": {
60            "application/json": {
61              "schema": {
62                "$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                  "$ref": "#/components/schemas/runsResponseSchema"
85                }
86              }
87            }
88          }
89        }
90      }
91    },
92    "/acts/zeeb0t~web-scraping-api---scrape-any-website/run-sync": {
93      "post": {
94        "operationId": "run-sync-zeeb0t-web-scraping-api---scrape-any-website",
95        "x-openai-isConsequential": false,
96        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
97        "tags": [
98          "Run Actor"
99        ],
100        "requestBody": {
101          "required": true,
102          "content": {
103            "application/json": {
104              "schema": {
105                "$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          "url",
135          "method",
136          "output"
137        ],
138        "properties": {
139          "url": {
140            "title": "URL of the page",
141            "type": "string",
142            "description": "The URL of web page you want to turn into an API."
143          },
144          "method": {
145            "title": "API Method Name",
146            "type": "string",
147            "description": "A user-defined name for the API action. This can be any name that guides the AI in interpreting the task. Be creative and descriptive to ensure the AI understands your needs."
148          },
149          "output": {
150            "title": "API Output Structure (JSON)",
151            "type": "string",
152            "description": "The expected structure of the API’s response, defined by the user. You can specify explicit requirements or let the AI infer the details. Utilize this to generate outputs that are explicit, inferred, analytic, and more."
153          },
154          "proxy_country": {
155            "title": "Proxy Country",
156            "type": "string",
157            "description": "Specifies the country code for using a premium web proxy, only when a specific country is needed to bypass restrictions. The system defaults to ‘us’ if not provided."
158          }
159        }
160      },
161      "runsResponseSchema": {
162        "type": "object",
163        "properties": {
164          "data": {
165            "type": "object",
166            "properties": {
167              "id": {
168                "type": "string"
169              },
170              "actId": {
171                "type": "string"
172              },
173              "userId": {
174                "type": "string"
175              },
176              "startedAt": {
177                "type": "string",
178                "format": "date-time",
179                "example": "2025-01-08T00:00:00.000Z"
180              },
181              "finishedAt": {
182                "type": "string",
183                "format": "date-time",
184                "example": "2025-01-08T00:00:00.000Z"
185              },
186              "status": {
187                "type": "string",
188                "example": "READY"
189              },
190              "meta": {
191                "type": "object",
192                "properties": {
193                  "origin": {
194                    "type": "string",
195                    "example": "API"
196                  },
197                  "userAgent": {
198                    "type": "string"
199                  }
200                }
201              },
202              "stats": {
203                "type": "object",
204                "properties": {
205                  "inputBodyLen": {
206                    "type": "integer",
207                    "example": 2000
208                  },
209                  "rebootCount": {
210                    "type": "integer",
211                    "example": 0
212                  },
213                  "restartCount": {
214                    "type": "integer",
215                    "example": 0
216                  },
217                  "resurrectCount": {
218                    "type": "integer",
219                    "example": 0
220                  },
221                  "computeUnits": {
222                    "type": "integer",
223                    "example": 0
224                  }
225                }
226              },
227              "options": {
228                "type": "object",
229                "properties": {
230                  "build": {
231                    "type": "string",
232                    "example": "latest"
233                  },
234                  "timeoutSecs": {
235                    "type": "integer",
236                    "example": 300
237                  },
238                  "memoryMbytes": {
239                    "type": "integer",
240                    "example": 1024
241                  },
242                  "diskMbytes": {
243                    "type": "integer",
244                    "example": 2048
245                  }
246                }
247              },
248              "buildId": {
249                "type": "string"
250              },
251              "defaultKeyValueStoreId": {
252                "type": "string"
253              },
254              "defaultDatasetId": {
255                "type": "string"
256              },
257              "defaultRequestQueueId": {
258                "type": "string"
259              },
260              "buildNumber": {
261                "type": "string",
262                "example": "1.0.0"
263              },
264              "containerUrl": {
265                "type": "string"
266              },
267              "usage": {
268                "type": "object",
269                "properties": {
270                  "ACTOR_COMPUTE_UNITS": {
271                    "type": "integer",
272                    "example": 0
273                  },
274                  "DATASET_READS": {
275                    "type": "integer",
276                    "example": 0
277                  },
278                  "DATASET_WRITES": {
279                    "type": "integer",
280                    "example": 0
281                  },
282                  "KEY_VALUE_STORE_READS": {
283                    "type": "integer",
284                    "example": 0
285                  },
286                  "KEY_VALUE_STORE_WRITES": {
287                    "type": "integer",
288                    "example": 1
289                  },
290                  "KEY_VALUE_STORE_LISTS": {
291                    "type": "integer",
292                    "example": 0
293                  },
294                  "REQUEST_QUEUE_READS": {
295                    "type": "integer",
296                    "example": 0
297                  },
298                  "REQUEST_QUEUE_WRITES": {
299                    "type": "integer",
300                    "example": 0
301                  },
302                  "DATA_TRANSFER_INTERNAL_GBYTES": {
303                    "type": "integer",
304                    "example": 0
305                  },
306                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
307                    "type": "integer",
308                    "example": 0
309                  },
310                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
311                    "type": "integer",
312                    "example": 0
313                  },
314                  "PROXY_SERPS": {
315                    "type": "integer",
316                    "example": 0
317                  }
318                }
319              },
320              "usageTotalUsd": {
321                "type": "number",
322                "example": 0.00005
323              },
324              "usageUsd": {
325                "type": "object",
326                "properties": {
327                  "ACTOR_COMPUTE_UNITS": {
328                    "type": "integer",
329                    "example": 0
330                  },
331                  "DATASET_READS": {
332                    "type": "integer",
333                    "example": 0
334                  },
335                  "DATASET_WRITES": {
336                    "type": "integer",
337                    "example": 0
338                  },
339                  "KEY_VALUE_STORE_READS": {
340                    "type": "integer",
341                    "example": 0
342                  },
343                  "KEY_VALUE_STORE_WRITES": {
344                    "type": "number",
345                    "example": 0.00005
346                  },
347                  "KEY_VALUE_STORE_LISTS": {
348                    "type": "integer",
349                    "example": 0
350                  },
351                  "REQUEST_QUEUE_READS": {
352                    "type": "integer",
353                    "example": 0
354                  },
355                  "REQUEST_QUEUE_WRITES": {
356                    "type": "integer",
357                    "example": 0
358                  },
359                  "DATA_TRANSFER_INTERNAL_GBYTES": {
360                    "type": "integer",
361                    "example": 0
362                  },
363                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
364                    "type": "integer",
365                    "example": 0
366                  },
367                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
368                    "type": "integer",
369                    "example": 0
370                  },
371                  "PROXY_SERPS": {
372                    "type": "integer",
373                    "example": 0
374                  }
375                }
376              }
377            }
378          }
379        }
380      }
381    }
382  }
383}

Web Scraping API - Scrape Any Website 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 Web Scraping API - Scrape Any Website 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:

Web Scraping API - Scrape Any Website API in Python

Web Scraping API - Scrape Any Website API in JavaScript

Web Scraping API - Scrape Any Website API through CLI

Web Scraping API - Scrape Any Website API

Developer

Anthony Ziebell

Actor Metrics

43 monthly users
5 bookmarks
>99% runs succeeded
Created in Aug 2024
Modified 3 months ago

Categories

Puppeteer Scraper

apify/puppeteer-scraper

Crawls websites with the headless Chrome and Puppeteer library using a provided server-side Node.js code. This crawler is an alternative to apify/web-scraper that gives you finer control over the process. Supports both recursive crawling and list of URLs. Supports login to website.

Apify

5.4k

YouTube Video Subtitles (captions) Scraper

genial_candlestand/youtube-subtitles-scraper

Extract subtitles (captions) from one or multiple YouTube videos. Download YouTube video subtitles (captions) as a HTML, JSON, CSV, Excel, or XML doc.

Flowo

376

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

37.1k

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

28.1k

323

Amazon Scraper

junglee/free-amazon-product-scraper

Gets you product data from Amazon. Unofficial API. Scrapes and downloads product information without using the Amazon API, including reviews, prices, descriptions, and ASIN.

Junglee

Fast YouTube Channel Scraper

streamers/youtube-channel-scraper

This alternative YouTube Data API has no limits or quotas. Use it to scrape one or multiple YouTube channels: channel info, URL, total number of subscribers, videos and views, creation date. Try it and get basic video data. You can download extracted data in JSON, CSV, and Excel.

Streamers

3.4k

143

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

75.1k

Instagram Reel Scraper

apify/instagram-reel-scraper

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

Apify

9.1k

243

Yelp Scraper

tri_angle/yelp-scraper

Free Yelp web scraper to extract data from Yelp. Fast Yelp review scraper, but also gets business details and ratings without using the Yelp API.

Tri⟁angle

3.5k

Google Trends Scraper

emastra/google-trends-scraper

Scrape data from Google Trends by search terms or URLs. Specify locations, define time ranges, select categories to get interest by subregion and over time, related queries and topics, and more. Export scraped data, run the scraper via API, schedule and monitor runs, or integrate with other tools.