WebScraper
WebScraper · GPT アクション
Get Webpage
Provides browser automation services such as content retrieval, web scraping, and screenshot capturing.
POST /contentGetWebpageContentRetrieve the content of a webpage.
POST /scrapeScrapeWebpageScrape elements from a webpage with cookie and wait support.
POST /pdfGeneratePDFGenerate a PDF from a webpage.
POST /screenshotTakeWebpageScreenshotCapture a screenshot of a webpage.
元の API スキーマ
{
"openapi": "3.1.0",
"info": {
"title": "Get Webpage",
"description": "Provides browser automation services such as content retrieval, web scraping, and screenshot capturing.",
"version": "v1.0.0"
},
"servers": [
{
"url": "https://scraper.xukecheng.tech"
}
],
"paths": {
"/content": {
"post": {
"description": "Retrieve the content of a webpage.",
"operationId": "GetWebpageContent",
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The URL of the webpage to retrieve content from."
},
"download": {
"type": "boolean",
"description": "If true, prepares scraped data for download. Default is false.",
"default": false
}
},
"required": [
"url"
]
}
}
}
}
}
},
"/scrape": {
"post": {
"description": "Scrape elements from a webpage with cookie and wait support.",
"operationId": "ScrapeWebpage",
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The URL of the webpage to scrape."
},
"elements": {
"type": "array",
"items": {
"type": "object",
"properties": {
"selector": {
"type": "string",
"description": "CSS selector of the element to scrape."
}
}
},
"description": "Array of elements to scrape."
},
"cookies": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Name of the cookie."
},
"value": {
"type": "string",
"description": "Value of the cookie."
},
"url": {
"type": "string",
"description": "URL scope for the cookie."
},
"path": {
"type": "string",
"description": "Path scope for the cookie."
},
"sameSite": {
"type": "string",
"enum": [
"Strict",
"Lax",
"None"
],
"description": "SameSite attribute of the cookie."
}
},
"required": [
"name",
"value"
]
},
"description": "Array of cookies to be used in the scraping process."
},
"waitFor": {
"oneOf": [
{
"type": "string",
"description": "JavaScript function as a string or a CSS selector to wait for."
},
{
"type": "integer",
"description": "Number of milliseconds to wait."
}
],
"description": "Condition to wait for before starting the scrape. Can be a JavaScript function, a CSS selector, or a time in milliseconds."
},
"download": {
"type": "boolean",
"description": "If true, prepares scraped data for download. Default is false.",
"default": false
}
},
"required": [
"url",
"elements"
]
}
}
}
}
}
},
"/pdf": {
"post": {
"description": "Generate a PDF from a webpage.",
"operationId": "GeneratePDF",
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The URL of the webpage to convert into a PDF."
},
"gotoOptions": {
"type": "object",
"properties": {
"waitUntil": {
"type": "string",
"description": "When to consider navigation succeeded, e.g., 'load', 'domcontentloaded', 'networkidle0', 'networkidle2'."
}
},
"description": "Options for navigating to the URL."
},
"options": {
"type": "object",
"properties": {
"displayHeaderFooter": {
"type": "boolean",
"description": "Display header and footer in the PDF."
},
"printBackground": {
"type": "boolean",
"description": "Print background graphics."
},
"format": {
"type": "string",
"enum": [
"Letter",
"Legal",
"Tabloid",
"Ledger",
"A0",
"A1",
"A2",
"A3",
"A4",
"A5",
"A6"
],
"description": "Paper format. If set, takes priority over width or height options."
}
},
"description": "PDF generation options."
}
},
"required": [
"url"
]
}
}
}
}
}
},
"/screenshot": {
"post": {
"description": "Capture a screenshot of a webpage.",
"operationId": "TakeWebpageScreenshot",
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The URL of the webpage to capture."
},
"options": {
"type": "object",
"properties": {
"fullPage": {
"type": "boolean",
"description": "Capture the full page."
},
"type": {
"type": "string",
"description": "The image type (e.g., jpeg, png)."
}
},
"description": "Options for capturing the screenshot."
}
},
"required": [
"url"
]
}
}
}
}
}
}
},
"components": {
"schemas": {}
}
}