/zyte | Type: Application | PCID required: Yes
Tools
| Tool | Description |
|---|---|
zyte_extract | Extract data from a webpage |
zyte_extract
Extract data from a webpage Parameters:| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
actions | object[] | No | — | Browser actions to perform before extraction (click, type, scroll, wait, etc.). |
article | boolean | No | — | Set to true to extract structured article data (headline, body text, author, date, etc.). |
articleList | boolean | No | — | Set to true to extract a list of articles from a feed or index page. |
articleListOptions | object | No | — | Options for article list extraction. |
articleNavigation | boolean | No | — | Set to true to extract navigation data from article pages. |
articleNavigationOptions | object | No | — | Options for article navigation extraction. |
articleOptions | object | No | — | Options for article extraction. |
browserHtml | boolean | No | — | Set to true to retrieve the browser-rendered HTML of the page. |
customHttpRequestHeaders | object[] | No | — | Custom HTTP headers to send with the request. |
device | string | No | — | Device type to emulate. |
echoData | object | No | — | Arbitrary data to echo back in the response. Useful for tracking requests. |
experimental | object | No | — | Experimental features configuration. |
followRedirect | boolean | No | — | Whether to follow HTTP redirects. Defaults to true. |
forumThread | boolean | No | — | Set to true to extract forum thread data (posts, authors, dates). |
forumThreadOptions | object | No | — | Options for forum thread extraction. |
geolocation | string | No | — | Two-letter ISO country code for geolocation targeting (e.g., ‘US’, ‘GB’, ‘DE’). |
httpRequestBody | string | No | — | Base64-encoded request body for binary data. |
httpRequestMethod | string | No | — | HTTP method to use for the request. Defaults to GET. |
httpRequestText | string | No | — | UTF-8 encoded request body for text data. |
httpResponseBody | boolean | No | — | Set to true to retrieve the HTTP response body as a Base64-encoded string. |
httpResponseHeaders | boolean | No | — | Set to true to retrieve the HTTP response headers. |
ipType | string | No | — | Type of IP address to use for the request. |
jobPosting | boolean | No | — | Set to true to extract structured job posting data (title, company, salary, description, etc.). |
jobPostingNavigation | boolean | No | — | Set to true to extract navigation data from job posting pages. |
jobPostingNavigationOptions | object | No | — | Options for job posting navigation extraction. |
jobPostingOptions | object | No | — | Options for job posting extraction. |
metadata | boolean | No | — | Set to true to include request metadata in the response. |
pageContent | boolean | No | — | Set to true to extract general page content using AI. |
pageContentOptions | object | No | — | Options for page content extraction. |
product | boolean | No | — | Set to true to extract structured product data (name, price, description, images, etc.). |
productList | boolean | No | — | Set to true to extract a list of products from a category or search results page. |
productListOptions | object | No | — | Options for product list extraction. |
productNavigation | boolean | No | — | Set to true to extract navigation data (pagination, subcategories) from product pages. |
productNavigationOptions | object | No | — | Options for product navigation extraction. |
productOptions | object | No | — | Options for product extraction. |
requestCookies | object[] | No | — | Cookies to send with the request. |
responseCookies | boolean | No | — | Set to true to include response cookies in the output. |
screenshot | boolean | No | — | Set to true to capture a screenshot of the page as a Base64-encoded PNG. |
screenshotOptions | object | No | — | Options for screenshot capture. |
serp | boolean | No | — | Set to true to extract Google Search Engine Results Page data. |
sessionContext | object[] | No | — | Session context from a previous request to maintain state across requests. |
sessionContextParameters | object | No | — | Parameters for session context handling. |
url | string | Yes | — | The target URL to extract data from. |
viewport | object | No | — | Browser viewport size for rendering. |
Show inputSchema
Show inputSchema
{
"type": "object",
"properties": {
"PCID": {
"type": "string",
"description": "Pink Connect ID for the authenticated connection"
},
"actions": {
"type": "array",
"items": {
"type": "object",
"properties": {
"action": {
"type": "string",
"enum": [
"click",
"type",
"scroll",
"scrollBottom",
"wait",
"waitForSelector",
"waitForTimeout",
"press",
"select",
"setSelect",
"screenshot",
"evaluate"
],
"description": "Action type."
},
"selector": {
"type": "string",
"description": "CSS selector for the target element."
},
"text": {
"type": "string",
"description": "Text to type (for type action)."
},
"timeout": {
"type": "number",
"description": "Timeout in milliseconds."
},
"key": {
"type": "string",
"description": "Key to press (for press action)."
},
"onError": {
"type": "string",
"enum": [
"return",
"ignore"
],
"description": "Error handling strategy."
}
},
"required": [
"action"
]
},
"description": "Browser actions to perform before extraction (click, type, scroll, wait, etc.)."
},
"article": {
"type": "boolean",
"description": "Set to true to extract structured article data (headline, body text, author, date, etc.)."
},
"articleList": {
"type": "boolean",
"description": "Set to true to extract a list of articles from a feed or index page."
},
"articleListOptions": {
"type": "object",
"description": "Options for article list extraction.",
"properties": {
"extractFrom": {
"type": "string",
"description": "Data source for extraction.",
"enum": [
"httpResponseBody",
"browserHtml",
"browserHtmlOnly"
]
}
}
},
"articleNavigation": {
"type": "boolean",
"description": "Set to true to extract navigation data from article pages."
},
"articleNavigationOptions": {
"type": "object",
"description": "Options for article navigation extraction.",
"properties": {
"extractFrom": {
"type": "string",
"description": "Data source for extraction.",
"enum": [
"httpResponseBody",
"browserHtml",
"browserHtmlOnly"
]
}
}
},
"articleOptions": {
"type": "object",
"description": "Options for article extraction.",
"properties": {
"extractFrom": {
"type": "string",
"description": "Data source for extraction.",
"enum": [
"httpResponseBody",
"browserHtml",
"browserHtmlOnly"
]
}
}
},
"browserHtml": {
"type": "boolean",
"description": "Set to true to retrieve the browser-rendered HTML of the page."
},
"customHttpRequestHeaders": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Header name."
},
"value": {
"type": "string",
"description": "Header value."
}
},
"required": [
"name",
"value"
]
},
"description": "Custom HTTP headers to send with the request."
},
"device": {
"type": "string",
"description": "Device type to emulate.",
"enum": [
"desktop",
"mobile"
]
},
"echoData": {
"description": "Arbitrary data to echo back in the response. Useful for tracking requests."
},
"experimental": {
"type": "object",
"description": "Experimental features configuration."
},
"followRedirect": {
"type": "boolean",
"description": "Whether to follow HTTP redirects. Defaults to true."
},
"forumThread": {
"type": "boolean",
"description": "Set to true to extract forum thread data (posts, authors, dates)."
},
"forumThreadOptions": {
"type": "object",
"description": "Options for forum thread extraction.",
"properties": {
"extractFrom": {
"type": "string",
"description": "Data source for extraction.",
"enum": [
"httpResponseBody",
"browserHtml",
"browserHtmlOnly"
]
}
}
},
"geolocation": {
"type": "string",
"description": "Two-letter ISO country code for geolocation targeting (e.g., 'US', 'GB', 'DE')."
},
"httpRequestBody": {
"type": "string",
"description": "Base64-encoded request body for binary data."
},
"httpRequestMethod": {
"type": "string",
"description": "HTTP method to use for the request. Defaults to GET.",
"enum": [
"GET",
"POST",
"PUT",
"PATCH",
"DELETE",
"HEAD",
"OPTIONS"
]
},
"httpRequestText": {
"type": "string",
"description": "UTF-8 encoded request body for text data."
},
"httpResponseBody": {
"type": "boolean",
"description": "Set to true to retrieve the HTTP response body as a Base64-encoded string."
},
"httpResponseHeaders": {
"type": "boolean",
"description": "Set to true to retrieve the HTTP response headers."
},
"ipType": {
"type": "string",
"description": "Type of IP address to use for the request.",
"enum": [
"datacenter",
"residential"
]
},
"jobPosting": {
"type": "boolean",
"description": "Set to true to extract structured job posting data (title, company, salary, description, etc.)."
},
"jobPostingNavigation": {
"type": "boolean",
"description": "Set to true to extract navigation data from job posting pages."
},
"jobPostingNavigationOptions": {
"type": "object",
"description": "Options for job posting navigation extraction.",
"properties": {
"extractFrom": {
"type": "string",
"description": "Data source for extraction.",
"enum": [
"httpResponseBody",
"browserHtml",
"browserHtmlOnly"
]
}
}
},
"jobPostingOptions": {
"type": "object",
"description": "Options for job posting extraction.",
"properties": {
"extractFrom": {
"type": "string",
"description": "Data source for extraction.",
"enum": [
"httpResponseBody",
"browserHtml",
"browserHtmlOnly"
]
}
}
},
"metadata": {
"type": "boolean",
"description": "Set to true to include request metadata in the response."
},
"pageContent": {
"type": "boolean",
"description": "Set to true to extract general page content using AI."
},
"pageContentOptions": {
"type": "object",
"description": "Options for page content extraction.",
"properties": {
"extractFrom": {
"type": "string",
"description": "Data source for extraction.",
"enum": [
"httpResponseBody",
"browserHtml",
"browserHtmlOnly"
]
}
}
},
"product": {
"type": "boolean",
"description": "Set to true to extract structured product data (name, price, description, images, etc.)."
},
"productList": {
"type": "boolean",
"description": "Set to true to extract a list of products from a category or search results page."
},
"productListOptions": {
"type": "object",
"description": "Options for product list extraction.",
"properties": {
"extractFrom": {
"type": "string",
"description": "Data source for extraction.",
"enum": [
"httpResponseBody",
"browserHtml",
"browserHtmlOnly"
]
}
}
},
"productNavigation": {
"type": "boolean",
"description": "Set to true to extract navigation data (pagination, subcategories) from product pages."
},
"productNavigationOptions": {
"type": "object",
"description": "Options for product navigation extraction.",
"properties": {
"extractFrom": {
"type": "string",
"description": "Data source for extraction.",
"enum": [
"httpResponseBody",
"browserHtml",
"browserHtmlOnly"
]
}
}
},
"productOptions": {
"type": "object",
"description": "Options for product extraction.",
"properties": {
"extractFrom": {
"type": "string",
"description": "Data source for extraction.",
"enum": [
"httpResponseBody",
"browserHtml",
"browserHtmlOnly"
]
}
}
},
"requestCookies": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Cookie name."
},
"value": {
"type": "string",
"description": "Cookie value."
},
"domain": {
"type": "string",
"description": "Cookie domain."
},
"path": {
"type": "string",
"description": "Cookie path."
}
},
"required": [
"name",
"value"
]
},
"description": "Cookies to send with the request."
},
"responseCookies": {
"type": "boolean",
"description": "Set to true to include response cookies in the output."
},
"screenshot": {
"type": "boolean",
"description": "Set to true to capture a screenshot of the page as a Base64-encoded PNG."
},
"screenshotOptions": {
"type": "object",
"description": "Options for screenshot capture.",
"properties": {
"fullPage": {
"type": "boolean",
"description": "Capture the full scrollable page instead of just the viewport."
}
}
},
"serp": {
"type": "boolean",
"description": "Set to true to extract Google Search Engine Results Page data."
},
"sessionContext": {
"type": "array",
"items": {
"type": "object"
},
"description": "Session context from a previous request to maintain state across requests."
},
"sessionContextParameters": {
"type": "object",
"description": "Parameters for session context handling.",
"properties": {
"actions": {
"type": "array",
"items": {
"type": "object"
},
"description": "Actions that were used to reach the current session state."
}
}
},
"url": {
"type": "string",
"description": "The target URL to extract data from."
},
"viewport": {
"type": "object",
"description": "Browser viewport size for rendering.",
"properties": {
"width": {
"type": "integer",
"description": "Viewport width in pixels."
},
"height": {
"type": "integer",
"description": "Viewport height in pixels."
}
}
}
},
"required": [
"PCID",
"url"
]
}