Extractor

LLM-Powered data extractor for one-time data extraction, unstructured data, and classic code-based scrapers.

`extract`

Extract structured data from a URL:

Endpoint: POST /v1/extractor/extract (alias: POST /v1/extract)

curl https://api.parsera.org/v1/extractor/extract \
--header 'Content-Type: application/json' \
--header 'X-API-KEY: <YOUR_API_KEY>' \
--data '{
    "url": "https://news.ycombinator.com/",
    "prompt": "Extract news metadata",
    "attributes": [
        {
            "name": "title",
            "description": "News title"
        },
        {
            "name": "points",
            "description": "Number of points"
        }
    ],
    "proxy_country": "Germany"
}'

Parameters:

Minimal payload requires url and either prompt or attributes.

Parameter	Type	Default	Description
`url`	`string`	-	URL of the webpage to extract data from
`prompt`	`string`	`""`	Prompt for initial scraping
`attributes`	`array`	`[]`	A list of attribute objects with `name` and `description` fields to extract from the webpage. Also, you can specify Output Types
`mode`	`string`	`standard`	Mode of the extractor: `standard` or `precision`
`proxy_country`	`string`	`UnitedStates`	Proxy country, see Proxy Countries
`cookies`	`array`	Empty	Cookies to use during extraction, see Cookies

It's recommended to set the proxy_country parameter to a specific country since a page could be unavailable from some locations.

If some data is missing, you can retry with precision mode. See Precision Mode for details.

`parse`

Parse data from HTML or text content you already have, instead of fetching from a URL:

Endpoint: POST /v1/extractor/parse (alias: POST /v1/parse)

curl https://api.parsera.org/v1/extractor/parse \
--header 'Content-Type: application/json' \
--header 'X-API-KEY: <YOUR_API_KEY>' \
--data '{
    "content": <HTML_OR_TEXT_HERE>,
    "prompt": "Extract news metadata",
    "attributes": [
        {
            "name": "title",
            "description": "News title"
        },
        {
            "name": "points",
            "description": "Number of points"
        }
    ]
}'

Parameters:

Parameter	Type	Default	Description
`content`	`string`	-	Raw HTML or text content to extract data from
`prompt`	`string`	`""`	Prompt for initial scraping
`attributes`	`array`	-	A list of attribute objects with `name` and `description` fields to extract from the webpage. Also, you can specify Output Types
`mode`	`string`	`standard`	Mode of the extractor: `standard` or `precision`

`extract_markdown`

Get clean markdown from a URL:

Endpoint: POST /v1/extractor/extract_markdown (alias: POST /v1/extract_markdown)

curl https://api.parsera.org/v1/extractor/extract_markdown \
--header 'Content-Type: application/json' \
--header 'X-API-KEY: <YOUR_API_KEY>' \
--data '{
    "url": "https://news.ycombinator.com/",
    "proxy_country": "UnitedStates"
}'

Parameters:

Parameter	Type	Default	Description
`url`	`string`	-	URL of the webpage to extract data from
`proxy_country`	`string`	`UnitedStates`	Proxy country, see Proxy Countries
`cookies`	`array`	Empty	Cookies to use during extraction, see Cookies

Manage Scrapers

The Extractor API also lets you create and manage classic code-based scrapers. See Manage Scrapers for the full CRUD reference (create, generate, get, delete).

More Features

Manage Scrapers — Create and manage classic scrapers
Code Mode — Code generation details and benefits
Precision Mode — Extract data hidden in HTML tags
Specify Output Types
Setting Proxy
Setting Cookies