get_webpage_content
Extract webpage content in markdown format for analysis or processing. Specify URL, optional wait time, and country to retrieve clean text from web pages.
Instructions
Retrieve content of a webpage in markdown
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| country | No | Residential country to load the request from (e.g., US, CA, GB). Optional. | |
| url_to_scrape | Yes | The URL of the webpage to scrape. | |
| wait_before_scraping | No | Time to wait in milliseconds before starting the scrape. |
Input Schema (JSON Schema)
{
"properties": {
"country": {
"description": "Residential country to load the request from (e.g., US, CA, GB). Optional.",
"type": "string"
},
"url_to_scrape": {
"description": "The URL of the webpage to scrape.",
"format": "uri",
"type": "string"
},
"wait_before_scraping": {
"default": 0,
"description": "Time to wait in milliseconds before starting the scrape.",
"minimum": 0,
"type": "integer"
}
},
"required": [
"url_to_scrape"
],
"type": "object"
}