Tools
HTML To Text
Extract text from a given HTML page
A simple agent that returns the text of a given HTML page. First, we try to extract the text from the html with the readability tool. If we don't find it, extract the text from the html with the beautifulsoup library.
Playground
Your organization, project and token stay in this browser's local storage and are sent straight to the API — this page never sees them.
Billing
Fixed cost per item requested. Text is extracted from HTML you already have, inside Botify.
These usage SKUs can be charged on a call.
| SKU | Credits | Description |
|---|---|---|
| Tool call | 1 per request | Charged once per successful item. |
Schemas
item is what you send, config how the tool behaves,
and the response is what you get back.
Item
objecthtml_code
string
required
HTML code of the page to process
{
"html_code": "string"
}
Response
objecttext
string
required
Text extracted from the html
{
"text": "string"
}
Endpoints
http://agents.botify.com/{organization}/{project}/html_to_text/process
http://agents.botify.com/{organization}/{project}/html_to_text/batch_process
http://agents.botify.com/{organization}/{project}/html_to_text/async_process
http://agents.botify.com/{organization}/{project}/html_to_text/async_batch_process
See running a long job in the background for the polling flow.
cURL
curl -X POST "http://agents.botify.com/{organization}/{project}/html_to_text/process" \
-H "Authorization: Bearer $BOTIFY_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"item": {
"html_code": "<html_code>"
}
}'
Raw metadata
- GET /agents/html_to_text — this page as JSON.
- /agents/html_to_text/skill.md — Markdown for coding agents.