---
title: "Extract content from a web page."
method: POST
path: "/api/ai/v2/web-extract"
---

# Extract content from a web page.

`POST /api/ai/v2/web-extract`

## Request body

- object
  - `url_path` string, required — The URL of the web page to extract content from.
  - `headline` boolean — Flag indicating whether to extract headlines from the web page. (Optional)
  - `inline_code` boolean — Flag indicating whether to extract inline code snippets from the web page. (Optional)
  - `code_blocks` boolean — Flag indicating whether to extract code blocks from the web page. (Optional)
  - `references` boolean — Flag indicating whether to extract references from the web page. (Optional)
  - `tables` boolean — Flag indicating whether to extract tables from the web page. (Optional)

## Response `200`

OK

- WebExtractResponse
  - `id` string — The unique identifier associated with the extraction process.
  - `status` string — The status of the extraction process.
  - `timestamp` integer — The timestamp when the extraction request was processed.
  - `content` object
    - `text_content` string — The extracted text content from the web page.
    - `tags` object[] — The extracted tags from the web page.
      - `name` string — The name of the tag.
      - `value` string — The value associated with the tag.
      - `data` object — Additional data associated with the tag.
  - `processing_count` integer — The number of times the content has been processed to generate the final result.

## Other responses

- `400` — Bad Request
- `401` — Unauthorized - Invalid API Key or Organization Key
- `404` — Not Found
- `500` — Internal Server Error

---

[API](https://skmtc.net/worqhat/apis/worqhat-ai-api-endpoints.md) · [All operations](https://skmtc.net/worqhat/apis/worqhat-ai-api-endpoints/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/worqhat/worqhat-ai-api-endpoints/revisions/a1044e79bd85/schema)