# Jina Search

Blocks for extracting website content and performing web searches using Jina AI.

## Extract Website Content

### What it is

This block scrapes the content from the given web URL.

### How it works

The block sends a request to the given URL, downloads the HTML content, and uses content extraction algorithms to identify and extract the main text content of the page.

### Inputs

| Input        | Description                                                                           | Type | Required |
| ------------ | ------------------------------------------------------------------------------------- | ---- | -------- |
| url          | The URL to scrape the content from                                                    | str  | Yes      |
| raw\_content | Whether to do a raw scrape of the content or use Jina-ai Reader to scrape the content | bool | No       |

### Outputs

| Output  | Description                                      | Type |
| ------- | ------------------------------------------------ | ---- |
| error   | Error message if the content cannot be retrieved | str  |
| content | The scraped content from the given URL           | str  |

### Possible use case

A data analyst could use this block to automatically extract article content from news websites for sentiment analysis or topic modeling.

***

## Search The Web

### What it is

This block searches the internet for the given search query.

### How it works

The block sends the search query to a search engine API, processes the results, and returns them in a structured format.

### Inputs

| Input | Description                            | Type | Required |
| ----- | -------------------------------------- | ---- | -------- |
| query | The search query to search the web for | str  | Yes      |

### Outputs

| Output  | Description                                          | Type |
| ------- | ---------------------------------------------------- | ---- |
| error   | Error message if the operation failed                | str  |
| results | The search results including content from top 5 URLs | str  |

### Possible use case

A content creator could use this block to research trending topics in their field, gathering ideas for new articles or videos.

***


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://agpt.co/docs/integrations/block-integrations/search-2.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.