> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/browser-use/browser-use/llms.txt
> Use this file to discover all available pages before exploring further.

# Extraction Actions

> Actions for extracting data and taking screenshots from web pages

Extraction actions retrieve information from web pages using LLM-powered extraction or visual snapshots.

## extract

Use an LLM to extract structured or free-text data from the current page's markdown content.

<ParamField path="query" type="string" required>
  Description of what data to extract from the page
</ParamField>

<ParamField path="extract_links" type="bool" default="False">
  Set to `True` if the query requires URLs/links, `False` to save tokens
</ParamField>

<ParamField path="start_from_char" type="int" default="0">
  Character position to start extraction from. Use this for long pages when previous extraction was truncated.

  **Note:** This is a character offset in the markdown content, NOT an element index from browser\_state.
</ParamField>

<ParamField path="output_schema" type="dict">
  Optional JSON Schema dictionary. When provided, extraction returns validated JSON matching this schema instead of free-text.

  See [Structured Output Example](https://github.com/browser-use/browser-use/blob/main/examples/features/custom_output.py)
</ParamField>

### Free-text Extraction Example

```python theme={null}
from browser_use import Agent, Browser, ChatBrowserUse

agent = Agent(
    task="Go to quotes.toscrape.com and extract the first 3 quotes with their authors",
    llm=ChatBrowserUse(),
    browser=Browser()
)

history = await agent.run()
print(history.final_result())
```

### Structured Extraction Example

```python theme={null}
from browser_use import Agent, Browser, ChatBrowserUse
from pydantic import BaseModel

class Quote(BaseModel):
    text: str
    author: str

class QuotesOutput(BaseModel):
    quotes: list[Quote]

agent = Agent(
    task="Extract the first 5 quotes from quotes.toscrape.com",
    llm=ChatBrowserUse(),
    browser=Browser(),
    output_model_schema=QuotesOutput
)

history = await agent.run()
structured_data = history.structured_output
print(structured_data.quotes)
```

<Note>
  **When to use extract:**

  * You're on the right page
  * You know what data to extract
  * You haven't called extract before on the same page for the same query

  **Limitations:**

  * Cannot extract interactive elements (use browser\_state for that)
  * Large content may be truncated (use `start_from_char` to continue)
</Note>

<Warning>
  The extracted content is converted to markdown before extraction, which filters out advertising and noise but removes some interactive elements.
</Warning>

**Implementation:** `browser_use.tools.service:951`

***

## screenshot

Take a screenshot of the current viewport.

<ParamField path="file_name" type="string">
  Optional filename to save the screenshot. If provided, saves to file and returns the path.

  If omitted, the screenshot will be included in the next browser\_state observation.

  **Supported format:** PNG (`.png` extension added automatically)
</ParamField>

### Save to File Example

```python theme={null}
from browser_use import Agent, Browser, ChatBrowserUse

agent = Agent(
    task="Go to example.com and save a screenshot as 'homepage.png'",
    llm=ChatBrowserUse(),
    browser=Browser()
)

await agent.run()
```

### Include in Observation Example

```python theme={null}
from browser_use import Agent, Browser, ChatBrowserUse

agent = Agent(
    task="Go to example.com and take a screenshot to verify the page loaded",
    llm=ChatBrowserUse(),
    browser=Browser()
)

await agent.run()
```

<Tip>
  Screenshots are useful for:

  * Visual confirmation of page state
  * Debugging issues
  * Creating documentation
  * Verifying forms filled correctly
</Tip>

**Implementation:** `browser_use.tools.service:1387`

***

## search\_page

Search page text for a pattern instantly with zero LLM cost (like grep).

<ParamField path="pattern" type="string" required>
  Text or regex pattern to search for in page content
</ParamField>

<ParamField path="regex" type="bool" default="False">
  Treat pattern as regex (default: literal text match)
</ParamField>

<ParamField path="case_sensitive" type="bool" default="False">
  Case-sensitive search (default: case-insensitive)
</ParamField>

<ParamField path="context_chars" type="int" default="150">
  Characters of surrounding context per match
</ParamField>

<ParamField path="css_scope" type="string">
  CSS selector to limit search scope (e.g., `"div#main"`)
</ParamField>

<ParamField path="max_results" type="int" default="25">
  Maximum matches to return
</ParamField>

### Example

```python theme={null}
from browser_use import Agent, Browser, ChatBrowserUse

agent = Agent(
    task='Go to wikipedia.org and search for "quantum" on the page',
    llm=ChatBrowserUse(),
    browser=Browser()
)

await agent.run()
```

<Note>
  **Zero LLM cost** - This action executes JavaScript directly in the browser for instant results.
</Note>

**Implementation:** `browser_use.tools.service:1169`

***

## find\_elements

Query DOM elements by CSS selector instantly with zero LLM cost.

<ParamField path="selector" type="string" required>
  CSS selector to query elements (e.g., `"table tr"`, `"a.link"`, `"div.product"`)
</ParamField>

<ParamField path="attributes" type="list[string]">
  Specific attributes to extract (e.g., `["href", "src", "class"]`).

  If not set, returns tag and text only.
</ParamField>

<ParamField path="max_results" type="int" default="50">
  Maximum elements to return
</ParamField>

<ParamField path="include_text" type="bool" default="True">
  Include text content of each element
</ParamField>

### Example

```python theme={null}
from browser_use import Agent, Browser, ChatBrowserUse

agent = Agent(
    task='Go to example.com and find all links with their href attributes',
    llm=ChatBrowserUse(),
    browser=Browser()
)

await agent.run()
```

<Tip>
  Use `find_elements` to:

  * Explore page structure
  * Count items
  * Get links/attributes
  * Verify elements exist
</Tip>

**Implementation:** `browser_use.tools.service:1206`

***

## Related Actions

* [Navigation Actions](/api/actions/navigation) - Navigate between pages
* [Interaction Actions](/api/actions/interaction) - Interact with elements