Get Page Text Node

G

Automation/Browser/Extract

Reads the rendered text of the page, or of one scoped element, and a Markdown version of the same content for prompts and summaries. Hidden elements are excluded from the text; scripts, styles and embedded media are dropped from the Markdown.

browser_get_page_textautomationLocal only

Inputs5

Outputs5

Security exposure6/10

Packageautomation

Ratings

Scores range from 0 to 10. Higher values mean more impact, exposure, or operational weight.

SecurityAttack surface and exposure impact.

6/10Medium

PrivacyPotential sensitivity of processed data.

4/10Medium

PerformanceRuntime or resource pressure.

7/10High

GovernancePolicy, audit, or compliance impact.

6/10Medium

ReliabilityOperational stability considerations.

8/10High

CostExternal or compute cost impact.

10/10High

Input Pins

5

▶

Execution

exec_in

Trigger

Session

Struct

session

Automation session

SchemaAutomationSessionAutomationSessionAutomationSession11 fields

session_refstringrequired

platformPlatformrequired

enum "Windows", "MacOS", "Linux"

default_delay_msinteger:uint64required

format uint64min 0

click_delay_msinteger:uint64required

format uint64min 0

debug_modebooleanrequired

browser_typeanyOf (2)

Browser context info if browser is attached

variant 1BrowserTypevariant

enum "Chrome", "Firefox", "Edge", "Safari"

variant 2nullvariant

browser_headlessboolean | null

browser_user_data_dirstring | null

current_page_refstring | null

Current page info if a page is open

current_window_handlestring | null

browser_frame_selectorsArray<Selector>

default []

itemsSelectorarray item

kindSelectorKindrequired

variant 1enumvariant

enum "Css", "Xpath", "TextExact", "TestId"...

variant 2constvariant

Visible text contained in the element; script, style and head content is ignored.

const "Text"

variant 3constvariant

ARIA role, optionally filtered by accessible name: `button`, `button|Sign in` (case-insensitive substring), `button|=Sign in` (exact) or `button|/^sign/i` (regex).

const "Role"

variant 4constvariant

Element ref from the latest Browser Snapshot, such as `e12`.

const "Ref"

valuestringrequired

confidencenumber | null

format double

scopestring | null

Scope

String

scope

CSS selector of the element to read; empty reads the whole page body

Locator

Struct

locator

Typed selector, including its kind and optional CSS scope. Overrides the legacy CSS selector when connected.

SchemaSelectorSelectorSelector4 fields

kindSelectorKindrequired

variant 1enumvariant

enum "Css", "Xpath", "TextExact", "TestId"...

variant 2constvariant

Visible text contained in the element; script, style and head content is ignored.

const "Text"

variant 3constvariant

ARIA role, optionally filtered by accessible name: `button`, `button|Sign in` (case-insensitive substring), `button|=Sign in` (exact) or `button|/^sign/i` (regex).

const "Role"

variant 4constvariant

Element ref from the latest Browser Snapshot, such as `e12`.

const "Ref"

valuestringrequired

confidencenumber | null

format double

scopestring | null

Max Characters

Integer

max_chars

Maximum characters returned in Text and in Markdown; 0 returns everything

Default 50000

Output Pins

5

▶

Execution

exec_out

Continue

Session

Struct

session_out

Updated automation session

SchemaAutomationSessionAutomationSessionAutomationSession11 fields

session_refstringrequired

platformPlatformrequired

enum "Windows", "MacOS", "Linux"

default_delay_msinteger:uint64required

format uint64min 0

click_delay_msinteger:uint64required

format uint64min 0

debug_modebooleanrequired

browser_typeanyOf (2)

Browser context info if browser is attached

variant 1BrowserTypevariant

enum "Chrome", "Firefox", "Edge", "Safari"

variant 2nullvariant

browser_headlessboolean | null

browser_user_data_dirstring | null

current_page_refstring | null

Current page info if a page is open

current_window_handlestring | null

browser_frame_selectorsArray<Selector>

default []

itemsSelectorarray item

kindSelectorKindrequired

variant 1enumvariant

enum "Css", "Xpath", "TextExact", "TestId"...

variant 2constvariant

Visible text contained in the element; script, style and head content is ignored.

const "Text"

variant 3constvariant

ARIA role, optionally filtered by accessible name: `button`, `button|Sign in` (case-insensitive substring), `button|=Sign in` (exact) or `button|/^sign/i` (regex).

const "Role"

variant 4constvariant

Element ref from the latest Browser Snapshot, such as `e12`.

const "Ref"

valuestringrequired

confidencenumber | null

format double

scopestring | null

Text

String

text

Rendered text (innerText) with the page's line breaks

Markdown

String

markdown

Markdown converted from the same content, keeping headings, links, lists and tables

Truncated

Boolean

truncated

True when Text or Markdown was cut to Max Characters

Node Info

Internal name

browser_get_page_text

Category

Automation/Browser/Extract

Version

1