mirror of
https://github.com/browser-use/browser-use
synced 2026-05-06 17:52:15 +02:00
c5a3c0cf2e
Replaces static page statistics with dynamic calculations for viewport and scroll position metrics. Simplifies code logic in scroll handling by removing unnecessary defaults for page scrolling. Improves readability and reliability of page scroll operations by requiring explicit num_pages parameter. Enhances page-view consistency and user interaction handling.
90 lines
2.1 KiB
Python
90 lines
2.1 KiB
Python
from dataclasses import dataclass, field
|
|
from typing import Any
|
|
|
|
from pydantic import BaseModel
|
|
|
|
from browser_use.dom.history_tree_processor.service import DOMHistoryElement
|
|
from browser_use.dom.views import DOMState
|
|
|
|
|
|
# Pydantic
|
|
class TabInfo(BaseModel):
|
|
"""Represents information about a browser tab"""
|
|
|
|
page_id: int
|
|
url: str
|
|
title: str
|
|
parent_page_id: int | None = None # parent page that contains this popup or cross-origin iframe
|
|
|
|
|
|
class PageInfo(BaseModel):
|
|
"""Comprehensive page size and scroll information"""
|
|
|
|
# Current viewport dimensions
|
|
viewport_width: int
|
|
viewport_height: int
|
|
|
|
# Total page dimensions
|
|
page_width: int
|
|
page_height: int
|
|
|
|
# Current scroll position
|
|
scroll_x: int
|
|
scroll_y: int
|
|
|
|
# Calculated scroll information
|
|
pixels_above: int
|
|
pixels_below: int
|
|
pixels_left: int
|
|
pixels_right: int
|
|
|
|
# Page statistics are now computed dynamically instead of stored
|
|
|
|
|
|
@dataclass
|
|
class BrowserStateSummary(DOMState):
|
|
"""The summary of the browser's current state designed for an LLM to process"""
|
|
|
|
# provided by DOMState:
|
|
# element_tree: DOMElementNode
|
|
# selector_map: SelectorMap
|
|
|
|
url: str
|
|
title: str
|
|
tabs: list[TabInfo]
|
|
screenshot: str | None = field(default=None, repr=False)
|
|
page_info: PageInfo | None = None # Enhanced page information
|
|
|
|
# Keep legacy fields for backward compatibility
|
|
pixels_above: int = 0
|
|
pixels_below: int = 0
|
|
browser_errors: list[str] = field(default_factory=list)
|
|
|
|
|
|
@dataclass
|
|
class BrowserStateHistory:
|
|
"""The summary of the browser's state at a past point in time to usse in LLM message history"""
|
|
|
|
url: str
|
|
title: str
|
|
tabs: list[TabInfo]
|
|
interacted_element: list[DOMHistoryElement | None] | list[None]
|
|
screenshot: str | None = None
|
|
|
|
def to_dict(self) -> dict[str, Any]:
|
|
data = {}
|
|
data['tabs'] = [tab.model_dump() for tab in self.tabs]
|
|
data['screenshot'] = self.screenshot
|
|
data['interacted_element'] = [el.to_dict() if el else None for el in self.interacted_element]
|
|
data['url'] = self.url
|
|
data['title'] = self.title
|
|
return data
|
|
|
|
|
|
class BrowserError(Exception):
|
|
"""Base class for all browser errors"""
|
|
|
|
|
|
class URLNotAllowedError(BrowserError):
|
|
"""Error raised when a URL is not allowed"""
|