Extract BrowserState.scrape_website (#4184)

This commit is contained in:
Stanislav Novosad
2025-12-03 15:08:32 -07:00
committed by GitHub
parent ce01f2cb35
commit f754272f9c
16 changed files with 375 additions and 313 deletions

View File

@@ -126,7 +126,7 @@ from skyvern.webeye.actions.parse_actions import (
)
from skyvern.webeye.actions.responses import ActionResult, ActionSuccess
from skyvern.webeye.browser_state import BrowserState
from skyvern.webeye.scraper.scraper import ElementTreeFormat, ScrapedPage, scrape_website
from skyvern.webeye.scraper.scraped_page import ElementTreeFormat, ScrapedPage
from skyvern.webeye.utils.page import SkyvernFrame
LOG = structlog.get_logger()
@@ -2274,10 +2274,9 @@ class ForgeAgent:
draw_boxes = False
scroll = False
return await scrape_website(
browser_state,
task.url,
app.AGENT_FUNCTION.cleanup_element_tree_factory(task=task, step=step),
return await browser_state.scrape_website(
url=task.url,
cleanup_element_tree=app.AGENT_FUNCTION.cleanup_element_tree_factory(task=task, step=step),
scrape_exclude=app.scrape_exclude,
max_screenshot_number=max_screenshot_number,
draw_boxes=draw_boxes,

View File

@@ -24,7 +24,7 @@ from skyvern.services import workflow_script_service
from skyvern.webeye.actions.action_types import POST_ACTION_EXECUTION_ACTION_TYPES
from skyvern.webeye.actions.actions import Action
from skyvern.webeye.browser_state import BrowserState
from skyvern.webeye.scraper.scraper import ELEMENT_NODE_ATTRIBUTES, CleanupElementTreeFunc, json_to_html
from skyvern.webeye.scraper.scraped_page import ELEMENT_NODE_ATTRIBUTES, CleanupElementTreeFunc, json_to_html
from skyvern.webeye.utils.dom import SkyvernElement
from skyvern.webeye.utils.page import SkyvernFrame