vodorod/Dorod-Sky
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Extract BrowserState.scrape_website (#4184)

Browse Source
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
Download Patch File Download Diff File Expand all files Collapse all files

2
skyvern/core/script_generations/real_skyvern_page_ai.py
View File

@@ -34,7 +34,7 @@ from skyvern.webeye.actions.handler import (
handle_upload_file_action,
)
from skyvern.webeye.actions.parse_actions import parse_actions
from skyvern.webeye.scraper.scraper import ScrapedPage
from skyvern.webeye.scraper.scraped_page import ScrapedPage
jinja_sandbox_env = SandboxedEnvironment()

5
skyvern/core/script_generations/script_skyvern_page.py
View File

@@ -27,7 +27,7 @@ from skyvern.webeye.actions.actions import (
)
from skyvern.webeye.actions.handler import ActionHandler, handle_complete_action
from skyvern.webeye.browser_state import BrowserState
from skyvern.webeye.scraper.scraper import ScrapedPage, scrape_website
from skyvern.webeye.scraper.scraped_page import ScrapedPage
LOG = structlog.get_logger()
@@ -106,8 +106,7 @@ class ScriptSkyvernPage(SkyvernPage):
# initialize browser state
# TODO: add workflow_run_id or eventually script_id/script_run_id
browser_state = await cls._get_or_create_browser_state(browser_session_id=browser_session_id)
return await scrape_website(
browser_state=browser_state,
return await browser_state.scrape_website(
url="",
cleanup_element_tree=app.AGENT_FUNCTION.cleanup_element_tree_factory(),
scrape_exclude=app.scrape_exclude,