Skip to content

Add browser_type / executable_path to MarkdownifyWebScraperDriver #2230

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
feder-cr wants to merge 2 commits into
base: main
Choose a base branch
from
+29 −1
Draft

Add browser_type / executable_path to MarkdownifyWebScraperDriver #2230

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
45c04b8
Add browser_type / executable_path to MarkdownifyWebScraperDriver
feder-cr Jul 2, 2026
4949ffc
test: cover browser_type and executable_path on MarkdownifyWebScraper…
feder-cr Jul 11, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 10 additions & 1 deletion griptape/drivers/web_scraper/markdownify_web_scraper_driver.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,9 @@ class MarkdownifyWebScraperDriver(BaseWebScraperDriver):
exclude_ids: Optionally provide custom ids to exclude from the scraped content.
timeout: Optionally provide a timeout in milliseconds for the page to continue loading after
the browser has emitted the "load" event.
browser_type: Optionally provide a Playwright browser type (chromium, firefox, webkit).
Defaults to chromium.
executable_path: Optionally provide a path to a custom browser executable.
"""

DEFAULT_EXCLUDE_TAGS = ["script", "style", "head", "audio", "img", "picture", "source", "video"]
Expand All @@ -37,11 +40,17 @@ class MarkdownifyWebScraperDriver(BaseWebScraperDriver):
exclude_classes: list[str] = field(default=Factory(list), kw_only=True)
exclude_ids: list[str] = field(default=Factory(list), kw_only=True)
timeout: int | None = field(default=None, kw_only=True)
browser_type: str = field(default="chromium", kw_only=True)

@collindutter collindutter Jul 17, 2026

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can we add some validation here? Maybe replace str with Literal["chromium", "firefox", "webkit"] and add an attr's validator validator=attrs.validators.in_(["chromium", "firefox", "webkit"])?

executable_path: str | None = field(default=None, kw_only=True)

def fetch_url(self, url: str) -> str:
sync_playwright = import_optional_dependency("playwright.sync_api").sync_playwright

with sync_playwright() as p, p.chromium.launch(headless=True) as browser:
launch_kwargs: dict[str, Any] = {"headless": True}
if self.executable_path is not None:
launch_kwargs["executable_path"] = self.executable_path

with sync_playwright() as p, getattr(p, self.browser_type).launch(**launch_kwargs) as browser:
page = browser.new_page()

def skip_loading_images(route: Any) -> Any:
Expand Down
19 changes: 19 additions & 0 deletions tests/unit/drivers/web_scraper/test_markdownify_web_scraper_driver.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,3 +88,22 @@ def test_scrape_url_raises_on_none_from_playwright(self, web_scraper, mock_conte

with pytest.raises(Exception, match="can't access URL"):
web_scraper.scrape_url("https://example.com/")

def test_default_launch_uses_chromium_headless(self, web_scraper, mock_playwright):
web_scraper.scrape_url("https://example.com/")
mock_playwright.__enter__.return_value.chromium.launch.assert_called_once_with(headless=True)

def test_executable_path_passthrough(self, mock_playwright, mock_content):
MarkdownifyWebScraperDriver(executable_path="/opt/ff/firefox").scrape_url("https://example.com/")
mock_playwright.__enter__.return_value.chromium.launch.assert_called_once_with(
headless=True, executable_path="/opt/ff/firefox"
)

def test_browser_type_selects_firefox(self, mock_playwright):
firefox_launch = mock_playwright.__enter__.return_value.firefox.launch
firefox_launch.return_value.__enter__.return_value.new_page.return_value.content.return_value = (
'<html><a href="foobar.com">foobar</a></html>'
)
artifact = MarkdownifyWebScraperDriver(browser_type="firefox").scrape_url("https://example.com/")
assert artifact.value == "[foobar](foobar.com)"
firefox_launch.assert_called_once_with(headless=True)
Loading