Skip to content

fix(crawler): skip body visibility check when ignore_body_visibility=True (#2129) #2192

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

Open
Battleplus wants to merge 1 commit into
base: main
Choose a base branch
from
+32 −28
Open

fix(crawler): skip body visibility check when ignore_body_visibility=True (#2129) #2192

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
60 changes: 32 additions & 28 deletions crawl4ai/async_crawler_strategy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -808,41 +808,45 @@ async def handle_request_failed_capture(request):
response_headers = {}

# Wait for body element and visibility
try:
await page.wait_for_selector("body", state="attached", timeout=30000)
# Skip entirely when ignore_body_visibility=True (the default)
# to avoid a hardcoded 30s penalty on pages where body is never visible
# (e.g., AngularJS ng-cloak, Vue v-cloak). See #2129.
if not config.ignore_body_visibility:
try:
await page.wait_for_selector("body", state="attached", timeout=30000)

# Use the new check_visibility function with csp_compliant_wait
is_visible = await self.csp_compliant_wait(
page,
"""() => {
const element = document.body;
if (!element) return false;
const style = window.getComputedStyle(element);
const isVisible = style.display !== 'none' &&
style.visibility !== 'hidden' &&
style.opacity !== '0';
return isVisible;
}"",
timeout=30000,
)

# Use the new check_visibility function with csp_compliant_wait
is_visible = await self.csp_compliant_wait(
page,
"""() => {
const element = document.body;
if (!element) return false;
const style = window.getComputedStyle(element);
const isVisible = style.display !== 'none' &&
style.visibility !== 'hidden' &&
style.opacity !== '0';
return isVisible;
}""",
timeout=30000,
)
if not is_visible:
visibility_info = await self.check_visibility(page)
raise Error(f"Body element is hidden: {visibility_info}")

if not is_visible and not config.ignore_body_visibility:
except Error:
visibility_info = await self.check_visibility(page)
raise Error(f"Body element is hidden: {visibility_info}")

except Error:
visibility_info = await self.check_visibility(page)

if self.browser_config.verbose:
self.logger.debug(
message="Body visibility info: {info}",
tag="DEBUG",
params={"info": visibility_info},
)
if self.browser_config.verbose:
self.logger.debug(
message="Body visibility info: {info}",
tag="DEBUG",
params={"info": visibility_info},
)

if not config.ignore_body_visibility:
raise Error(f"Body element is hidden: {visibility_info}")


# try:
# await page.wait_for_selector("body", state="attached", timeout=30000)

Expand Down