Skip to content

feat: add force viewport screenshot #1694

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
theredrad wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat: add force viewport screenshot #1694

Show file tree
Hide file tree
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
5 changes: 5 additions & 0 deletions crawl4ai/async_configs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1081,6 +1081,9 @@ class CrawlerRunConfig():
Default: None.
screenshot_height_threshold (int): Threshold for page height to decide screenshot strategy.
Default: SCREENSHOT_HEIGHT_TRESHOLD (from config, e.g. 20000).
force_viewport_screenshot (bool): If True, always take viewport-only screenshots regardless of page height.
When False, uses automatic decision (viewport for short pages, full-page for long pages).
Default: False.
pdf (bool): Whether to generate a PDF of the page.
Default: False.
image_description_min_word_threshold (int): Minimum words for image description extraction.
Expand Down Expand Up @@ -1220,6 +1223,7 @@ def __init__(
screenshot: bool = False,
screenshot_wait_for: float = None,
screenshot_height_threshold: int = SCREENSHOT_HEIGHT_TRESHOLD,
force_viewport_screenshot: bool = False,
pdf: bool = False,
capture_mhtml: bool = False,
image_description_min_word_threshold: int = IMAGE_DESCRIPTION_MIN_WORD_THRESHOLD,
Expand Down Expand Up @@ -1336,6 +1340,7 @@ def __init__(
self.screenshot = screenshot
self.screenshot_wait_for = screenshot_wait_for
self.screenshot_height_threshold = screenshot_height_threshold
self.force_viewport_screenshot = force_viewport_screenshot
self.pdf = pdf
self.capture_mhtml = capture_mhtml
self.image_description_min_word_threshold = image_description_min_word_threshold
Expand Down
11 changes: 10 additions & 1 deletion crawl4ai/async_crawler_strategy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -998,7 +998,9 @@ async def handle_request_failed_capture(request):
if config.screenshot_wait_for:
await asyncio.sleep(config.screenshot_wait_for)
screenshot_data = await self.take_screenshot(
page, screenshot_height_threshold=config.screenshot_height_threshold
page,
screenshot_height_threshold=config.screenshot_height_threshold,
force_viewport_screenshot=config.force_viewport_screenshot
)

if screenshot_data or pdf_data or mhtml_data:
Expand Down Expand Up @@ -1536,6 +1538,13 @@ async def take_screenshot(self, page, **kwargs) -> str:
Returns:
str: The base64-encoded screenshot data
"""
# Check if viewport-only screenshot is forced
force_viewport = kwargs.get('force_viewport_screenshot', False)

if force_viewport:
# Use viewport-only screenshot
return await self.take_screenshot_naive(page)

need_scroll = await self.page_need_scroll(page)

if not need_scroll:
Expand Down