ayrisdev/crawl4ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(async_playwright_crawler): improve segment handling and viewport adjustments during screenshot capture (Fixed bug: Capturing Screenshot Twice and Increasing Image Size)

Browse Source
This commit is contained in:
ntohidi
2025-04-17 12:48:11 +02:00
parent 0ec3c4a788
commit 0886153d6a
1 changed files with 21 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
crawl4ai/async_crawler_strategy.py
View File

@@ -1162,12 +1162,32 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
num_segments = (page_height // viewport_height) + 1
for i in range(num_segments):
y_offset = i * viewport_height
# Special handling for the last segment
if i == num_segments - 1:
last_part_height = page_height % viewport_height
# If page_height is an exact multiple of viewport_height,
# we don't need an extra segment
if last_part_height == 0:
# Skip last segment if page height is exact multiple of viewport
break
# Adjust viewport to exactly match the remaining content height
await page.set_viewport_size({"width": page_width, "height": last_part_height})
await page.evaluate(f"window.scrollTo(0, {y_offset})")
await asyncio.sleep(0.01) # wait for render
seg_shot = await page.screenshot(full_page=False)
# Capture the current segment
# Note: Using compression options (format, quality) would go here
seg_shot = await page.screenshot(full_page=False, type="jpeg", quality=85)
# seg_shot = await page.screenshot(full_page=False)
img = Image.open(BytesIO(seg_shot)).convert("RGB")
segments.append(img)
# Reset viewport to original size after capturing segments
await page.set_viewport_size({"width": page_width, "height": viewport_height})
total_height = sum(img.height for img in segments)
stitched = Image.new("RGB", (segments[0].width, total_height))
offset = 0