Apply same fix to puppeteer

changedetectionio/content_fetchers/playwright.py

@@ -49,6 +49,9 @@ async def capture_full_page_async(page, screenshot_format='JPEG', watch_uuid=Non
     if page_height > page.viewport_size['height']:
         if page_height < step_size:
             step_size = page_height # Incase page is bigger than default viewport but smaller than proposed step size
+        # Never set viewport taller than our max capture height - otherwise one screenshot chunk
+        # captures the whole (e.g. 8098px) page even when SCREENSHOT_MAX_HEIGHT=1000
+        step_size = min(step_size, SCREENSHOT_MAX_TOTAL_HEIGHT)
         viewport_start = time.time()
         logger.debug(f"{watch_info}Setting bigger viewport to step through large page width W{page.viewport_size['width']}xH{step_size} because page_height > viewport_size")
         # Set viewport to a larger size to capture more content at once

changedetectionio/content_fetchers/puppeteer.py

@@ -75,6 +75,9 @@ async def capture_full_page(page, screenshot_format='JPEG', watch_uuid=None, loc
     if page_height > page.viewport['height']:
         if page_height < step_size:
             step_size = page_height # Incase page is bigger than default viewport but smaller than proposed step size
+        # Never set viewport taller than our max capture height - otherwise one screenshot chunk
+        # captures the whole page even when SCREENSHOT_MAX_HEIGHT is set smaller
+        step_size = min(step_size, SCREENSHOT_MAX_TOTAL_HEIGHT)
         viewport_start = time.time()
         await page.setViewport({'width': page.viewport['width'], 'height': step_size})
         viewport_time = time.time() - viewport_start

changedetectionio/content_fetchers/screenshot_handler.py

@@ -56,6 +56,10 @@ def stitch_images_worker_raw_bytes(pipe_conn, original_page_height, capture_heig
             im.close()
         del images
 
+        # Clip stitched image to capture_height (chunks may overshoot by up to step_size-1 px)
+        if total_height > capture_height:
+            stitched = stitched.crop((0, 0, max_width, capture_height))
+
         # Draw caption only if page was trimmed
         if original_page_height > capture_height:
             draw = ImageDraw.Draw(stitched)