Skip to content
Open
Changes from all commits
Commits
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
8 changes: 8 additions & 0 deletions crawl4ai/content_scraping_strategy.py
Original file line number Diff line number Diff line change
Expand Up @@ -562,6 +562,14 @@ def remove_empty_elements_fast(self, root, word_count_threshold=5):
):
parent = el.getparent()
if parent is not None:
# Preserve .tail text before removing the element
tail = el.tail
if tail:
prev = el.getprevious()
if prev is not None:
prev.tail = (prev.tail or "") + tail
else:
parent.text = (parent.text or "") + tail
parent.remove(el)

return root
Expand Down