INNER CODE UNIT · Python
block_text
adbar/trafilatura · trafilatura/baseline.py:312
def block_text(element: HtmlElement) -> str:
"""text_content() alternative that preserves word boundaries at block tags (#896)."""
element = copy(element)
for elem in element.iter(*_BLOCK_ELEMS):
elem.text = f" {remove_control_characters(elem.text)}" if elem.text else " "
elem.tail = f" {remove_control_characters(elem.tail)}" if elem.tail else " "
return " ".join(element.text_content().split())