方法
def has_class_but_no_id(tag):
return tag.has_attr('class') and not tag.has_attr('id')soup.find_all(has_class_but_no_id)
# [<p class="title"><b>The Dormouse's story</b></p>,
# <p class="story">Once upon a time there were...</p>,
# <p class="story">...</p>]def not_lacie(href):
return href and not re.compile("lacie").search(href)
soup.find_all(href=not_lacie)
# [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>,
# <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]from bs4 import NavigableString
def surrounded_by_strings(tag):
return (isinstance(tag.next_element, NavigableString)
and isinstance(tag.previous_element, NavigableString))
for tag in soup.find_all(surrounded_by_strings):
print tag.name
# p
# a
# a
# a
# pLast updated