def handle_startendtag(self, tag, attrs):
'''
处理类似于<br/>这样的直接闭合的标签
:param tag:
:param attrs:
:return:
'''
# print("tag_startend:{0}".format(tag))
# 父方法获取对应的标签和属性
HTMLParser.handle_startendtag(self, tag, attrs)
# 新建该节点 并分类
node = wn.WebNode()
if tag == "br":
node = wn.BrNode()
elif tag == "hr":
node = wn.HrNode()
elif tag == "meta":
node = wn.MetaNode()
elif tag == "img":
node = wn.ImgNode()
# 赋值标签信息
node.tag = tag
node.father = self.now
# 直接闭合标签必然是有父节点的
node.index = node.father.index + 1
node.path = node.father.path + "-" + "{0}[{1}]".format(tag, len(node.father.children) + 1)
# 给其赋值其属性
for each in attrs:
node.attr[each[0]] = each[1]
# 设定其特别的类型
node.type = "startendtag"
# 将其加入其父节点的子节点列表中
self.now.children.append(node)
def handle_startendtag(self, tag, attrs):
HTMLParser.handle_startendtag(self, tag, attrs)