python 中 lxml 的 etree 标签解析

pip install lxml

from lxml import etree

root = etree.Element('root')

from lxml import etree

root = etree.Element('root')
span = etree.SubElement(root, 'span')

from lxml import etree

root = etree.Element('root')

span = etree.SubElement(root, 'span')
root.remove(span)

from lxml import etree

root = etree.Element('root')
root.clear()

from lxml import etree

root = etree.Element('root')

span = etree.SubElement(root, 'span')

# 获取标签数
len(root)
# 获取标签索引号,如果有多个相同标签的话,可以区分
root.index(span)
# 按位置插入
root.insert(0, etree.Element('p'))
# 尾部添加
root.append(etree.Element('strong'))

from lxml import etree

root = etree.Element('root')

span = etree.SubElement(root, 'span')

# 获取父节点方法一
span.getparent().tag
# 获取父节点方法二,用列表获取子节点,再获取父节点
root[0].getparent().tag

from lxml import etree

root = etree.Element('root')
root.set('title', '这是一个root标签')

from lxml import etree
root = etree.Element('root')
# 获取属性方法一
root.get('title')
# 获取属性方法二,参考字典的操作
root.keys(),root.values(),root.items()
# 获取属性方法三,直接拿到属性存放的字典
root.attrib

from lxml import etree

root = etree.Element('root')

# 标签内添加文本
root.text='i am autofelix'
# 标签后追加文本
root.tail = 'i am autofelix'

from lxml import etree

root = etree.Element('root')

word = root.xpath('//text()')
word[0].getparent().tag

from lxml import etree

root = etree.Element('root')

word = root.xpath('//text()')
# 是否是text文本
word.is_text
# 是否是tail文本
word.is_tail

from lxml import etree

html = etree.fromstring('<root>autofelix</root>')
html.tag
etree.tostring(html)

from lxml import etree

html = etree.XML('<root>autofelix</root>')
html.tag
etree.tostring(html)

from lxml import etree

# 去除xml文件里的空行
parser= etree.XMLParser(remove_blank_text=True)
root = etree.XML('<root> auto felix </root>', parser)
print etree.tostring(root)

from lxml import etree

html = etree.HTML('<root>autofelix</root>')
etree.tostring(html)

from lxml import etree

root = etree.XML('<root><a class="uname">i am autofelix<b/><c/><b/></a></root>')
# findall操作返回列表
root.findall('a')[0].text
# find操作就相当与找到了这个元素节点,返回匹配到的第一个元素
root.find('.//a').text
# 配合列表解析
[ b.text for b in root.findall('.//a') ]
# 根据属性查询
root.findall('.//a[@class]')[0].tag