python 中 lxml 的 etree 標籤解析

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')

# 獲取標籤數
len(root)
# 獲取標籤索引號,如果有多個相同標籤的話,可以區分
root.index(span)
# 按位元置插入
root.insert(0, etree.Element('p'))
# 尾部新增
root.append(etree.Element('strong'))

from lxml import etree

root = etree.Element('root')

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

# 獲取父節點方法一
span.getparent().tag
# 獲取父節點方法二,用列表獲取子節點,再獲取父節點
root[0].getparent().tag

from lxml import etree

root = etree.Element('root')
root.set('title', '這是一個root標籤')

from lxml import etree
root = etree.Element('root')
# 獲取屬性方法一
root.get('title')
# 獲取屬性方法二,參考字典的操作
root.keys(),root.values(),root.items()
# 獲取屬性方法三,直接拿到屬性存放的字典
root.attrib

from lxml import etree

root = etree.Element('root')

# 標籤內新增文字
root.text='i am autofelix'
# 標籤後追加文字
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文字
word.is_text
# 是否是tail文字
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檔案裡的空行
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操作就相當與找到了這個元素節點,返回匹配到的第一個元素
root.find('.//a').text
# 配合列表解析
[ b.text for b in root.findall('.//a') ]
# 根據屬性查詢
root.findall('.//a[@class]')[0].tag