解析器_etree

# -*- coding:utf-8 -*- 
from lxml import etree



src_str='''
<?xml version="1.0" encoding="utf-8"?>

<bookstore>

<book category="COOKING">
  <title lang="en">Everyday Italian</title>
  <author>Giada De Laurentiis</author>
  <year>2005</year>
  <price>30.00</price>
</book>

<book category="CHILDREN">
  <title lang="en">Harry Potter</title>
  <author>J K. Rowling</author>
  <year>2005</year>
  <price>29.99</price>
</book>

<book category="WEB">
  <title lang="en">XQuery Kick Start</title>
  <author>James McGovern</author>
  <author>Per Bothner</author>
  <author>Kurt Cagle</author>
  <author>James Linn</author>
  <author>Vaidyanathan Nagarajan</author>
  <year>2003</year>
  <price>49.99</price>
</book>

<book category="WEB">
  <title lang="en" class="a-color-base a-text-normal">Learning XML</title>
  <author>Erik T. Ray</author>
  <year>2003</year>
  <price>39.95</price>
</book>

</bookstore>
'''



# ==================# 构造
html = etree.HTML(src_str.encode('utf-8')) # byte
html = etree.parse(src_str) # string
#html = etree.fromstring(src_str.encode('utf-8'))



# ==================返回节点
# 条件price标签>35
print(html.xpath("//bookstore/book[price>35]/price"))

# 属性包含字符
print(html.xpath("//title[contains(@class,'a-color-base') and contains(@class,'a-text-normal')]"))



# ==================返回值
#属性
print(html.xpath('//*[@lang="en"]/@lang'))

#文本
print(html.xpath("//html/html()"))
print(html.xpath("//bookstore/book/price/text()"))

# 单节点返回值
nds = html.xpath("//bookstore/book[price>35]/price")
for nd in nds:
    print(nd.text.encode('gbk').decode('gbk'))

for nd in nds:
    print(nd.xpath('string(.)'))

# 节点转值
for nd in nds:
    print(etree.tostring(nd,encoding='utf-8').decode('utf-8'))



# ==================其他
import html
a = '&#x5916;&#x89C2;'
print(html.unescape(a))