这篇博客通过Python的lxml库展示了XML和HTML的解析方法，包括使用XPath选取元素、获取属性值以及遍历节点等内容。示例中详细演示了如何提取书籍标题、价格等信息，并展示了如何针对特定属性筛选元素。
-
from lxml import etree -
s=""" -
<?xml version="1.0" encoding="UTF-8"?> -
<bookstore> -
<book> -
<title lang="eng">Harry Potter</title> -
<price>29.99</price> -
</book> -
<book> -
<title lang="eng">Learning XML</title> -
<price>39.95</price> -
</book> -
</bookstore> -
""" -
#将变量读取为html对象,自动添加<html><body>... ...</body></html> -
html=etree.HTML(s) -
#解析数据 /根节点 -
data1=html.xpath('/html') -
for i in data1: -
print(i) -
#//后面根子孙节点，后面的节点可以在任意位置 -
data2=html.xpath('//title') -
for i in data2: -
print(i) -
#写具体路径 -
data3=html.xpath('/html/body/bookstore/book/price') -
for i in data3: -
print(i.text) -
#循环某个属性 -
data4=html.xpath('/html/body/bookstore/book/title/@lang') -
for i in data4: -
print(i) -
#代表当前节点，..代表父节点 -
data5=html.xpath('/html/body/bookstore/book/title') -
for i in data5: -
a=i.xpath('./@lang') -
print(a) -
#读取某一个节点 -
data6=html.xpath('/html/body/bookstore/book') -
for i in data6: -
ti_1=i.xpath('./title[1]') -
print(ti_1) -
ti_last=i.xpath('./title[last()]') -
print(ti_last) -
#带有某些属性的标签 -
data7=html.xpath('//book/title[@lang="eng"]') -
for i in data7: -
print(i.text) -
#*位置节点 -
data8=html.xpath('//book/*') -
for i in data8: -
print(i) -
if hasattr(i,'text'): -
print(i.text) -
else: -
print(i)
-
from lxml import etree -
doc=''' -
<div> -
<ul> -
<li class="item-0"><a href="link1.html">first item</a></li> -
<li class="item-1"><a href="link2.html">second item</a></li> -
<li class="item-inactive"><a href="link3.html">third item</a></li> -
<li class="item-1"><a href="link4.html">fourth item</a></li> -
<li class="item-0"><a href="link5.html">fifth item</a> </li> -
</ul> -
</div> -
''' -
#将字符串解析为html对象，补全html，body -
html=etree.HTML(doc) -
#将a标签的文本直接获取//text() -
data2=html.xpath('//li/a/text()') -
print(data2) -
#解析html文件 -
parser=etree.HTMLParser(encoding='utf-8') -
html_file=etree.parse('123.htm',parser=parser) -
#匹配任意节点 -
data3=html_file.xpath('//*') -
for i in data3: -
if hasattr(i,'text'): -
print(i.text) -
#解析带属性的a标签的text文本 -
data4=html_file.xpath('//li/a[@href="link2.html"]/text()') -
print(data4) -
#解析属性的值 -
data5=html_file.xpath('//li/a/@href') -
print(data5) -
#谓语 -
data6=html_file.xpath('//li[last()]/a/text()') -
print(data6)
扫一扫
72
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
