xpath_邓治安

最新推荐文章于 2023-05-10 09:42:20 发布

xiao~zhi

最新推荐文章于 2023-05-10 09:42:20 发布

阅读量223

点赞数

文章标签：爬虫

本文链接：https://blog.csdn.net/m0_57120802/article/details/124082507

版权

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)

xiao~zhi

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
xpath_邓治安

from lxml import etrees=""" <?xml version="1.0" encoding="UTF-8"?> <bookstore> <book> <title lang="eng">Harry Potter</title> <price>29.99</price> </book&gt.
复制链接

扫一扫