Python爬虫入门

讲解Xpath常用代码，无任何实例：
· 读取xml节点内容（多个，单个）
· xpath读取heml文件
· 读取指定节点，条件筛选，循环读取

####XPath解析
from lxml import etree

xml = """

    l
    野花贬低向
    臭豆腐
    
        周大枪
        周芷若
        周杰伦
        蔡依林
        
            惹了
        
    

    
        胖胖陈
        胖胖不陈
    

"""


tree = etree.XML(xml)
tree.xpath("/book")  #/相当于节点关系，/相当于根节点
result = tree.xpath("/book/name/text()")  ## text()获取文本
result = tree.xpath("/book/author/nick/text()")  ## text()获取文本
result = tree.xpath("/book/author/div/nick/text()")  ## text()获取文本
result = tree.xpath("/book/author//nick/text()")  ## //相当于所有子节点
result = tree.xpath("/book/author当前所有节点
result = tree.xpath("/book//nick/text()")  ## /*/当前所有节点



print(result)

以下代码读取指定文件内容 b.html

b.html:

    
    


    

        
百度
        
谷歌
        
搜狗
    
    

        
飞机
        
大炮
        
火车
    
    
李嘉诚
    
胡辣汤

代码：

# %%
from lxml import etree

tree = etree.parse("b.html")
result = tree.xpath("/html/body/ul/li/a/text()")
result = tree.xpath("/html/body/ul/li[1]/a/text()")  ## 第一个li节点内容
result = tree.xpath("/html/body/ol/li/a[@href='dapao']/text()")  ###节点[@属性='值'] 找到指定值
list = tree.xpath("/html/body/ol/li")
for i in list:
    ###从每一个li中提取文字信息
    data = i.xpath("./a/text()")    
    print(data)
    params = i.xpath("./a/@href")
    print(params)
print(result)
print(tree.xpath("/html/body/ul/li/a/@href"))

##页面右键直接复制Xpath
print(tree.xpath("/html/body/div[2]/text()"))