python小白学习记录运用lxml的xpath解析html文件

 1 from lxml import etree
 2 text = "<div><p>nmsl</p><span>nmsl</span></div>"
 3 def htmlstree(text):
 4     html = etree.HTML(text)
 5     result = etree.tostring(html)
 6     print(result)
 7     return result.decode('utf-8')
 8 #解析html字符串并且会为标签自动加上<html><body></body></html>
 9 def parseetree():
10     parser = etree.HTMLParser(encoding='utf-8')
11     html = etree.parse("index111.html",parser=parser)
12     result = etree.tostring(html,encoding='utf-8').decode("utf-8")
13     print(result)
14 #解析xml 由于某写html标签会不全用普通的xml解析器会出错 如<br/>  所以要指定html解析器
15 if __name__ == '__main__':
16     parseetree()

以上为etree的使用范例

分别解析了html字符串和html文件

from lxml import etree
def parseetree():#找到包含onclick和id属性的a标签
    parser = etree.HTMLParser(encoding='utf-8')
    html = etree.parse("index111.html",parser=parser)
    trs = html.xpath("//a[@onclick][@id]")
    for tr in trs:
        result = etree.tostring(tr,encoding='utf-8').decode("utf-8")
        print(result)
def parseetree1():#找到包含onclick和id属性的a标签中的第4个，即[3]
    parser = etree.HTMLParser(encoding='utf-8')
    html = etree.parse("index111.html",parser=parser)
    tr = html.xpath("//a[@onclick][@id]")[3]
    result = etree.tostring(tr,encoding='utf-8').decode("utf-8")
    print(result)
def parseetree2():#找到包含onclik和id属性的a标签中的id的值  和  文本的值
    parser = etree.HTMLParser(encoding='utf-8')
    html = etree.parse("index111.html",parser=parser)
    trs = html.xpath("//a[@onclick][@id]/@id")
    for tr in trs:
        print(tr)
    trs2 = html.xpath("//a[@onclick][@id]/text()")
    for tr in trs2:
        print(tr)
if __name__ == "__main__":
    parseetree()
    print("***************")
    parseetree1()
    print("***************")
    parseetree2()