2020.11.28 Xpath

Xpath

先来一个无关的小练习–求和求平均数

N=10
sum=0
count=0
while count<N:
   number=int(input())
   sum=sum+number
   count=count+1
   average=sum/N
print("N={},sum={}".format(N,sum))
print(""Average={}".format(average))

XPATH解析HTML字符串

html=etree.HTML(text)
##转化为XML语法
result=etree.tostring(html,encoding='utf-8')
##result为bytes类型

XPATH解析HTML文件

htmlemt=etree.parse('text.xml')
result=etree.tostring(htmlemt,pretty_print=True)
##pretty_print 优化输出

获得所 < li> 标签

htmlemt=etree.parse('text.xml')
result=htmlemt.xpath('//li')
print(result)
print(result[0])

change a little
获得所 < li> 标签的所有class
result=htmlemt.xpath(’//li/@class’)
获得不包括 < li> 标签本身的class
result=htmlemt.xpath(’//li/a//@class’)

实战练习.爬取豆瓣网站

import requests
from lxml import etree
headers={
"User-Agentv":"Mozilla/5.0(windows NT 6.1;WOW64)AppleWebkit/537.36(khtml,like Gecko) Chrome/71.0.3554.0 Safari/537.36",
"Referer":"https://movie.douban.com/",
}#请求头设置
url="https://movie.douban.com/cinema/nowplaying/chongqing/"
#定义uRL
rep=requests.get(url,headers=headers)
text=rep.text#返回UNICODE
html=etree.html(text)
u1=html.xpath("//ul[@class='lists']")[0]
lis=ul.xpath("./li") #当前UL下所有LI标签
movie = []
for li in lis:   #循环更迭每一个li标签
   title=li.xpath("@data-title")[0]
   #直接通过@li属性来获得值
   score=li.xpath("@data-score")[0]
   region=li.xpath("@data-region")[0]
   actors=li.xpath("@data-actors")[0]
   director=li.xpath("@data-director")[0]
   liimg=li.xpath(".//img/@src")
movie={
   "title":title,
   "score":score,
   "region":region,
   "actors":actors,
   "directors":directors,
   "liimg":liimg,
   }#字典数据
 movies.append(movie)
 #添加到列表
 print(movies)