注意后面的解释
from lxml import etree#导入lxml库中的etree模块
import requests#导入requests模块,
url = "https://book.douban.com/tag/小说?start=0&type=T"#变量赋值
s = requests.get(url).text#requests的get方法
n = etree.HTML(s)#将网页进行etree模块下HTML方法解析
name = n.xpath('//*[@id="subject_list"]/ul/li[1]/div[2]/h2/a/@title')[0]#通过定位获取元素
score = n.xpath('//*[@id="subject_list"]/ul/li[1]/div[2]/div[2]/span[2]/text()')#不加[0]的话,会显示【‘’】
people = n.xpath('//*[@id="subject_list"]/ul/li[1]/div[2]/div[2]/span[3]/text()')[0].strip().strip('(')#.strip()删除空格
print(name)
print(score)
print(people)
解忧杂货店
[‘8.5’]
537281人评价)
from lxml import etree#导入lxml库中的etree模块
import requests#导入requests模块,
url = "https://book.douban.com/tag/小说?start=0&type=T"#变量赋值
s = requests.get(url).text#request