单页调用代码
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
book = n.xpath('//*[@id="subject_list"]/ul/li')#通过定位获取元素,定位至整个模块的xpath
for ele in book:
name = ele.xpath('./div[2]/h2/a/@title')[0]#不加[0]的话,会显示【‘’】
score = ele.xpath('./div[2]/div[2]/span[2]/text()')[0]
people = ele.xpath('./div[2]/div[2]/span[3]/text()')[0].strip().strip('(').strip(')').strip('人评价')#.strip()删除空格
print('{} {} {}'.format(name,score,people))
循环页面调用(第一第二循环页面,引入time模块)
from lxml import etree#导入lxml库中的etree模块
import requests#导入requests模块,
import time#导入time模块,
for i in range(5):#调用5页循环
ur