import requests
from lxml import etree
import openpyxl
url = 'https://www.qidian.com/rank/yuepiao'headers = {'user-agent': 'Mozilla/5.0 (s NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36 Edg/88.0.705.63'}
resp = requests.get(url, headers=headers)
e = etree.HTML(resp.text)
names = e.xpath('//div[@class="book-mid-info"]/h4/a/text()')
authors = e.xpath('//p[@class="author"]/a[1]/text()')
lst = [['小说名称', '作者']]
print('将两个列表整合')
for i in range(0, len(names)):
lst.([names[i], authors[i]])
wb = openpyxl.Workbook()
sheet = wb.active
for item in lst:
sheet.((item))
wb.save('我的小说.xlsx')
步骤:
找到目标网站
模拟浏览器发送请求并获得相应结果
用xpath解析数据
用循环将数据存储到列表中
用openpyxl将数据存储到Excel中
附录:
第三方安装见:https://www.jianshu.com/p/d4262c8d8af8
xpath使用见:https://www.jianshu.com/p/1c34a1a0fae5