import requests
from lxml import etree
import csv
import json
#//tbody/tr[@class]/td[2]/div/text()
fieldnames=['省份','住宿场所名称','城市','商圈','是否为客栈','星级','房间数','评论数','评分','城市平均订单','城市平均间夜','城市平均实住订单','城市平均实住间夜','住宿场所订单','住宿场所总间夜','住宿场所实住订单','住宿场所实住间夜','住宿场所直销订单','住宿场所直销间夜','住宿场所直销实住间夜','住宿场所直销拒单','城市直销订单','城市实住订单','城市直销拒单率']
op=open('hotel.csv','w',newline='',encoding='utf-8-sig')
find=csv.DictWriter(op,fieldnames=fieldnames)
find.writeheader()
for ym in range(1,6):
url=f'http://192.168.48.10:9091/info_{ym}.html'
http=requests.get(url)
root=etree.HTML(http.content.decode('utf-8'))
noob11=root.xpath('//tbody/tr[@class]/td[12]/div/text()')
print(processed_noob11)
输出结果为：
['500', '900', '100', '900', '500', '600', '300', '300', '900', '900', '500', '100', '500', '700']
['900', '100', '200', '300', '600', '800', '400', '600', '400', '100', '600', '400', '500', '300', '600']
['800', '800', '800', '200', '300', '100', '600', '400', '400', '300', '700', '600', '200', '200', '900']
['200', '500', '500', '200', '600', '300', '900', '300', '200', '200', '900', '700', '300', '300', '600']
['900', '500', '700', '900', '300', '400', '400', '500', '600', '700', '200', '700', '500', '200', '500']
主要问题：
在这个网页中，用的数据在div下没有text文本所以取不到那么应该怎么解决这个问题
网页源码：
