问题相关代码,请勿粘贴截图
我想要达到的结果
import openpyxl
import requests
from lxml import etree
wb=openpyxl.Workbook() # 新建一个workbook
#print(wb)
ws=wb.active # 调用正在运行的工作表
ws['AL']='漫画';ws['B1']='作者名字';ws['C1'] = '人气'
number=2
for n in range(460):
url=f'https://ac.qq.com/Comic/all/search/hot/page/{n}'
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.111 Safari/537.36'
}
response=requests.get(url=url,headers=headers)
html=response.text
tree=etree.HTML(html)
li_all=tree.xpath('/html/body/div[3]/div[2]/div/div[2]/ul')
for q in range(len(li_all)):
e=li_all[q].xpath('./div[2]/h3/a/text()')
z=li_all[q].xpath('./div[2]/p[1]/text()')
r=li_all[q].xapth('/div[2]/p[2]/span/em/text()')
ws[f'A{number}']=e[0]
ws[f'B{number}'] = z[0]
ws[f'C{number}'] = r[0]
print('漫画:',e[0],'\n作者名字:',z[0],'n\人气:',r[0])
print()
number+=1
wb.save('./漫画.xlsx')