如何将抓取的数据列表转换为 excel 列？

Question

import openpyxl
xl_file = openpyxl.Workbook()
xl_sheet =xl_file.active

from urllib.request import urlopen
from bs4 import BeautifulSoup

stockItem = '028300'

url = 'http://finance.naver.com/item/sise_day.nhn?code='+ stockItem
html = urlopen(url) 
source = BeautifulSoup(html.read(), "html.parser")

maxPage=source.find_all("table",align="center")
mp = maxPage[0].find_all("td",class_="pgRR")
mpNum = int(mp[0].a.get('href')[-3:])

for page in range(1, 10):
   print (str(page) )
   url = 'http://finance.naver.com/item/sise_day.nhn?code=' + stockItem +'&page='+ str(page)
   html = urlopen(url)
   source = BeautifulSoup(html.read(), "html.parser")
   srlists=source.find_all("tr")
   isCheckNone = None

   if((page % 1) == 0):
      time.sleep(0)

   for i in range(1,len(srlists)-1):
      if(srlists[i].span != isCheckNone):

          srlists[i].td.text
          data1 = srlists[i].find_all("td",align="center")
          data2 = srlists[i].find_all("td",class_="num") 
          print(srlists[i].find_all("td",align="center")[0].text, srlists[i].find_all("td",class_="num")[0].text )

          for item in data1:
             xl_sheet.append([item.get_text()])

这就是我从网站抓取股票数据所做的。 我已经成功爬取了股票的数据。 但是，我无法将数据保存到 excel 文件中。 我试过了，但它只显示没有价格数据的日期数据。 如何将结果转换为 excel 文件？

Answer 1

你错过了两件事， 1）导入包错误 2）没有在包含价格的excel中附加data2

这是最终代码，它将提供您想要的输出。只需将您的文件夹位置用于保存 excel 文件即可。

import time
from openpyxl import Workbook  #
xl_file = Workbook()
xl_sheet =xl_file.active

from urllib.request import urlopen
from bs4 import BeautifulSoup
i = 0
stockItem = '028300'

url = 'http://finance.naver.com/item/sise_day.nhn?code='+ stockItem
html = urlopen(url) 
source = BeautifulSoup(html.read(), "html.parser")

maxPage=source.find_all("table",align="center")
mp = maxPage[0].find_all("td",class_="pgRR")
mpNum = int(mp[0].a.get('href')[-3:])

for page in range(1, 10):
   print (str(page) )
   url = 'http://finance.naver.com/item/sise_day.nhn?code=' + stockItem +'&page='+ str(page)
   html = urlopen(url)
   source = BeautifulSoup(html.read(), "html.parser")
   srlists=source.find_all("tr")
   isCheckNone = None

   if((page % 1) == 0):
      time.sleep(0)

   for i in range(1,len(srlists)-1):
      if(srlists[i].span != isCheckNone):

          srlists[i].td.text
          data1 = srlists[i].find_all("td",align="center")
          data2 = srlists[i].find_all("td",class_="num") 
          #print(srlists[i].find_all("td",align="center")[0].text, srlists[i].find_all("td",class_="num")[0].text )

          for item1,item2 in zip(data1,data2):
              xl_sheet.append([item.get_text(),item2.get_text()])


print(xl_sheet)
xl_file.save(r'C:\Users\Asus\Desktop\vi.xlsx')

建议：你可以使用 Yahoofinance 的 Python 包轻松下载股票数据。 你可以点击这个链接>>https://pypi.org/project/yfinance/