爬虫代码:
import urllib.request
import os, re
from bs4 import BeautifulSoup
import xlwt URL = "https://baike.baidu.com/item/%E7%99%BE%E5%90%8D%E7%BA%A2%E9%80%9A%E4%BA%BA%E5%91%98/23252458?fr=aladdin"
page = urllib.request.urlopen(URL)
soup = BeautifulSoup(page)
page.close() tables = soup.findAll('table')
tab = tables[0]
tr=tab.findAll('tr')
j=0
aa=[None]*100
pm = xlwt.Workbook()
sheet = pm.add_sheet('Sheet1', cell_overwrite_ok=True)
for th in tr:
i = 0
for td in th.findAll('td'):
sheet.write(j,i,str(td.text.replace("\n", "").replace(' ', '')))
i=i+1
j=j+1
pm.save("F://py//百名红通人员.xls")