import time
import os
#if no directory called andrew_course9
if 'andrew_course9' not in os.listdir():
#create andrew_course9 directory
os.mkdir('andrew_course9')
#stock_id
sid = ['1101','2330']
for s in sid:
res = requests.get('website')
res.encoding = 'big5'
#set up save address , ex:andrew_course9\1101.html
path = os.path.join('andrew_course9',s+'.html')
#open the file ,write in ,then close
f = open(path,'w',encoding='utf-8')
f.write(res.text)
f.close()
print(s)
#pause 20 sec , to prevent website does not let you catch data
time.sleep(20)
********************************************************************************
dfs = []
#for every stock
for s in sid:
#get the file from directory
path = os.path.join('andrew_course9', s + '.html')
dfs.append(pd.read_html(path,encoding = 'utf-8'))
dfs[1][1].head(10)
*********************************************************************************
沒有留言:
張貼留言