from datetime import date
import requests
import dill
def crawl_date(ordinaldate):
dd = date.fromordinal(ordinaldate)
datestr = dd.strftime("%Y%m%d")
fetchstr = 'http://www.twse.com.tw/exchangeReport/MI_INDEX?response=csv&date=' + datestr + '&type=ALLBUT0999'
print("fetching",fetchstr)
r = requests.post(fetchstr)
f = open("twse/"+datestr, "wt", encoding="utf8", newline='\n')
f.write(r.text)
f.close()
datestr2 = dd.strftime("%Y/%m/%d")
datestr2 = datestr2.replace(datestr2[0:4], str(int(datestr2[0:4])-1911))
fetchstr = 'http://www.tpex.org.tw/web/stock/aftertrading/daily_close_quotes/stk_quote_download.php?l=zh-tw&d=' + datestr2 + '&s=0,asc,0'
print("fetching tpex ", fetchstr)
r = requests.post(fetchstr)
f = open("tpex/"+datestr, "wt", encoding="utf8", newline='\n')
f.write(r.text)
f.close()
return 0
crawl_test.py
from datetime import date
import crawl_save
import time
if __name__ == "__main__":
import sys
if ((not sys.argv[1]) or (not sys.argv[2])):
print("need 2 parameters\n");
sys.exit(0)
d1=date.fromisoformat(sys.argv[1][:4]+'-'+sys.argv[1][4:6]+'-'+sys.argv[1][6:8])
d2=date.fromisoformat(sys.argv[2][:4]+'-'+sys.argv[2][4:6]+'-'+sys.argv[2][6:8])
d1ord=d1.toordinal()
d2ord=d2.toordinal()
for dd in range(d1ord, d2ord+1):
crawl_save.crawl_date(dd)
time.sleep(10)
沒有留言:
張貼留言