上次用python抓了三大法人每日买卖 CODE如下
LINK http://www.twse.com.tw/ch/trading/fund/T86/T86.php
这次想说如法炮制 来抓
LINK http://www.taifex.com.tw/chinese/3/3_1_2.asp
结果失败了
可以提点一下吗?
抓下来CSV内容如下
<HTML>
3 <head><link rel="image_src" type="image/jpeg" href="http://www.taifex.com.tw/chinese/images/fb_logo.jpg" /><meta property="og:image" content="http://www.taifex.com.tw/chinese/images/
4 <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
5 <META NAME="GENERATOR" Content="Microsoft Visual Studio 6.0">
6 </HEAD>
7 <BODY>
8
9 <script language="javascript">
10 alert('?亦访鞈欧?');
11 window.history.go(-1);
12 </script>
13
14 </BODY>
15 </HTML>
我的程式码
import requests
import time
import os
import sys
#mydate = time.strftime("%Y/%m/%d")
mydate = "2016/11/28"
#mydate = "2016/10/03"
#mydate2 = "105/10/03"
if len(sys.argv) < 2: # argv=1 path
print 'no argument'
elif sys.argv[1].strip()!='':
mydate = sys.argv[1]
year = str(int(mydate[0:4])-1911)
mydate2 = mydate.replace(mydate[0:4],year)
print sys.argv
print mydate2
setting = os.getcwd() + "\\" + "path.ini"
if os.path.exists(setting):
with open(setting, 'r') as r:
path = r.read()
if not os.path.exists(path):
os.makedirs(path)
else:
path = "/home/telepaq/frankh/fonepy/" #path have to be direct path
headers = {"User-Agent":"Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.112 Safari/537.36", "Referer":"http://www.taifex.com.tw/chinese/3/3_1_2.asp"}
url1 = "http://www.taifex.com.tw/chinese/3/3_1_2dl.asp"
payload1 = {"DATA_DATE": mydate,
"DATA_DATE1": mydate,
"COMMODITY_ID": "ALL",
#"sorting": "by_issue"}
"his_year": "2015",
"datestart": mydate,
"dateend": mydate
}
res1 = requests.post(url1, headers=headers, data=payload1, stream=True)
print payload1
fName1 = path + mydate.replace("/","") + ".csv"
print fName1
with open(fName1, 'wb') as f1:
for chunk in res1.iter_content(1024):
f1.write(chunk)
f = open("/home/telepaq/frankh/fonepy/log_future312.txt",'w')
#f.write(payload1 + "\r\n")
f.write(mydate + " mydate\r\n")
f.write(mydate2 + " mydate2 \r\n")
f.write(fName1 + " fName1 \r\n")
print 'this is a test'