Created
July 15, 2016 07:12
-
-
Save djinn/caff94cd59d02248da63bd894c671477 to your computer and use it in GitHub Desktop.
Download entire Indian Banks IFSC code database as xls files
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
#pip install requests | |
#pip install bs4 | |
#Author: Supreet Sethi <supreet.sethi@gmail.com> | |
#Date: Fri Jul 15 14:11:38 WIB 2016 | |
#License: MIT | |
from requests import get | |
import cookielib | |
from bs4 import BeautifulSoup | |
import re | |
from os.path import basename | |
jar = cookielib.CookieJar() | |
headers = {'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36'} | |
u = get("https://www.rbi.org.in/Scripts/bs_viewcontent.aspx?Id=2009", cookies=jar) | |
soup = BeautifulSoup(u.content) | |
ulist = soup.findAll("a", href=re.compile('xls$')) | |
for xl in ulist: | |
dataurl = xl['href'] | |
if dataurl.startswith("http://"): | |
dataurl = 'https://' +dataurl[7:] | |
print dataurl | |
xlfd = get(dataurl, cookies=jar) | |
fname = basename(dataurl) | |
writefd = open(fname, 'w') | |
writefd.write(xlfd.content) | |
writefd.close() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment