Created
September 14, 2015 08:07
-
-
Save shantanuo/55646e47602f140e82f5 to your computer and use it in GitHub Desktop.
a python script that will download and merge all excel files of village Amenities across all states
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
### Download the xlsx files in the range of 1,000 to 2,999 | |
import urllib2, urllib, time | |
for i in xrange(1000, 3000): | |
filename='DCHB_Village_Release_'+str(i)+'.xlsx' | |
url = "http://www.censusindia.gov.in/2011census/dchb/"+filename | |
try: | |
urllib2.urlopen(url) | |
except urllib2.HTTPError, e: | |
print(e.code) | |
except urllib2.URLError, e: | |
print(e.args) | |
else: | |
urllib.urlretrieve(url, filename) | |
finally: | |
time.sleep(1) | |
### Open the excel files downloaded from the above script and load data as dataFrame for each file | |
import glob,os | |
import pandas as pd | |
dfList=[] | |
for myfile in glob.glob('/home/ubuntu/datameet/*.xlsx'): | |
print myfile.split(',')[0] | |
myvar=os.path.basename(myfile).split('.')[0] | |
myvar=pd.read_excel(myfile) | |
dfList.append(myvar) | |
### merge all dataframes into one | |
final=pd.concat(dfList) | |
### export all data to csv | |
import sys | |
reload(sys) | |
sys.setdefaultencoding('utf-8') | |
final.to_csv('final_data.csv') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment