Created
August 13, 2013 23:27
-
-
Save finoradin/6226706 to your computer and use it in GitHub Desktop.
A pretty jenky way of finding the date in an XML blob and putting it in the correct column.
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
import csv, re, argparse, os | |
parser = argparse.ArgumentParser(description="Helper for fixing xfr stn metadata. yolo.") | |
parser.add_argument('-i', '--input', type=str, required=True, help='full path to csv') | |
args = parser.parse_args() | |
csv_file = os.path.normpath(args.input) | |
with open(csv_file, 'rb') as xfrstncsv: | |
reader = csv.reader(xfrstncsv, delimiter=',', quotechar='"') | |
writefile = open(csv_file+'_fixed.csv', 'wb') | |
writer = csv.writer(writefile, delimiter=',', quotechar='"', quoting=csv.QUOTE_ALL) | |
i = 1 | |
for row in reader: | |
xml_blob = row[11] | |
m = "".join(re.findall ( '<date>(.*?)</date>', xml_blob, re.DOTALL)) | |
print "Row " + str(i) +" created date is: " + m | |
writer.writerow([row[0],str(row[1]),row[2],row[3],m,row[5],row[6],row[7],row[8],row[9],row[10],row[11]]) | |
i = i + 1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment