[image purify] #image # 11st #url #purify

purify.py

import csv
import gzip
import os

file_name = 'input0000'
out_file_name = 'input0000.fix'

if os.path.exists(out_file_name):
    os.remove(out_file_name)

with open(file_name) as ifd, open(out_file_name, mode='a') as ofd:
    csv_reader = csv.reader(ifd, delimiter=',', quoting=csv.QUOTE_NONE)
    csv_writer = csv.writer(ofd, delimiter=',')
    try:
        for row in csv_reader:
            url = row[2].split(',')[0].strip('"')
            if url.startswith('/RoL'):
                url = url[4:]
            out_row = [row[0], row[1], url]
            csv_writer.writerow(out_row)
    except Exception as error:
        print error

def purify(url):
    url = url.split(',')[0].strip('"')
    if url.startswith('/RoL'):
        url = url[4:]
    return