Check duplicate by key in csv file, and then print the duplicate lines out.

csvDuplicateCheck.py

import codecs

filename = 'input.csv'
# fr = open(filename)
fr = codecs.open(filename,"r","shift_jis")
lines = fr.readlines()

lines.sort()

dict = {}
for line in lines:
    line = line.strip()
    key = line.split(',')[0]
    if key in dict:
        dict[key] += 1
    else:
        dict[key] = 1

list = dict.keys()

for line in lines:
    line = line.strip()
    key = line.split(',')[0]
    if key in dict and dict[key] > 1:
        print line