/promotion/232 utm_source
/promotion/237 LandingPage/borrowExtend/? ;
/promotion/25113 LandingPage/mhd
/promotion/25113 LandingPage/mhd
/promotion/25199 com/LandingPage
/promotion/254 LandingPage/mhd/mhd4/? ;
/promotion/259 LandingPage/ydy/? ;
/promotion/25113 LandingPage/mhd
/promotion/25199 com/LandingPage
/promotion/25199 com/LandingPage

line_dict_uniq = dict()
with open('1.txt','r') as fd:
for line in fd:
key = line.split(' ')[0]
if key not in line_dict_uniq.values():
line_dict_uniq[key] = line
else:
continue
print line_dict_uniq 
print len(line_dict_uniq)
# 這里是打印了不重復的行（重復的只打印一次），實際再把這個結(jié)果寫入文件就可以了，
# 就不寫這段寫入文件的代碼了

line_dict_uniq = dict()
with open('1.txt','r') as fd:
for line in fd:
key = line.split(' ')[0]
if key not in line_dict_uniq.keys():
line_dict_uniq[key] = line
else:
continue
print line_dict_uniq
print len(line_dict_uniq)

# -*- coding: utf-8 -*-
'''
只使用與較小的文件，比較大的文件運行時間長
'''
def quchong(infile,outfile):

  infopen = open(infile,'r',encoding='utf-8')
  outopen = open(outfile,'w',encoding='utf-8')
  lines = infopen.readlines()
  list_1 = []
  for line in lines:
    if line not in list_1:
      list_1.append(line)
      outopen.write(line)
  infopen.close()
  outopen.close()
quchong("源文件路徑","目標文件路徑")