按第一字段切分文件

split_by_field.py

#!/bin/env python

#usage argv[0] file_tobe_split target_dir
#按第一字段切分文件

import sys

src_file = sys.argv[1]
tgt_dir = sys.argv[2]

last_index = None
for line in open(src_file):
    line = line.rstrip() 
    index = line.split('\t')[0]
    if last_index is None or index <> last_index:
        file = open(tgt_dir + '/' + index, 'w')
    print >>file, line 
    last_index = index