adchos 文本混淆工具

#-*- coding:utf-8 -*- 
import jieba
import random
import codecs
import sys
import string
import chardet


#chos_symbol_header = u‘???????????????????????‘
chos_symbol_tailer = u‘★☆??????♀????????‘
chos_symbol_midle = u‘．、︰﹒．﹐﹑ˋ´﹎﹍﹒，′‵‘～﹏﹌﹋—–―＿¯￣﹍﹉‘
def getcontentfromfile(in_filename):
    try:
        f = open(in_filename,‘r‘)
        l = f.readlines()
        return l
    except:
        print ‘ERROR WHILE OPENING ‘ + in_filename

def splitstring(in_ad):
    if ‘‘ != in_ad:
        seg_list = jieba.cut(in_ad)
        return seg_list
    else:
        return ‘‘

if __name__ == ‘__main__‘:
    reload(sys) 
    sys.setdefaultencoding("utf-8")

    if 2 != len(sys.argv):
        content = getcontentfromfile(‘ad.txt‘)
    else:
        content = getcontentfromfile(sys.argv[1])

    output = codecs.open(‘output.txt‘,‘w+‘,‘utf-8‘)
    for item in content:
        buf = u‘‘
        words = splitstring(item.strip())
        for word in words:
            buf = buf + word + ‘‘.join(random.sample(chos_symbol_midle,1)).encode(‘utf-8‘) 
        h = ‘‘.join(random.sample(chos_symbol_tailer,1))
        t = ‘‘.join(random.sample(chos_symbol_tailer,1))
        output.write(h.encode(‘utf-8‘) +  buf.encode(‘utf-8‘) + t.encode(‘utf-8‘)  +‘\r\n‘.encode(‘utf-8‘))
    output.close()