发一个去除文本干扰字符的函数

#coding:utf-8

def defrag_txt(txt):#for unicode
    result = []
    pre_is_en = False
    stop_word = set(u' ,.。')
    for i in txt:
        num_i = ord(i)
        if i not in stop_word:
            if 0x4e00 <= num_i < 0x9fa6:
                result.append(i)
                continue
            if 97 <= num_i <= 122 or 65 <= num_i <= 90:
                result.append(i)
                pre_is_en = True
                continue
            if 48 <= num_i <= 57:
                result.append(i)
                continue
            num_diff = num_i-0xff10
            if 0 <= num_diff < 10:
                result.append(str(num_diff))
                continue
            pre_is_en = False
        else:
            if pre_is_en:
                result.append(i)
                pre_is_en = False
    return ''.join(result)


print defrag_txt(u"""腾//讯○电●话:１２３４５６７８９０""")

腾讯电话1234567890   

评论

1 楼 fxsjy 2009-03-24  

有效果吗？我订阅了豆瓣的RSS，最近一个月总是有类似的广告。