python字符處理_只保留文本里的漢字

# -*- coding: utf-8 -*-

def is_chinese(uchar):
    """判斷一個unicode是否是漢字"""
    if uchar >= u'\u4e00' and uchar <= u'\u9fa5':
        return True
    else:
        return False

def is_number(uchar):
    """判斷一個unicode是否是數字"""
    if uchar >= u'\u0030' and uchar <= u'\u0039':
        return True
    else:
        return False

def is_alphabet(uchar):
    """判斷一個unicode是否是英文字母"""
    if (uchar >= u'\u0041' and uchar <= u'\u005a') or (uchar >= u'\u0061' and uchar <= u'\u007a'):
        return True
    else:
        return False

def is_legal(uchar):
    """判斷是否非漢字，數字和英文字符"""
    if not (is_chinese(uchar) or is_number(uchar) or is_alphabet(uchar)):
        return False
    else:
        return True

# -*- coding: utf-8 -*-
"""
輸入文件格式需要是gb2312
"""
import check_legal
fileRead = file('input.txt', 'r')
fileWrite = file('result.txt', 'w')
while True:
    line = fileRead.readline()
    # check end file
    if len(line) == 0:
        break
    # ignore作用: 忽略非法字符
    strBuffer = line.decode('gb2312', 'ignore')
    str = ""
    for oneWord in strBuffer:
        if check_legal.is_chinese(oneWord):
            str += oneWord
    fileWrite.write(str.encode('gb2312'))
    fileWrite.write('\n')
fileRead.close()
fileWrite.close()

至於文件格式問題，可以用一些文本編輯器指定保存格式，例如EmEditor.