中文转数字

最新推荐文章于 2024-04-23 09:33:57 发布

starcslike

最新推荐文章于 2024-04-23 09:33:57 发布

阅读量182

点赞数

分类专栏： Python 文章标签： python

本文链接：https://blog.csdn.net/starcslike/article/details/125409099

版权

Python 专栏收录该内容

4 篇文章 0 订阅

订阅专栏

本文介绍了一个Python脚本，用于将中文数字字符串转换为阿拉伯数字。重点讲解了`chinese2digits`函数，它处理了中文数字的读法和单位转换。通过实例展示了如何查找并替换整个字符串中的所有中文数字。

摘要由CSDN通过智能技术生成

#!/usr/bin/python
# coding:utf-8

num_str_start_symbol = [u'一', u'二', u'两', u'三', u'四', u'五', u'六', u'七', u'八', u'九', u'十']
more_num_str_symbol = [u'零', u'一', u'二', u'两', u'三', u'四', u'五', u'六', u'七', u'八', u'九', u'十', u'百', u'千', u'万', u'亿']
common_used_numerals = {u'零': 0, u'一': 1, u'二': 2, u'两': 2, u'三': 3, u'四': 4, u'五': 5, u'六': 6, u'七': 7, u'八': 8, u'九': 9, u'十': 10, u'百': 100, u'千': 1000, u'万': 10000, u'亿': 100000000}


def chinese2digits(uchars_chinese):
    total = 0
    r = 1  # 表示单位：个十百千...
    for i in range(len(uchars_chinese) - 1, -1, -1):
        val = common_used_numerals.get(uchars_chinese[i])
        if val >= 10 and i == 0:  # 应对 十三 十四 十*之类
            if val > r:
                r = val
                total = total + val
            else:
                r = r * val
        elif val >= 10:
            if val > r:
                r = val
            else:
                r = r * val
        else:
            total = total + r * val
    return total


def changeChineseNum2Arab(oriStr):
    lenStr = len(oriStr)
    aProStr = ''
    if lenStr == 0:
        return aProStr

    hasNumStart = False
    numberStr = ''
    for idx in range(lenStr):
        if oriStr[idx] in num_str_start_symbol:
            if not hasNumStart:
                hasNumStart = True

            numberStr += oriStr[idx]
        else:
            if hasNumStart:
                if oriStr[idx] in more_num_str_symbol:
                    numberStr += oriStr[idx]
                    continue
                else:
                    numResult = str(chinese2digits(numberStr))
                    numberStr = ''
                    hasNumStart = False
                    aProStr += numResult

            aProStr += oriStr[idx]
            pass

    if len(numberStr) > 0:
        resultNum = chinese2digits(numberStr)
        aProStr += str(resultNum)

    return aProStr


def findAllChineseNum(oriStr):
    chineseNums = []
    lenStr = len(oriStr);
    if lenStr > 0:
        hasNumStart = False
        numberStr = ''
        for idx in range(lenStr):
            if oriStr[idx] in num_str_start_symbol:
                if not hasNumStart:
                    hasNumStart = True

                numberStr += oriStr[idx]
            else:
                if hasNumStart:
                    if oriStr[idx] in more_num_str_symbol:
                        numberStr += oriStr[idx]
                        continue
                    else:
                        chineseNums.append(numberStr)
                        numberStr = ''
                        hasNumStart = False

                pass
        if len(numberStr) > 0:
            chineseNums.append(numberStr)

    return chineseNums