Use regular expressions to identify Chinese in text

When we use regular expressions to identify Chinese, we use the Unicode character range to match Chinese numbers, and the Unicode range is \ue4e00-\u9fff.

import re
def extract_chinese_chars(code):
    chinese_pattern = '[\u4e00-\u9fff]+'  # 匹配中文字符
    chinese_chars = re.findall(chinese_pattern, code)
    return chinese_chars
# 测试代码
code = '''梅西是最好的，messi is the best'''
chinese_chars = extract_chinese_chars(code)
print("中文字符:", chinese_chars)

If we want to match character classes, we need to change the pattern to [a-zA-Z]

import re
def extract_chinese_chars(code):
    english_pattern = '[a-zA-Z]+'  # 匹配中文字符
    chinese_chars = re.findall(english_pattern, code)
    return chinese_chars
# 测试代码
code = '''梅西是最好的，messi is the best'''
english_chars = extract_chinese_chars(code)
print("中文字符:", english_chars)

Regular expressions have powerful text pattern matching, search, match, replace and extract strings.