def name(c):
'传入1个字符，返回该字符的unicode name'
if c in d:return d[c]
else:return c.encode('ascii',errors='namereplace').decode('raw_unicode_escape')[3:-1]
d={
'\x00': 'NULL',
'\x01': 'START OF HEADING',
'\x02': 'START OF TEXT',
'\x03': 'END OF TEXT',
'\x04': 'END OF TRANSMISSION',
'\x05': 'ENQUIRY',
'\x06': 'ACKNOWLEDGE',
'\x07': 'BEL',
'\x08': 'BACKSPACE',
'\t': 'HORIZONTAL TABULATION',
'\n': 'LINE FEED',
'\x0b': 'VERTICAL TABULATION',
'\x0c': 'FORM FEED',
'\r': 'CARRIAGE RETURN',
'\x0e': 'SHIFT OUT',
'\x0f': 'SHIFT IN',
'\x10': 'DATA LINK ESCAPE',
'\x11': 'DEVICE CONTROL ONE',
'\x12': 'DEVICE CONTROL TWO',
'\x13': 'DEVICE CONTROL THREE',
'\x14': 'DEVICE CONTROL FOUR',
'\x15': 'NEGATIVE ACKNOWLEDGE',
'\x16': 'SYNCHRONOUS IDLE',
'\x17': 'END OF TRANSMISSION BLOCK',
'\x18': 'CANCEL',
'\x19': 'END OF MEDIUM',
'\x1a': 'SUBSTITUTE',
'\x1b': 'ESCAPE',
'\x1c': 'FILE SEPARATOR',
'\x1d': 'GROUP SEPARATOR',
'\x1e': 'RECORD SEPARATOR',
'\x1f': 'UNIT SEPARATOR',
' ': 'SPACE',
'!': 'EXCLAMATION MARK',
'"': 'QUOTATION MARK',
'#': 'NUMBER SIGN',
'$': 'DOLLAR SIGN',
'%': 'PERCENT SIGN',
'&': 'AMPERSAND',
"'": 'APOSTROPHE',
'(': 'LEFT PARENTHESIS',
')': 'RIGHT PARENTHESIS',
'*': 'ASTERISK',
'+': 'PLUS SIGN',
',': 'COMMA',
'-': 'HYPHEN-MINUS',
'.': 'FULL STOP',
'/': 'SOLIDUS',
'0': 'DIGIT ZERO',
'1': 'DIGIT ONE',
'2': 'DIGIT TWO',
'3': 'DIGIT THREE',
'4': 'DIGIT FOUR',
'5': 'DIGIT FIVE',
'6': 'DIGIT SIX',
'7': 'DIGIT SEVEN',
'8': 'DIGIT EIGHT',
'9': 'DIGIT NINE',
':': 'COLON',
';': 'SEMICOLON',
'<': 'LESS-THAN SIGN',
'=': 'EQUALS SIGN',
'>': 'GREATER-THAN SIGN',
'?': 'QUESTION MARK',
'@': 'COMMERCIAL AT',
'A': 'LATIN CAPITAL LETTER A',
'B': 'LATIN CAPITAL LETTER B',
'C': 'LATIN CAPITAL LETTER C',
'D': 'LATIN CAPITAL LETTER D',
'E': 'LATIN CAPITAL LETTER E',
'F': 'LATIN CAPITAL LETTER F',
'G': 'LATIN CAPITAL LETTER G',
'H': 'LATIN CAPITAL LETTER H',
'I': 'LATIN CAPITAL LETTER I',
'J': 'LATIN CAPITAL LETTER J',
'K': 'LATIN CAPITAL LETTER K',
'L': 'LATIN CAPITAL LETTER L',
'M': 'LATIN CAPITAL LETTER M',
'N': 'LATIN CAPITAL LETTER N',
'O': 'LATIN CAPITAL LETTER O',
'P': 'LATIN CAPITAL LETTER P',
'Q': 'LATIN CAPITAL LETTER Q',
'R': 'LATIN CAPITAL LETTER R',
'S': 'LATIN CAPITAL LETTER S',
'T': 'LATIN CAPITAL LETTER T',
'U': 'LATIN CAPITAL LETTER U',
'V': 'LATIN CAPITAL LETTER V',
'W': 'LATIN CAPITAL LETTER W',
'X': 'LATIN CAPITAL LETTER X',
'Y': 'LATIN CAPITAL LETTER Y',
'Z': 'LATIN CAPITAL LETTER Z',
'[': 'LEFT SQUARE BRACKET',
'\\': 'REVERSE SOLIDUS',
']': 'RIGHT SQUARE BRACKET',
'^': 'CIRCUMFLEX ACCENT',
'_': 'LOW LINE',
'`': 'GRAVE ACCENT',
'a': 'LATIN SMALL LETTER A',
'b': 'LATIN SMALL LETTER B',
'c': 'LATIN SMALL LETTER C',
'd': 'LATIN SMALL LETTER D',
'e': 'LATIN SMALL LETTER E',
'f': 'LATIN SMALL LETTER F',
'g': 'LATIN SMALL LETTER G',
'h': 'LATIN SMALL LETTER H',
'i': 'LATIN SMALL LETTER I',
'j': 'LATIN SMALL LETTER J',
'k': 'LATIN SMALL LETTER K',
'l': 'LATIN SMALL LETTER L',
'm': 'LATIN SMALL LETTER M',
'n': 'LATIN SMALL LETTER N',
'o': 'LATIN SMALL LETTER O',
'p': 'LATIN SMALL LETTER P',
'q': 'LATIN SMALL LETTER Q',
'r': 'LATIN SMALL LETTER R',
's': 'LATIN SMALL LETTER S',
't': 'LATIN SMALL LETTER T',
'u': 'LATIN SMALL LETTER U',
'v': 'LATIN SMALL LETTER V',
'w': 'LATIN SMALL LETTER W',
'x': 'LATIN SMALL LETTER X',
'y': 'LATIN SMALL LETTER Y',
'z': 'LATIN SMALL LETTER Z',
'{': 'LEFT CURLY BRACKET',
'|': 'VERTICAL LINE',
'}': 'RIGHT CURLY BRACKET',
'~': 'TILDE',
'\x7f': 'DELETE',
'\x80': 'PADDING CHARACTER',
'\x81': 'HIGH OCTET PRESET',
'\x82': 'BREAK PERMITTED HERE',
'\x83': 'NO BREAK HERE',
'\x84': 'INDEX',
'\x85': 'NEXT LINE (NEL)',
'\x86': 'START OF SELECTED AREA',
'\x87': 'END OF SELECTED AREA',
'\x88': 'CHARACTER TABULATION SET',
'\x89': 'CHARACTER TABULATION WITH JUSTIFICATION',
'\x8A': 'LINE TABULATION SET',
'\x8B': 'PARTIAL LINE FORWARD',
'\x8C': 'PARTIAL LINE BACKWARD',
'\x8D': 'REVERSE LINE FEED',
'\x8E': 'SINGLE SHIFT TWO',
'\x8F': 'SINGLE SHIFT THREE',
'\x90': 'DEVICE CONTROL STRING',
'\x91': 'PRIVATE USE ONE',
'\x92': 'PRIVATE USE TWO',
'\x93': 'SET TRANSMIT STATE',
'\x94': 'CANCEL CHARACTER',
'\x95': 'MESSAGE WAITING',
'\x96': 'START OF GUARDED AREA',
'\x97': 'END OF GUARDED AREA',
'\x98': 'START OF STRING',
'\x99': 'SINGLE GRAPHIC CHARACTER INTRODUCER',
'\x9A': 'SINGLE CHARACTER INTRODUCER',
'\x9B': 'CONTROL SEQUENCE INTRODUCER',
'\x9C': 'STRING TERMINATOR',
'\x9D': 'OPERATING SYSTEM COMMAND',
'\x9E': 'PRIVACY MESSAGE',
'\x9F': 'APPLICATION PROGRAM COMMAND',
}
def main():
s=input('将字符串转换成\\N{...}\n请输入：')
l=[]
for c in s:
if c in d:
l.append('\\N{%s}'%d[c])
else:
l.append(c.encode('ascii',errors='namereplace').decode('raw_unicode_escape'))
s=''.join(l)
print("\'%s\'"%s)
if __name__=='__main__':
main()
别问了，不优化了！
ascii部分数据来源
import re
# 数据来自于lib\encoding目录的latin-1，并修改一处BELL至BEL
s='''
'\x00' # 0x00 -> NULL
'\x01' # 0x01 -> START OF HEADING
'\x02' # 0x02 -> START OF TEXT
'\x03' # 0x03 -> END OF TEXT
'\x04' # 0x04 -> END OF TRANSMISSION
'\x05' # 0x05 -> ENQUIRY
'\x06' # 0x06 -> ACKNOWLEDGE
'\x07' # 0x07 -> BEL
'\x08' # 0x08 -> BACKSPACE
'\t' # 0x09 -> HORIZONTAL TABULATION
'\n' # 0x0A -> LINE FEED
'\x0b' # 0x0B -> VERTICAL TABULATION
'\x0c' # 0x0C -> FORM FEED
'\r' # 0x0D -> CARRIAGE RETURN
'\x0e' # 0x0E -> SHIFT OUT
'\x0f' # 0x0F -> SHIFT IN
'\x10' # 0x10 -> DATA LINK ESCAPE
'\x11' # 0x11 -> DEVICE CONTROL ONE
'\x12' # 0x12 -> DEVICE CONTROL TWO
'\x13' # 0x13 -> DEVICE CONTROL THREE
'\x14' # 0x14 -> DEVICE CONTROL FOUR
'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
'\x16' # 0x16 -> SYNCHRONOUS IDLE
'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
'\x18' # 0x18 -> CANCEL
'\x19' # 0x19 -> END OF MEDIUM
'\x1a' # 0x1A -> SUBSTITUTE
'\x1b' # 0x1B -> ESCAPE
'\x1c' # 0x1C -> FILE SEPARATOR
'\x1d' # 0x1D -> GROUP SEPARATOR
'\x1e' # 0x1E -> RECORD SEPARATOR
'\x1f' # 0x1F -> UNIT SEPARATOR
' ' # 0x20 -> SPACE
'!' # 0x21 -> EXCLAMATION MARK
'"' # 0x22 -> QUOTATION MARK
'#' # 0x23 -> NUMBER SIGN
'$' # 0x24 -> DOLLAR SIGN
'%' # 0x25 -> PERCENT SIGN
'&' # 0x26 -> AMPERSAND
"'" # 0x27 -> APOSTROPHE
'(' # 0x28 -> LEFT PARENTHESIS
')' # 0x29 -> RIGHT PARENTHESIS
'*' # 0x2A -> ASTERISK
'+' # 0x2B -> PLUS SIGN
',' # 0x2C -> COMMA
'-' # 0x2D -> HYPHEN-MINUS
'.' # 0x2E -> FULL STOP
'/' # 0x2F -> SOLIDUS
'0' # 0x30 -> DIGIT ZERO
'1' # 0x31 -> DIGIT ONE
'2' # 0x32 -> DIGIT TWO
'3' # 0x33 -> DIGIT THREE
'4' # 0x34 -> DIGIT FOUR
'5' # 0x35 -> DIGIT FIVE
'6' # 0x36 -> DIGIT SIX
'7' # 0x37 -> DIGIT SEVEN
'8' # 0x38 -> DIGIT EIGHT
'9' # 0x39 -> DIGIT NINE
':' # 0x3A -> COLON
';' # 0x3B -> SEMICOLON
'<' # 0x3C -> LESS-THAN SIGN
'=' # 0x3D -> EQUALS SIGN
'>' # 0x3E -> GREATER-THAN SIGN
'?' # 0x3F -> QUESTION MARK
'@' # 0x40 -> COMMERCIAL AT
'A' # 0x41 -> LATIN CAPITAL LETTER A
'B' # 0x42 -> LATIN CAPITAL LETTER B
'C' # 0x43 -> LATIN CAPITAL LETTER C
'D' # 0x44 -> LATIN CAPITAL LETTER D
'E' # 0x45 -> LATIN CAPITAL LETTER E
'F' # 0x46 -> LATIN CAPITAL LETTER F
'G' # 0x47 -> LATIN CAPITAL LETTER G
'H' # 0x48 -> LATIN CAPITAL LETTER H
'I' # 0x49 -> LATIN CAPITAL LETTER I
'J' # 0x4A -> LATIN CAPITAL LETTER J
'K' # 0x4B -> LATIN CAPITAL LETTER K
'L' # 0x4C -> LATIN CAPITAL LETTER L
'M' # 0x4D -> LATIN CAPITAL LETTER M
'N' # 0x4E -> LATIN CAPITAL LETTER N
'O' # 0x4F -> LATIN CAPITAL LETTER O
'P' # 0x50 -> LATIN CAPITAL LETTER P
'Q' # 0x51 -> LATIN CAPITAL LETTER Q
'R' # 0x52 -> LATIN CAPITAL LETTER R
'S' # 0x53 -> LATIN CAPITAL LETTER S
'T' # 0x54 -> LATIN CAPITAL LETTER T
'U' # 0x55 -> LATIN CAPITAL LETTER U
'V' # 0x56 -> LATIN CAPITAL LETTER V
'W' # 0x57 -> LATIN CAPITAL LETTER W
'X' # 0x58 -> LATIN CAPITAL LETTER X
'Y' # 0x59 -> LATIN CAPITAL LETTER Y
'Z' # 0x5A -> LATIN CAPITAL LETTER Z
'[' # 0x5B -> LEFT SQUARE BRACKET
'\\' # 0x5C -> REVERSE SOLIDUS
']' # 0x5D -> RIGHT SQUARE BRACKET
'^' # 0x5E -> CIRCUMFLEX ACCENT
'_' # 0x5F -> LOW LINE
'`' # 0x60 -> GRAVE ACCENT
'a' # 0x61 -> LATIN SMALL LETTER A
'b' # 0x62 -> LATIN SMALL LETTER B
'c' # 0x63 -> LATIN SMALL LETTER C
'd' # 0x64 -> LATIN SMALL LETTER D
'e' # 0x65 -> LATIN SMALL LETTER E
'f' # 0x66 -> LATIN SMALL LETTER F
'g' # 0x67 -> LATIN SMALL LETTER G
'h' # 0x68 -> LATIN SMALL LETTER H
'i' # 0x69 -> LATIN SMALL LETTER I
'j' # 0x6A -> LATIN SMALL LETTER J
'k' # 0x6B -> LATIN SMALL LETTER K
'l' # 0x6C -> LATIN SMALL LETTER L
'm' # 0x6D -> LATIN SMALL LETTER M
'n' # 0x6E -> LATIN SMALL LETTER N
'o' # 0x6F -> LATIN SMALL LETTER O
'p' # 0x70 -> LATIN SMALL LETTER P
'q' # 0x71 -> LATIN SMALL LETTER Q
'r' # 0x72 -> LATIN SMALL LETTER R
's' # 0x73 -> LATIN SMALL LETTER S
't' # 0x74 -> LATIN SMALL LETTER T
'u' # 0x75 -> LATIN SMALL LETTER U
'v' # 0x76 -> LATIN SMALL LETTER V
'w' # 0x77 -> LATIN SMALL LETTER W
'x' # 0x78 -> LATIN SMALL LETTER X
'y' # 0x79 -> LATIN SMALL LETTER Y
'z' # 0x7A -> LATIN SMALL LETTER Z
'{' # 0x7B -> LEFT CURLY BRACKET
'|' # 0x7C -> VERTICAL LINE
'}' # 0x7D -> RIGHT CURLY BRACKET
'~' # 0x7E -> TILDE
'\x7f' # 0x7F -> DELETE
'''
# l1=re.findall('(?<=\').*(?=\')|(?<=").*(?=")',s)
# l1=re.findall('(?<=\')[.\n]*(?=\')|(?<=").*(?=")',s)
# l1=re.findall('((?<=\')(.*|\n)(?=\'))|(?<=").*(?=")',s)
# l1=re.findall('(?<=\')(.*|\n)(?=\')|(?<=").*(?=")',s)
l1=re.findall('(?<=").+(?=")|(?<=\').*(?=\')|(?<=\')\n(?=\')',s)
l2=re.findall('> (.*)\n?',s)
d={
}
for i in range(0x80):
d[l1[i]]=l2[i]
for i,j in d.items():
c=eval("'\\N{%s}'"%j)
if i!=c:
print(repr(i),repr(c))
又见正则的坑！