用于将纯文本（ASCII）转换为 GSM 7 位字符集的 Python 库？

Question

是否有用于将 ascii 数据编码为 7 位 GSM 字符集（用于发送 SMS）的 python 库？

Answer 1

现在有:)

感谢Chad 指出这不太正确

Python2 版本

# -*- coding: utf8 -*- 
gsm = (u"@£$¥èéùìòÇ\nØø\rÅåΔ_ΦΓΛΩΠΨΣΘΞ\x1bÆæßÉ !\"#¤%&'()*+,-./0123456789:;<=>"
       u"?¡ABCDEFGHIJKLMNOPQRSTUVWXYZÄÖÑܧ¿abcdefghijklmnopqrstuvwxyzäöñüà")
ext = (u"````````````````````^```````````````````{}`````\\````````````[~]`"
       u"|````````````````````````````````````€``````````````````````````")

def gsm_encode(plaintext):
    res = ""
    for c in plaintext:
        idx = gsm.find(c)
        if idx != -1:
            res += chr(idx)
            continue
        idx = ext.find(c)
        if idx != -1:
            res += chr(27) + chr(idx)
    return res.encode('hex')

print gsm_encode(u"Hello World")

输出为十六进制。显然，如果你想要二进制流，你可以跳过它

Python3 版本

# -*- coding: utf8 -*- 
import binascii
gsm = ("@£$¥èéùìòÇ\nØø\rÅåΔ_ΦΓΛΩΠΨΣΘΞ\x1bÆæßÉ !\"#¤%&'()*+,-./0123456789:;<=>?"
       "¡ABCDEFGHIJKLMNOPQRSTUVWXYZÄÖÑܧ¿abcdefghijklmnopqrstuvwxyzäöñüà")
ext = ("````````````````````^```````````````````{}`````\\````````````[~]`"
       "|````````````````````````````````````€``````````````````````````")

def gsm_encode(plaintext):
    res = ""
    for c in plaintext:
        idx = gsm.find(c);
        if idx != -1:
            res += chr(idx)
            continue
        idx = ext.find(c)
        if idx != -1:
            res += chr(27) + chr(idx)
    return binascii.b2a_hex(res.encode('utf-8'))

print(gsm_encode("Hello World"))

Answer 2

我从 gnibbler 的回答中得到了提示。这是我在查看在线转换器后以某种方式编写的脚本：http://smstools3.kekekasvi.com/topic.php?id=288，它对我来说可以正常工作。编码和解码。

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

gsm = (u"@£$¥èéùìòÇ\nØø\rÅåΔ_ΦΓΛΩΠΨΣΘΞ\x1bÆæßÉ !\"#¤%&'()*+,-./0123456789:;<=>"
   u"?¡ABCDEFGHIJKLMNOPQRSTUVWXYZÄÖÑÜ`¿abcdefghijklmnopqrstuvwxyzäöñüà")
ext = (u"````````````````````^```````````````````{}`````\\````````````[~]`"
   u"|````````````````````````````````````€``````````````````````````")

def get_encode(currentByte, index, bitRightCount, position, nextPosition, leftShiftCount, bytesLength, bytes):
    if index < 8:
        byte = currentByte >> bitRightCount
        if nextPosition < bytesLength:
            idx2 = bytes[nextPosition]
            byte = byte | ((idx2) << leftShiftCount)
            byte = byte & 0x000000FF
        else:
            byte = byte & 0x000000FF
        return chr(byte).encode('hex').upper()
    return ''

def getBytes(plaintext):
    if type(plaintext) != str:
         plaintext = str(plaintext)
    bytes = []
    for c in plaintext.decode('utf-8'):
        idx = gsm.find(c)
        if idx != -1:
            bytes.append(idx)
        else:
            idx = ext.find(c)
            if idx != -1:
                bytes.append(27)
                bytes.append(idx)
    return bytes

def gsm_encode(plaintext):
    res = ""
    f = -1
    t = 0
    bytes = getBytes(plaintext)
    bytesLength = len(bytes)
    for b in bytes:
        f = f+1
        t = (f%8)+1
        res += get_encode(b, t, t-1, f, f+1, 8-t, bytesLength, bytes)

    return res


def chunks(l, n):
    if n < 1:
        n = 1
    return [l[i:i + n] for i in range(0, len(l), n)]

def gsm_decode(codedtext):
    hexparts = chunks(codedtext, 2)
    number   = 0
    bitcount = 0
    output   = ''
    found_external = False
    for byte in hexparts:
    byte = int(byte, 16);
        # add data on to the end
        number = number + (byte << bitcount)
        # increase the counter
        bitcount = bitcount + 1
        # output the first 7 bits
        if number % 128 == 27:
             '''skip'''
             found_external = True
        else:
            if found_external == True:                
                 character = ext[number % 128]
                 found_external = False
            else:
                 character = gsm[number % 128]
            output = output + character

        # then throw them away
        number = number >> 7
        # every 7th letter you have an extra one in the buffer
        if bitcount == 7:
            if number % 128 == 27:
                '''skip'''
                found_external = True
            else:
                if found_external == True:                
                    character = ext[number % 128]
                    found_external = False
                else:
                    character = gsm[number % 128]
                output = output + character

            bitcount = 0
            number = 0
    return output

Answer 3

我找不到任何图书馆。但我认为这不应该需要图书馆。它有点容易做到。

Here 是 Jon Skeet 本人在同一主题上。

例子：

s = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'

def ascii_to_gsm(ch):
    return bin(65 + s.index(ch))

print ascii_to_gsm('A')
print '--'

binary_stream = ''.join([str(ascii_to_gsm(ch))[2:] for ch in s])
print binary_stream

您也可以使用dict 来存储mapping between ASCII and GSM 7-bit character set。

Answer 4

我最近遇到了一个类似的问题，我们从聚合器收到 gsm7bit 解码的短信，主要是针对带有西班牙字符的 Verizon 运营商，但我们无法成功解码。 这是我在论坛中其他答案的帮助下创建的。这适用于 Python 2.7.x。

def gsm7bitdecode(text):
    gsm = (u"@£$¥èéùìòÇ\nØø\rÅåΔ_ΦΓΛΩΠΨΣΘΞ\x1bÆæßÉ !\"#¤%&'()*+,-./0123456789:;<=>"
           u"?¡ABCDEFGHIJKLMNOPQRSTUVWXYZÄÖÑÜ`¿abcdefghijklmnopqrstuvwxyzäöñüà")
    ext = (u"````````````````````^```````````````````{}`````\\````````````[~]`"
           u"|````````````````````````````````````€``````````````````````````")

    text = ''.join(["{0:08b}".format(int(text[i:i+2], 16)) for i in range(0, len(text), 2)][::-1])

    text = [(int(text[::-1][i:i+7][::-1], 2)) for i in range(0, len(text), 7)]
    text = text[:len(text)-1] if text[-1] == 0 else text
    text =iter(text)

    result = []
    for i in text:
        if i == 27:
            i = next(text)
            result.append(ext[i])
        else:
            result.append(gsm[i])

    return "".join(result).rstrip()