Python文件处理实战：利用chardet解决编码与mimetypes识别类型

__coding__ = 'UTF-8'
__author__ = 'bingo'

import chardet
import configparser
parse = configparser.ConfigParser()
parse.read("config.ini")
print(parse.sections())

chardet检测编码并读取配置示例

import chardet
import configparser

data = open("config.ini", "rb").read()
a = chardet.detect(data)
print(a)

parse = configparser.ConfigParser()
parse.read("config.ini", encoding=a["encoding"])
print(parse.sections())

>>>>>>>>>>>>>>>再运行：
G:\Anaconda\python.exe "C:/Users/bingo/Desktop/The crawler/学习/demo.py"
{'encoding': 'UTF-16', 'confidence': 1.0, 'language': ''}
['config']

Process finished with exit code 0

使用mimetypes识别文件类型

import mimetypes

# 获取文件MIME类型
type, encoding = mimetypes.guess_type("demo.py")
print(type)
# 根据MIME类型获取所有可能的文件后缀名
c = mimetypes.guess_all_extensions(type)
print(c)

>>>运行结果如下：
G:\Anaconda\python.exe "C:/Users/bingo/Desktop/The crawler/学习/demo.py"
text/plain
['.bat', '.c', '.h', '.ksh', '.pl', '.txt', '.asm', '.cc', '.cod', '.cpp', '.cs', '.csh', '.cshader', >'.csproj', '.cxx', '.def', '.dsh', '.dshader', '.dsp', '.dsw', '.efu', '.filters', '.fx', '.gitattributes', >'.gitignore', '.gitmodules', '.gsh', '.gshader', '.hh', '.hlsl', '.hlsli', '.hpp', '.hsh', '.hshader', >'.hxx', '.i', '.idl', '.inc', '.inl', '.ipp', '.js', '.jsproj', '.jsx', '.jsxbin', '.jsxinc', '.lst', '.mak', >'.map', '.mdp', '.mk', '.odh', '.odl', '.pkgdef', '.pkgundef', '.psh', '.pshader', '.py', '.pyw', >'.rc', '.rc2', '.rct', '.res', '.rgs', '.s', '.sln', '.sol', '.sor', '.srf', '.tlh', '.tli', '.ts', '.tsx', '.tt', >'.user', '.vb', '.vbproj', '.vcp', '.vcw', '.vsh', '.vshader']
.bat

Process finished with exit code 0