python(指定URLの符号化を検出)


import urllib.request
import chardet

def main():
	url = input('   URL:')
	response = urllib.request.urlopen(url)
	html = response.read()

#      
encode = chardet.detect(html)['encoding']
if encode == 'GB2312':
	encode == 'GBK'

print('         :%s' % encode)

if __name__ == '__main__':
	main()

実行結果
>>>   URL:https://www.baidu.com/
         :ascii
>>>   URL:https://www.python.org/
         :utf-8