Reptile _ urllib use the library without any anti-climb means crawling Baidu Home

"" " 
Get Baidu Home 
chardet: analytic function encoding format 
" "" 

from urllib Import Request 
Import the chardet 

get # page source code to binary 
url = "https://www.baidu.com/" 
byteHtml = request.urlopen (url ) .read () 
Print (byteHtml) 

# encoding format is determined binary code, the dictionary returns a value of 
# { 'encoding': 'ASCII', 'confidence': 1.0, 'Language': ''} 
result = chardet.detect (byteHtml ) 
Print (Result) 
Print (type (Result)) 
# source code obtained by decoding the binary encoding format correct page source code (a little, incomplete) 
resHtml byteHtml.decode = (Result [ "encoding"]) 
Print (resHtml)