python网络爬虫（一）

POST方式

from urllib.error import URLError,HTTPError

import urllib.request
import urllib.parse
url='http://www.baidu.com/s'
values={'wd':'python',
        'opt-webpage':'on',
        'ie':'gbk'}
 
data=urllib.parse.urlencode(values).encode(encoding='utf_8') 
req=urllib.request.Request(url,data) 
#or ony one sentense:full_url=url+'?'+url_values


try:
    response=urllib.request.urlopen(req)    
except HTTPError as e:
    print('Error code:',e.code) 
except URLError as e:
    print('Reason',e.reason)
the_page=response.read() 

print(the_page)

GET方式

import urllib.request
import urllib.parse
  
values={"rls":"ig"}  
  
data= urllib.parse.urlencode(values) 
url = 'http://www.baidu.com'    
full_url = url + '?' +  data
req=urllib.request.Request(full_url )  
response = urllib.request.urlopen(req)   
page=response.read()
print( page)