抓取中文网页

[python]代码库

 import sys
 import urllib.request
 req = urllib.request.Request('http://www.baidu.com')
 response = urllib.request.urlopen(req)
 the_page = response.read()
 type = sys.getfilesystemencoding() #转换成本地系统编码
 
print(the_page.decode(type))