python抓取新浪首页的小例子

参考

廖雪峰的python教程：http://www.liaoxuefeng.com/wiki/001374738125095c955c1e6d8bb493182103fac9270762a000/001386832653051fd44e44e4f9e4ed08f3e5a5ab550358d000

代码：

 #!/usr/bin/python

 # import module
 import socket
 import io

 # create TCP object
 s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
 # connect sina
 s.connect(('www.sina.com.cn', 80))
 # send request
 s.send('GET / HTTP/1.1\r\nHost: www.sina.com.cn\r\nConnection: close\r\n\r\n')
 # receive data
 buffer = []
 while True:
     # every time receive 1k data
     d = s.recv(1024)
     if d:
         buffer.append(d)
     else:
         break
 data = ''.join(buffer)
 # close socket
 header, html = data.split('\r\n\r\n', 1)
 print header
 # write receive data to file
 with open('sina.html', 'wb') as f:
     f.write(html)

主要功能是模拟浏览器访问网页服务器，并从网页服务器获取返回信息