python实现网页链接提取的方法分享
复制代码 代码如下:
#encoding:utf-8
import socket
import htmllib,formatter
def open_socket(host,servname):
s=socket.socket(socket.AF_INET,socket.SOCK_STREAM)
port=socket.getservbyname(servname)
s.connect((host,port))
return s
host=''
host=input('请输入网址\n')
mysocket=open_socket(host,'http')
message='GET http://%s/\n\n'%(host,)
mysocket.send(message)
file=mysocket.makefile()
htmldata=file.read()
file.close()
parser=htmllib.HTMLParser(formatter.NullFormatter())
parser.feed(htmldata)
print '\n'.join(parser.anchorlist)
parser.close()