python实现网页链接提取的方法分享
程序员文章站
2023-10-20 22:58:10
复制代码 代码如下:#encoding:utf-8import socketimport htmllib,formatterdef open_socket(host,ser...
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()