Python爬虫(九)
学习Python爬虫过程中的心得体会以及知识点的整理,方便我自己查找,也希望可以和大家一起交流。
—— socket库详解及实践相关代码 ——
文章目录
1.socket库应用详解
#coding:utf-8
import socket
#返回主机名
socket.gethostname()
#将host主机名转换为ipv4地址
socket.gethostbyname('edu.aqniu.com')
socket.gethostbyname('www.jd.com')
#功能扩展的gethostbyname函数,返回主机名、主机别名列表、主机IP地址列表
socket.gethostbyname_ex('edu.aqniu.com')
socket.gethostbyname_ex('www.jd.com')
#通过ip地址,返回包括主机名的三元组:(hostname, aliaslist, ipaddrlist)
socket.gethostbyaddr("180.76.136.71")
socket.gethostbyaddr('202.165.102.205')
socket.gethostbyaddr('192.168.99.110')
#返回该端口号的服务名
socket.getservbyport(80, 'tcp')
#通过给定的服务名,协议名,返回该服务所在的端口号
socket.getservbyname('http', 'tcp')
#返回一个包含5元组的list,用来获得host的地址信息
socket.getaddrinfo('edu.aqniu.com',80)
socket.getprotobyname("tcp")
"""
socket = socket.socket( family, type )
family参数代表地址家族,可为AF_INET或AF_UNIX。AF_INET家族包括Internet地址,AF_UNIX家族用于同一台机器上的进程间通信。
socket.AF_INET指的是IPv4,socket.AF_INET6指的是IPv6。
type表示套接字类型,socket.SOCK_STREAM指的是TCP连接,socket.SOCK_DGRAM指的是UDP协议
"""
socket.socket(socket.AF_INET, socket.SOCK_STREAM)
sock.connect(('edu.aqniu.com', 80))
#返回socket超时时间,以秒计(float)
socket.gettimeout()
#设置Socket超时时间,以秒计(float)
socket.settimeout(timeout)
2.socket库实践
【1】基于TCP协议
(1)模拟服务端
#coding:utf-8
import socket
s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
host = socket.gethostname()
port = 1234
s.bind((host, port))
s.listen(5) #参数就是等待连接队列中所能包含的连接数,多余的就直接拒绝
while True:
connection, address = s.accept()
print ('Got connection from', address)
#connection.settimeout(5)
buf = connection.recv(1024)
str1 ='Thank you for connecting'
str1 = str1.encode()
str2 ='Go away!'
str2 = str2.encode()
str3 ='1'
str3 = str3.encode()
if buf == str3:
connection.send(str1)
else:
connection.send(str2)
connection.close()
s.close()
(2)模拟客户端访问服务端
#coding:utf-8
import socket
import time
s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
host = socket.gethostname()
port = 1234
s.connect((host, port))
str01 = '1'
str01 = str01.encode()
time.sleep(1)
s.send(str01)
print (s.recv(1024))
s.close()
【2】基于UDP协议
(1)模拟服务端
#coding:utf-8
import socket
s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
host = socket.gethostname()
port = 1234
s.bind((host, port))
#s.listen(5) #UDP不需要三次握手,不需要listen和accept
while True:
recv,client_addr = s.recvfrom(1024)
if not recv:
break
print('[Client %s:%s said]:%s' % (client_addr[0],client_addr[1],recv))
str1 ='tcpServer has received your message'
str1 = str1.encode()
s.sendto(str1,client_addr)
(2)模拟客户端访问服务端
#coding:utf-8
import socket
import time
s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
host = socket.gethostname()
port = 1234
s.connect((host, port))
str01 = '1'
str01 = str01.encode()
time.sleep(1)
s.send(str01)
print (s.recv(1024))
s.close()