linux c++模拟简易网络爬虫

/*
* To change this license header, choose License Headers in Project Properties.
* To change this template file, choose Tools | Templates
* and open the template in the editor.
*/

/*
* File: main.cpp
* Author: yangchao
*
* Created on 2017年6月4日, 下午3:00
*/

#include <iostream>
#include <string>
#include <netdb.h>
#include <string.h>
#include <stdlib.h>

using namespace std;

void parseHostAndPagePath(const string url,string &hostUrl,string &pagePath){
hostUrl=url;
pagePath="/";
int pos=hostUrl.find("http://");
if(-1!=pos)
hostUrl=hostUrl.replace(pos,7,"");
pos=hostUrl.find("https://");
if(-1!=pos)
hostUrl=hostUrl.replace(pos,8,"");
pos=hostUrl.find("/");
if(-1!=pos)
{
pagePath=hostUrl.substr(pos);
hostUrl=hostUrl.substr(0,pos);
}
}

string getPageContent(const string url){
struct hostent *host;
string hostUrl,pagePath;
parseHostAndPagePath(url,hostUrl,pagePath);
if(0==(host=gethostbyname(hostUrl.c_str())))
{
cout<<"gethostbyname error\n"<<endl;
exit(1);
}
struct sockaddr_in pin;
int port=80;
bzero(&pin,sizeof(pin));
pin.sin_family=AF_INET;
pin.sin_port=htons(port);
pin.sin_addr.s_addr=((struct in_addr*)(host->h_addr))->s_addr;
int isock;
if((isock=socket(AF_INET,SOCK_STREAM,0))==-1)
{
cout<<"open socket error\n"<<endl;
exit(1);
}
string requestHeader;
requestHeader="GET "+pagePath+" HTTP/1.1\r\n";
requestHeader+="Host: "+hostUrl+"\r\n";
requestHeader+="Accept: */*\r\n";
requestHeader+="User-Agent: Mozilla/4.0(compatible)\r\n";
requestHeader+="connection:Keep-Alive\r\n";
requestHeader+="\r\n";
if(connect(isock,(const sockaddr*)&pin,sizeof(pin))==-1){
cout<<"connect error\n"<<endl;
exit(1);
}
if(send(isock,requestHeader.c_str(),requestHeader.size(),0)==-1){
cout<<"send error\n"<<endl;
exit(1);
}
struct timeval timeout={1,0};
setsockopt(isock,SOL_SOCKET,SO_RCVTIMEO,(char*)&timeout,sizeof(struct timeval));
char c;
bool flag=true;
while(recv(isock,&c,1,0)>0){
if('\r'==c){
continue;
}else if('\n'==c){
if(false==flag)
break;
flag=false;
}else{
flag=true;
}
}
int len,BUFFER_SIZE=512;
char buffer[BUFFER_SIZE];
string pageContent="";
while((len=recv(isock,buffer,BUFFER_SIZE-1,0))>0){
buffer[len]='\0';
pageContent+=buffer;
}
return pageContent;
}

int main(int argc, char** argv) {
cout<<getPageContent("http://www.hao123.com")<<endl;
return 0;
}

 

转载于:https://www.cnblogs.com/daochong/p/6940910.html

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值