c语言代码中使用HTTP代理IP爬虫，示例代码demo如何使用 ...

开着宝马看夕阳

示例代码demo的原理就是，打开API链接，提取里面的IP，使用IP访问目标网站，然后加一些判断有利于程序稳定运行，也可以一次提取多个IP，多线程调用效率提升百倍。如果你是初次接触HTTP的话可以手动操作试下，把API复制粘贴到浏览器里面打开，就可以看到IP端口了。

// demo.cpp : 定义控制台应用程序的入口点。
//
#include "stdafx.h"
#include "curl/curl.h"
#include <stdio.h>
#include <stdlib.h>
#pragma comment(lib, "libcurl.lib")
static size_t write_buff_data(char *buffer, size_t size, size_t nitems, void *outstream)
{
memcpy(outstream, buffer, nitems*size);
return nitems*size;
}
/*
使用http代理
*/
int GetUrlHTTP(char *url, char *buff, char* ip)
{
CURL *curl;
CURLcode res;
curl = curl_easy_init();
if (curl)
{
curl_easy_setopt(curl, CURLOPT_PROXY, ip); //代理方式 http://ip:port
curl_easy_setopt(curl, CURLOPT_WRITEDATA, (void*)buff);//获得访问结果
curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, write_buff_data);
curl_easy_setopt(curl, CURLOPT_URL, url);
curl_easy_setopt(curl, CURLOPT_LOW_SPEED_TIME, 10L);
curl_easy_setopt(curl, CURLOPT_LOW_SPEED_LIMIT, 50L);
curl_easy_setopt(curl, CURLOPT_MAX_RECV_SPEED_LARGE, 2000000L);/*下载最高速度*/
res = curl_easy_perform(curl);
curl_easy_cleanup(curl);
if (res == CURLE_OK) {
return res;
}
else {
printf("错误代码:%d\n", res);
MessageBox(NULL, TEXT("获取IP错误"), TEXT("助手"), MB_ICONINFORMATION | MB_YESNO);
}
}
return res;
}
//不使用代理
int GetUrl(char *url, char *buff)
{
CURL *curl;
CURLcode res;
curl = curl_easy_init();
if (curl)
{
curl_easy_setopt(curl, CURLOPT_WRITEDATA, (void*)buff);
curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, write_buff_data);
curl_easy_setopt(curl, CURLOPT_URL, url);/*访问url*/
curl_easy_setopt(curl, CURLOPT_LOW_SPEED_TIME, 10L);
curl_easy_setopt(curl, CURLOPT_LOW_SPEED_LIMIT, 50L);
curl_easy_setopt(curl, CURLOPT_MAX_RECV_SPEED_LARGE, 2000000L);/*下载最高速度*/
res = curl_easy_perform(curl);
curl_easy_cleanup(curl);
if (res == CURLE_OK)
{
return res;
}
else {
printf("错误代码:%d\n", res);
MessageBox(NULL, TEXT("获取IP错误"), TEXT("助手"), MB_ICONINFORMATION | MB_YESNO);
}
}
return res;
}
//将utf-8转为gbk格式
void utf8ToGbk(char *utf8String, char *gbkString)
{
wchar_t *unicodeStr = NULL;
int nRetLen = 0;
nRetLen = MultiByteToWideChar(CP_UTF8, 0, utf8String, -1, NULL, 0);//求需求的宽字符数大小
unicodeStr = (wchar_t *)malloc(nRetLen * sizeof(wchar_t));
nRetLen = MultiByteToWideChar(CP_UTF8, 0, utf8String, -1, unicodeStr, nRetLen);//将utf-8编码转换成unicode编码
nRetLen = WideCharToMultiByte(CP_ACP, 0, unicodeStr, -1, NULL, 0, NULL, 0);//求转换所需字节数
nRetLen = WideCharToMultiByte(CP_ACP, 0, unicodeStr, -1, gbkString, nRetLen, NULL, 0);//unicode编码转换成gbk编码
free(unicodeStr);
}
int main()
{
char *buff = (char*)malloc(1024 * 1024);
memset(buff, 0, 1024 * 1024);
//代理api（这里http://www.9vps.com/?28890注册就白嫖1万IP）
GetUrl("http://http.9vps.com/getip.asp?username=166xxxx6597&pwd=xxxxbaa59ce237dff65134984b9cxxxx&geshi=1&fenge=1&fengefu=&Contenttype=1&getnum=20&setcity=&operate=all&", buff);
printf("代理IP列表:\n%s", buff); //输出
//输入代理IP
char ip[100];
printf("\nEnter your IP:");
scanf_s("%s", &ip, 100);
//使用代理IP访问网站
memset(buff, 0, 1024 * 1024);
GetUrlHTTP("http://myip.top", buff, (char*)ip);
utf8ToGbk(buff, buff);//将获取到的网页内容转为gbk格式
printf("\nhttp结果：%s\n", buff);//输出访问结果
//不使用代理访问
GetUrl("http://myip.top", buff);
utf8ToGbk(buff, buff); // 将获取到的网页内容转为gbk格式
printf("不使用代理：%s \n", buff);//输出访问结果
Sleep(1000 * 1000);
free(buff);
return 0;
完整原版代码文件可以点击获取：http://www.9vps.com/?28890获取。

故事伴酒

路过的帮顶