关于从网页上下载数据

#include "curl/curl.h"  

#include <io.h> 
#include <direct.h>  
#include <stdio.h>
#include <string>
#include <fstream>
#include <stdlib.h> 

#pragma comment(lib, "libcurl.lib")   
#pragma comment(lib, "wldap32.lib")   
#pragma comment(lib, "ws2_32.lib")   
#pragma comment(lib, "winmm.lib")   

size_t write_func(void *ptr, size_t size, size_t nmemb, FILE *stream)
{
    return fwrite(ptr, size, nmemb, stream);
}


std::string analyze_name;
std::string analyze_url;
std::string cplocation;
std::string httpurl;

//得到每条链接的短地址和名字
void get_name_url(std::string line)
{
    //File d;
    char *linkhead = "<a href=";
    char *linkmiddle = """;
    char *linktail = "</a>";
    std::string head = "<a href=";

    char *s = strstr((char*)line.data(), linkhead);
    for (int i = 0; i<9; i++)
        *s++;
    int urloffset = 0;
    while (*s != *linkmiddle)
    {
        *s++;
        urloffset++;
    }
    analyze_url = line.substr(line.find(head) + 9, urloffset);
    for (int i = 0; i<2; i++)
        *s++;
    int nameoffset = 0;
    while (*s != *linktail)
    {
        *s++;
        nameoffset++;
    }
    analyze_name = line.substr(line.find(head) + 11 + urloffset, nameoffset);

    //return d;
}

//根据http网址下载网页到本机指定位置
int http_get(std::string httpurl, std::string location)
{
    CURL *curl;
    CURLcode res;
    FILE *outfile;
    errno_t err;
    err = fopen_s(&outfile, location.c_str(), "wb");
    //outfile = fopen(location.c_str(), "wb");
    const char *url = httpurl.c_str();
    curl = curl_easy_init();
    if (curl)
    {
        curl_easy_setopt(curl, CURLOPT_URL, url);
        curl_easy_setopt(curl, CURLOPT_WRITEDATA, outfile);
        curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, write_func);
        res = curl_easy_perform(curl);
        fclose(outfile);
        curl_easy_cleanup(curl);
    }
    return 0;
}


int linkextract(std::string httpfile, std::string httpurl, std::string cplocation)
{
    std::ifstream infile;
    std::string line, link, name;
    infile.open(httpfile, std::ios::in);
    std::string directory = "alt="[DIR]"";
    std::string file = "alt="[   ]"";

    while (!infile.eof())
    {
        getline(infile, line, '
');
        //if (line.find(directory) != -1)//目录
        //{
        //    get_name_url(line);
        //    analyze_name = analyze_name.substr(0, analyze_name.length() - 1);
        //    std::string content = cplocation + "/" + analyze_name;
        //    _mkdir((char*)content.c_str());
        //    httpurl = httpurl + analyze_url;
        //    cplocation = cplocation + "/" + analyze_name;
        //    http_get(httpurl, cplocation + "/" + analyze_name + ".txt");
        //    linkextract(cplocation + "/" + analyze_name + ".txt", httpurl, cplocation);
        //}
        //else if (line.find(file) != -1)//文件
        {
            //get_name_url(line);
            if (line.find("href="Tile")==-1)
                continue;

            char *linkhead = "<a href=";
            char *linkmiddle = """;
            char *linktail = "</a>";
            std::string head = "<a href=";

            char *s = strstr((char*)line.data(), linkhead);
            for (int i = 0; i<9; i++)
                *s++;
            int urloffset = 0;
            while (*s != *linkmiddle)
            {
                *s++;
                urloffset++;
            }
            analyze_url = line.substr(line.find(head) + 9, urloffset);
            for (int i = 0; i<2; i++)
                *s++;
            int nameoffset = 0;
            while (*s != *linktail)
            {
                *s++;
                nameoffset++;
            }
            analyze_name = line.substr(line.find(head) + 11 + urloffset, nameoffset);


            http_get(httpurl + analyze_url, cplocation + "/" + analyze_name);
        }
        /*else
            continue;*/
    }
    infile.close();

    return 0;
}




int main()
{
    std::string httpurl = "http://服务地址";
    std::string content = "../DownloadDirectory";
    _mkdir((char*)content.c_str());
    std::string localdir = "../DownloadDirectory/DownloadDirectory.txt";
    http_get(httpurl, localdir);
    linkextract(localdir, httpurl, content);
    return 0;
}

只能下载href里面的链接文件，而且很多网页不能下载；

其中，需要下载curl并配置路径，关于下载编译curl有很好的博客，暂时找不见了；