设为首页 加入收藏

TOP

c++爬虫大众点评数据
2017-01-04 08:14:51 】 浏览:103
Tags:爬虫 大众 点评 数据

#include < curl / curl.h >

#include < iostream >

#include < stdio.h >

#include < string.h >

#include < pcre.h >

#define OVECCOUNT 30
/* should be a multiple of 3 */

#define EBUFLEN 128

#define BUFLEN 10240

using namespacestd;

size_t onWriteData(void * buffer, size_t size, size_t nmemb, void * str) {

    if (!str || !buffer) {

        return - 1;

    }

    string * result = (string * ) str;

    result - >append((char * ) buffer, size * nmemb);

    return nmemb;

}

//获取页面
int getWeb(string url, string & result)

{

    long code = 0;

    string htmlpage;

    CURL * curl = curl_easy_init();

    curl_easy_setopt(curl, CURLOPT_URL, url.c_str()); //设置url
    curl_easy_setopt(curl, CURLOPT_POST, 0); //设置请求方法
    curl_easy_setopt(curl, CURLOPT_USERAGENT, "Mozilla/5."); //伪装客户端
    curl_easy_setopt(curl, CURLOPT_WRITEDATA, &htmlpage); //设置接受返回结果字符串
    curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, onWriteData); //设置处理方法
    curl_easy_perform(curl); //请求
    curl_easy_getinfo(curl, CURLINFO_RESPONSE_CODE, &code);

    if (code == 200)

    {

        cout << "request success" << endl;

        result = htmlpage;

        //cout<)";

    printf("String : %s\n", src);

    printf("Pattern: \"%s\"\n", pattern);

    re = pcre_compile(pattern, 0, &error, &erroffset, NULL);

    if (re == NULL) {

        printf("PCRE compilation failed at offset %d: %s\n", erroffset, error);

        return1;

    }

    char * p = (char * ) src;

    while ((rc = pcre_exec(re, NULL, p, strlen(p), 0, 0, ovector, OVECCOUNT)) != PCRE_ERROR_NOMATCH)

    {

        printf("\nOK, %d matched ...\n\n", rc);

        for (i = 0; i < rc - 1; i++)

        {

            char * substring_start = p + ovector[2 * i];

            int substring_length = ovector[2 * i + 1] - ovector[2 * i];

            char matched[10240];

            memset(matched, 0, 10240);

            strncpy(matched, substring_start, substring_length);

            printf("match:%s\n", matched);

        }

        p += ovector[1];

        if (!p)

        {

            break;

        }

    }

    pcre_free(re);

    return0;

}
】【打印繁体】【投稿】【收藏】 【推荐】【举报】【评论】 【关闭】 【返回顶部
分享到: 
上一篇C++实现窗口显示在最前面的代码 下一篇C++项目目录组织结构

评论

帐  号: 密码: (新用户注册)
验 证 码:
表  情:
内  容:

最新文章

热门文章

C 语言

C++基础

windows编程基础

linux编程基础

C/C++面试题目