Question

I would like to search for every IP address in a curl output. Is there a quick way to do so? I know about regex_search from boost, but from what I read, it is targeted for files.

My actual non-working code:

#include <iostream>
#include <curl/curl.h>
#include <boost/regex.hpp>

using namespace std;

boost::regex expression("\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}");
boost::smatch what;  // "match" specialized for std::string of char
boost::match_flag_type flags = boost::match_default;

string buffer = "hey";

int writer(char *data, size_t size, size_t nmemb, string *buffer){
    int result = 0;
    if(buffer != NULL) {
        buffer -> append(data, size * nmemb);
        result = size * nmemb;
    }
    return result;
} 

int main(int argc, char *argv[]) {
    CURL *curl;
    CURLcode res;

    curl = curl_easy_init();

    if(curl) {
        curl_easy_setopt(curl, CURLOPT_URL, "http://www.xroxy.com/proxylist.php");
        curl_easy_setopt(curl, CURLOPT_FOLLOWLOCATION, 0); /* Don't follow anything else than the particular url requested*/
        curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, writer); /* Function Pointer "writer" manages the required buffer size */
        curl_easy_setopt(curl, CURLOPT_WRITEDATA, &buffer ); /* Data Pointer &buffer stores downloaded web content */       
        curl_easy_perform(curl);
        /* always cleanup */ 
        curl_easy_cleanup(curl);
    }

    if (boost::regex_search(buffer.begin(), buffer.end(), what, expression, flags) ) {
        cout << "found: " << what << endl;
    }
    return 0;
}

Answer 1

regex_search from boost, but from what I read, it is targeted for files.

Are you sure? From what I see here:
http://www.boost.org/doc/libs/1_45_0/libs/regex/doc/html/boost_regex/ref/regex_search.html

Determines whether there is some sub-sequence within [first,last) that matches the regular expression e, parameter flags is used to control how the expression is matched against the character sequence. Returns true if such a sequence exists, false otherwise.

Am I missing something here?

Anyway, another option would be to filter curl’s output through grep.