find a random webserver using libcurl

Migrated from linuxjunk…

Compile with g++ code.cpp -lcurl -o randpages. Creates random IP addresses, then attempts to grab a page from http://IP using libcurl. Reports those that reply.

#include <iostream>
#include <string>
#include "stringify.h"
#include <curl/curl.h>
#include <stdlib.h>
#include <string.h>

using namespace std;

struct MemoryStruct {
  char *memory;
  size_t size;
};


static size_t
WriteMemoryCallback(void *ptr, size_t size, size_t nmemb, void *data)
{
  size_t realsize = size * nmemb;
  struct MemoryStruct *mem = (struct MemoryStruct *)data;

  mem->memory = (char *) realloc(mem->memory, mem->size + realsize + 1);
  if (mem->memory == NULL) {
    /* out of memory! */
    printf("not enough memory (realloc returned NULL)\n");
    exit(EXIT_FAILURE);
  }

  memcpy(&(mem->memory[mem->size]), ptr, realsize);
  mem->size += realsize;
  mem->memory[mem->size] = 0;

  return realsize;
}


string fetch_url(string url,bool &fail) {
 CURL *curl_handle;


  struct MemoryStruct chunk;

  chunk.memory =(char*) malloc(1);  /* will be grown as needed by the realloc above */
  chunk.size = 0;    /* no data at this point */

  curl_global_init(CURL_GLOBAL_ALL);

  /* init the curl session */
  curl_handle = curl_easy_init();
  curl_easy_setopt(curl_handle, CURLOPT_CONNECTTIMEOUT, 3);
  curl_easy_setopt(curl_handle, CURLOPT_TIMEOUT, 3);

  /* specify URL to get */
  curl_easy_setopt(curl_handle, CURLOPT_URL, url.c_str());

  /* send all data to this function  */
  curl_easy_setopt(curl_handle, CURLOPT_WRITEFUNCTION, WriteMemoryCallback);

  /* we pass our 'chunk' struct to the callback function */
  curl_easy_setopt(curl_handle, CURLOPT_WRITEDATA, (void *)&chunk);

  /* some servers don't like requests that are made without a user-agent
     field, so we provide one */
  curl_easy_setopt(curl_handle, CURLOPT_USERAGENT, "libcurl-agent/1.0");

  /* get it! */
  CURLcode res = curl_easy_perform(curl_handle);

  fail = false;
  if(res != 0) fail = true;
 // if(doc.size() == 0) fail = true;

  /* cleanup curl stuff */
  curl_easy_cleanup(curl_handle);

  /*
   * Now, our chunk.memory points to a memory block that is chunk.size
   * bytes big and contains the remote file.
   *
   * Do something nice with it!
   *
   * You should be aware of the fact that at this point we might have an
   * allocated data block, and nothing has yet deallocated that data. So when
   * you're done with it, you should free() it as a nice application.
   */
  //printf("%lu bytes retrieved\n", (long)chunk.size);

  string s = chunk.memory;
  if(chunk.memory)
    free(chunk.memory);

  /* we're done with libcurl, so clean it up */
  curl_global_cleanup();

  return s;
}

string rand_ip() {

  // anything but localhost please!
  int top = 127;
  for(;top==127;) top = rand()%256;


  string s = stringify(top) + "." + stringify(rand()%256) + "." + stringify(rand()%256) + "." + stringify(rand()%256);

  return s;
}

string rand_url(bool &fail) {

  string current_address;

  bool no_address = true;

  string ip = rand_ip();
  current_address = "http://" + ip;

  string doc = fetch_url(current_address,fail);

  return ip;
}
int main(int argc,char **argv) {

  size_t failed_connections = 0;
  size_t valid_connections  = 0;

  if(argc < 1) cout << "randpages <random seed>" << endl;

  srand(time(NULL) + convertTo<int>(argv[1]));

  for(;;) {
    bool fail = true;
    string url = rand_url(fail);

    if(fail) { failed_connections++; } else { valid_connections++; }

    if(!fail) cout << url << " " << valid_connections << " " << failed_connections << endl;
  }
}