Get only the text from a webpage

web_scraper.cpp

//Code that scrapes webpages

#include <stdio.h>
#include <stdlib.h>
#include <iostream>
#include <string>
#include <fstream>
using namespace std;

string url;
ifstream file;
string line;
int n;

const int array_size = 99999;
string array_in[array_size];
string array_out[array_size];

int i;
int j;
ofstream text;

int command(string input)
{
    system ( (input).c_str() );
    return 0;
}

int main(int argc, char **argv)
{
   if (argc < 2) { cout << "Too few arguments" << '\n'; exit(1); }
   if (argc > 2) { cout << "Too many arguments" << '\n'; exit(1); }
   
   url = argv[1];

   command("curl -k " + url + " -o scrape.html");
   command("tidy -q -asxml --numeric-entities yes scrape.html >scrape.xml 2>/dev/null");
   command("rm scrape.html");

   file.open("scrape.xml");
   n = 0;
   while ( getline(file, line) )
   {
      array_in[n] = line;
      n++;
   }
   file.close();
   command("rm scrape.xml");

   bool toggle = false;
   for ( i=0; i < n; i++ )
   {
      array_out[i] = "";
      for ( j=0; j < array_in[i].length(); j++ )
      {
         if (array_in[i].at(j) == '<')
         {
            toggle = false;
         }
         if (toggle)
         {
            array_out[i] += array_in[i].at(j);
         }
         if (array_in[i].at(j) == '>')
         {
            toggle = true;
         }
      }

      if (i == array_size-1)
      {
         cout << "Array ran out of space" << '\n';
      }
   }

   text.open("scrape.txt");
   for ( i=0; i < sizeof(array_out)/sizeof(*array_out); i++)
   {
      if (array_out[i] != "")
      {
         text << array_out[i] << '\n';
      }
   }
   text.close();

   return 0;
}