Get only the text from a webpage

web_scraper.c

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <stdbool.h>

#define SIZE 999999
#define WORD 255

int n;
int m;
int i;
int j;
long fsize;

int command(char input[WORD])
{
    system(input);
    return 0;
}

int main(int argc, char **argv)
{
    char **array_in;
    char **array_out;
    array_in = (char **)malloc(sizeof(char *)*SIZE);
    array_out = (char **)malloc(sizeof(char *)*SIZE);
    for(i = 0; i < SIZE; i++)
    {
        array_in[i] = (char *)malloc(sizeof(char)*WORD);
        array_out[i] = (char *)malloc(sizeof(char)*WORD);
    }
    
    char temp[WORD];
    
    FILE * file;
    FILE * text;
    
    if (argc > 2) { printf("Too many arguments\n"); exit(1); }
    
    strcpy(temp, "curl -k "); strcat(temp, argv[1]); strcat(temp, " -o scrape.html");
    command( temp );
    command("tidy -q -asxml --numeric-entities yes scrape.html >scrape.xml");
    command("rm scrape.html");
    
    file = fopen("scrape.xml", "r");
    n = 0;
    while( fgets(array_in[n], WORD, (FILE*)file) ){ n++; }
    fclose(file);
    command("rm scrape.xml");
    
    bool toggle = false;
    for (i = 0; i < n; i++)
    {
        m = 0;
        for (j = 0; j < WORD; j++)
        {
            if (array_in[i][j] == '<')
            {
                toggle = false;
            }
            if (toggle)
            {
                array_out[i][m] = array_in[i][j];
                m++;
            }
            if (array_in[i][j] == '>')
            {
                toggle = true;
            }
        }
        
        if (i == SIZE-1)
        {
            printf("Array ran out of space\n");
        }
    }
    
    text = fopen("scrape.txt", "w");
    for (i = 0; i < SIZE; i++)
    {
        if ( (array_out[i][0] != '\n') && (array_out[i][0] != '\0') )
        {
            fprintf(text, "%s", array_out[i]);
        }
    }
    fclose(text);
    
    free(array_in);
    free(array_out);
    return 0;
}