Linux Question

How can i strip the HTML from document between and including the <…> tags in a HTML document using C? My current program uses curl to get the contents of the webpage and puts it into a text file, it then reads from the text file and removes the <>, but i am unsure of how to remove everything between those tags.

#include <curl/curl.h>
#include <stdio.h>
#include <stdlib.h>
#include <fcntl.h>
#include <unistd.h>

#define WEBPAGE_URL "http://homepages.paradise.net.nz/adrianfu/index.html"
#define DESTINATION_FILE "/home/user/data.txt"

size_t write_data( void *ptr, size_t size, size_t nmeb, void *stream)
{
 return fwrite(ptr,size,nmeb,stream);
}

int main()
{
 int in_tag = 0;
 char * buffer;
 char c;
 long lSize;
 size_t result;

 FILE * file = fopen(DESTINATION_FILE,"w+");
 if (file==NULL) {
    fputs ("File error",stderr); 
    exit (1);
    }

 CURL *handle = curl_easy_init();
 curl_easy_setopt(handle,CURLOPT_URL,WEBPAGE_URL); /*Using the http protocol*/
 curl_easy_setopt(handle,CURLOPT_WRITEFUNCTION, write_data);
 curl_easy_setopt(handle,CURLOPT_WRITEDATA, file);
 curl_easy_perform(handle);
 curl_easy_cleanup(handle);

  int i, nRead, fd;
    int source;
    char buf[1024];


    if((fd = open("data.txt", O_RDONLY)) == -1)
    {
        printf("Cannot open the file");
    }
    else
    {
        nRead = read(fd, buf, 1024);
        printf("Original String ");
        for(i=0; i<nRead; i++)
        {
                printf("%c", buf[i]);
        }

        printf("nReplaced String ");

        for(i=0; i<nRead; i++)
        {
            if(buf[i]=='<' || buf[i]=='>'){
            buf[i]=' ';

            }
            printf("%c", buf[i]);
        }
    }
    close(source);

 return 0;
 }

JavaScript
​x
 
#include <curl/curl.h>#include <stdio.h>#include <stdlib.h>#include <fcntl.h>#include <unistd.h>​#define WEBPAGE_URL "http://homepages.paradise.net.nz/adrianfu/index.html"#define DESTINATION_FILE "/home/user/data.txt"​size_t write_data( void *ptr, size_t size, size_t nmeb, void *stream){ return fwrite(ptr,size,nmeb,stream);}​int main(){ int in_tag = 0; char * buffer; char c; long lSize; size_t result;​ FILE * file = fopen(DESTINATION_FILE,"w+"); if (file==NULL) {    fputs ("File error",stderr);     exit (1);    }​ CURL *handle = curl_easy_init(); curl_easy_setopt(handle,CURLOPT_URL,WEBPAGE_URL); /*Using the http protocol*/ curl_easy_setopt(handle,CURLOPT_WRITEFUNCTION, write_data); curl_easy_setopt(handle,CURLOPT_WRITEDATA, file); curl_easy_perform(handle); curl_easy_cleanup(handle);​  int i, nRead, fd;    int source;    char buf[1024];​​    if((fd = open("data.txt", O_RDONLY)) == -1)    {        printf("Cannot open the file");    }    else    {        nRead = read(fd, buf, 1024);        printf("Original String ");        for(i=0; i<nRead; i++)        {                printf("%c", buf[i]);        }​        printf("nReplaced String ");​        for(i=0; i<nRead; i++)        {            if(buf[i]=='<' || buf[i]=='>'){            buf[i]=' ';​            }            printf("%c", buf[i]);        }    }    close(source);​ return 0; }​

Answer

Placing just the code that removes the contents between the ‘<‘ and ‘>’ tags (assuming that you deal with proper html, meaning that you don’t have one tag nested in the declaration of the other like <html < body> >). I am just changing a small portion of your code. I will also remove the tags from the buf variable, instead of replacing the undesired characters with intervals, because I think this will be more useful to you (correct me if I am wrong).

int idx = 0;
int opened = 0; // false
for(i=0; i<nRead; i++)
{
    if(buf[i]=='<') {
        opened = 1; // true
    } else if (buf[i] == '>') {
        opened = 0; // false
    } else if (!opened) {
        buf[idx++] = buf[i];
    }
}
buf[idx] = '';
printf("%sn", buf);

JavaScript
 
int idx = 0;int opened = 0; // falsefor(i=0; i<nRead; i++){    if(buf[i]=='<') {        opened = 1; // true    } else if (buf[i] == '>') {        opened = 0; // false    } else if (!opened) {        buf[idx++] = buf[i];    }}buf[idx] = '';printf("%sn", buf);​

C strip html between

Advertisement

Answer