codegolf.stackexchange.com/a/44592

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/socket.h>
#include <netdb.h>
#include <regex.h>

#define SZ 1024 //good default buffer size
#define ERROR(s) (puts(s)&&0)
#define VERROR(s) ((void*)(long)ERROR(s))

main()
{
  char* SITE = "www.stroustrup.com";
  char* PAGE = "C++.html";
  char* REGX = "((http://)?www([./#\\+-]\\w*)+)";
  int s = connect_to(SITE);
  FILE* f = fetch_page(s,SITE,PAGE);
  if (f)
    list_matches(f,REGX);
  else
    return printf("Can't fetch page %s/%s\n", SITE, PAGE);
  fclose(f);
  close(s);
}

int connect_to(char* w)
{
  // returns socket connected to website w.
  int s = socket(AF_INET, SOCK_STREAM, 0);
  // lookup host; address = port 80 of ipaddr; connect
  struct hostent* h = gethostbyname(w);
  if (!h)
    return ERROR("No Such Host");
  struct sockaddr_in a;
  a.sin_port = htons(80);
  a.sin_family = AF_INET;
  memcpy(&a.sin_addr.s_addr, h->h_addr, h->h_length);
  if (connect(s, (struct sockaddr*)&a, sizeof(a)) < 0)
    return ERROR("can't connect");
  else
    return s;
}

FILE* fetch_page(int s, char*w, char* p)
{
  // returns open file handle for page p from site w connected to socket s
  // create cache file; allocate buffer; check for errors; compose request
  FILE*f = fopen("/tmp/wcache", "w+");
  size_t n;
  char* b = malloc(SZ);
  if (!s || !f || !b)
    return VERROR("Resource Error");
  sprintf(b, "GET / HTTP/1.0\r\nHost:%s\r\nAccept:*/*\r\nConnection:close\r\n\r\n", w);
  // send request; receive request; write to cache file
  send(s, b, strlen(b), 0);
  while ((n = recv(s, b, SZ, 0)) > 0)
    fwrite(b, 1, n, f);
  n = 0;
  fseek(f, n, SEEK_SET);
  fgets(b,SZ,f); // read cached page, check response is OK
  if (!f || strncmp(b, "HTTP/", 5))
    return VERROR("Invalid Response");
  if (strtok(b, " ") && atoi(strtok(0, " ")) != 200)
    return VERROR("Bad Status Code");
  while (getline(&b, &n, f)>=0 && *b!='\r'); // discard headers upto blank line
  free(b);
  return f;
}

void list_matches(FILE* f, char* regx)
{
  //prints all strings from f which match regx
  regex_t r;
  size_t n = SZ;
  char* b = malloc(n);
  if (regcomp(&r, regx, REG_NOSUB | REG_EXTENDED))
    puts("invalid regex");
  else {
    while (getline(&b, &n, f) > 0) {
      if (!regexec(&r, b, 0, 0, 0))
        puts(b);
    }
  }
  regfree(&r);
  free(b);
}