extractdb.c

harvest是一个下载html网页得机器人

static char rcsid[] = "extractdb.c,v 1.15 1996/01/04 03:46:43 duane Exp";
/*
 *  extractdb.c - Extracts the named field from each template.
 *
 *  Usage: extractdb db attribute
 *
 *  Darren Hardy, [e-mail], May 1994
 *
 *  ----------------------------------------------------------------------
 *  Copyright (c) 1994, 1995.  All rights reserved.
 *  
 *    The Harvest software was developed by the Internet Research Task
 *    Force Research Group on Resource Discovery (IRTF-RD):
 *  
 *          Mic Bowman of Transarc Corporation.
 *          Peter Danzig of the University of Southern California.
 *          Darren R. Hardy of the University of Colorado at Boulder.
 *          Udi Manber of the University of Arizona.
 *          Michael F. Schwartz of the University of Colorado at Boulder.
 *          Duane Wessels of the University of Colorado at Boulder.
 *  
 *    This copyright notice applies to software in the Harvest
 *    ``src/'' directory only.  Users should consult the individual
 *    copyright notices in the ``components/'' subdirectories for
 *    copyright information about other software bundled with the
 *    Harvest source code distribution.
 *  
 *  TERMS OF USE
 *    
 *    The Harvest software may be used and re-distributed without
 *    charge, provided that the software origin and research team are
 *    cited in any use of the system.  Most commonly this is
 *    accomplished by including a link to the Harvest Home Page
 *    (http://harvest.cs.colorado.edu/) from the query page of any
 *    Broker you deploy, as well as in the query result pages.  These
 *    links are generated automatically by the standard Broker
 *    software distribution.
 *    
 *    The Harvest software is provided ``as is'', without express or
 *    implied warranty, and with no support nor obligation to assist
 *    in its use, correction, modification or enhancement.  We assume
 *    no liability with respect to the infringement of copyrights,
 *    trade secrets, or any patents, and are not responsible for
 *    consequential damages.  Proper use of the Harvest software is
 *    entirely the responsibility of the user.
 *  
 *  DERIVATIVE WORKS
 *  
 *    Users may make derivative works from the Harvest software, subject 
 *    to the following constraints:
 *  
 *      - You must include the above copyright notice and these 
 *        accompanying paragraphs in all forms of derivative works, 
 *        and any documentation and other materials related to such 
 *        distribution and use acknowledge that the software was 
 *        developed at the above institutions.
 *  
 *      - You must notify IRTF-RD regarding your distribution of 
 *        the derivative work.
 *  
 *      - You must clearly notify users that your are distributing 
 *        a modified version and not the original Harvest software.
 *  
 *      - Any derivative product is also subject to these copyright 
 *        and use restrictions.
 *  
 *    Note that the Harvest software is NOT in the public domain.  We
 *    retain copyright, as specified above.
 *  
 *  HISTORY OF FREE SOFTWARE STATUS
 *  
 *    Originally we required sites to license the software in cases
 *    where they were going to build commercial products/services
 *    around Harvest.  In June 1995 we changed this policy.  We now
 *    allow people to use the core Harvest software (the code found in
 *    the Harvest ``src/'' directory) for free.  We made this change
 *    in the interest of encouraging the widest possible deployment of
 *    the technology.  The Harvest software is really a reference
 *    implementation of a set of protocols and formats, some of which
 *    we intend to standardize.  We encourage commercial
 *    re-implementations of code complying to this set of standards.  
 *  
 */
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <gdbm.h>
#include "util.h"
#include "url.h"
#include "template.h"

/* Local functions */
static void usage();

static void usage()
{
	fprintf(stderr, "Usage: extractdb db attribute\n");
	exit(1);
}

int main(argc, argv)
     int argc;
     char *argv[];
{
	datum d, k, nk;
	GDBM_FILE dbf;
	Template *t;
	AVPair *avp;

	if (argc != 3)
		usage();

	if ((dbf = gdbm_open(argv[1], 0, GDBM_READER, 0644, NULL)) == NULL) {
		usage();
	}
	k = gdbm_firstkey(dbf);
	while (k.dptr) {
		nk = gdbm_nextkey(dbf, k);
		d = gdbm_fetch(dbf, k);

		init_parse_template_string(d.dptr, d.dsize);
		t = parse_template();
		finish_parse_template();
		if (t != NULL) {
			avp = extract_AVPair(t->list, argv[2]);
			if (avp != NULL) {
				printf("%s\t", t->url);
				fwrite(avp->value, 1, avp->vsize, stdout);
				putchar('\n');
				fflush(stdout);
			}
			free_template(t);
		}
		free(k.dptr);
		free(d.dptr);
		k = nk;
	}
	exit(0);
}