iafa2soif.c

harvest是一个下载html网页得机器人

static char rcsid[] = "iafa2soif.c,v 1.13 1996/01/05 20:28:18 duane Exp";
/*
 *  iafa2soif - Converts IAFA templates to SOIF.
 *
 *  Usage: iafa2soif url local-file
 *
 *  Darren Hardy, [e-mail], June 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 <stdlib.h>
#include <string.h>
#include "util.h"
#include "url.h"
#include "template.h"

static void usage()
{
	fprintf(stderr, "Usage: iafa2soif url local-file\n");
	exit(1);
}

#define isiafa(c)	(isalnum(c) || ((c) == '-') || ((c) == '#'))

static void do_iafatosoif(url, filename)
     char *url;
     char *filename;
{
	char buf[BUFSIZ], *s, *p;
	char attr[BUFSIZ];
	char value[BUFSIZ];
	int i;
	Template *t;
	FILE *fp;
	URL *up;

	if ((up = url_open(url)) == NULL) {
		errorlog("Cannot open URL: %s\n", url);
		return;
	}
	/* Build the template */
	t = create_template(NULL, up->url);

	/* Read the file and build a SOIF template from it */
	if ((fp = fopen(filename, "r")) == NULL) {
		log_errno(filename);
		url_close(up);
		return;
	}
	attr[0] = '\0';
	while (fgets(buf, BUFSIZ, fp)) {
		if ((s = strrchr(buf, '\n')) != NULL)
			*s = '\0';
		if (strlen(buf) < 1)
			continue;
		if ((s = strchr(buf, ':')) == NULL) {
			append_AVList(t->list, attr, buf, strlen(buf));
			continue;
		}
		for (p = buf, i = 0; p < s && isiafa(*p); p++, i++)
			attr[i] = *p;
		attr[i] = '\0';
		if (i < 1)
			continue;	/* null attribute */
		while (*s != '\0' && (*s == ':' || isspace(*s)))
			s++;
		if (strlen(s) < 1)	/* empty line */
			continue;
		strcpy(value, s);
		if (t->list)
			append_AVList(t->list, attr, value, strlen(value));
		else
			t->list = create_AVList(attr, value, strlen(value));

	}
	fclose(fp);

	/* Print out the template */
	(void) init_print_template(stdout);
	print_template(t);
	finish_print_template();
	free_template(t);
	url_close(up);
	return;
}

int main(argc, argv)
     int argc;
     char *argv[];
{
	char *url, *filename;

	if (argc != 3)
		usage();
	url = strdup(argv[1]);
	filename = strdup(argv[2]);

	init_log(stderr, stderr);
	init_url();
	do_iafatosoif(url, filename);
	finish_url();
	exit(0);
}