news.c

harvest是一个下载html网页得机器人

static char rcsid[] = "news.c,v 1.13 1996/01/05 20:28:27 duane Exp";
/*
 *  news.c - Retrieves USENET articles
 *
 *  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 <unistd.h>
#include <sys/ioctl.h>
#include "util.h"
#include "url.h"

#if HOLD_NNTP
int nntp_sock = -1;
#define NNTP_PORT 119
#endif

static int open_nntp_sock _PARAMS((void));

/*
 *  news_get() - retrieves the URL and prints into the file up->fp.
 *  Returns non-zero on error; 0 on success.
 */
int news_get(up)
     URL *up;
{
	static char cmd[BUFSIZ];
	long nbytes;
	char *buf = NULL;
	int rc;

#if HOLD_NNTP
	if (nntp_sock == -1)
		nntp_sock = open_nntp_sock();
	if (nntp_sock != (-1)) {
#ifdef FIONREAD
		/* drain the socket of any leftover data */
		buf = (char *) xmalloc(BUFSIZ);
		do {
			nbytes = 0;
			ioctl(nntp_sock, FIONREAD, (caddr_t) & nbytes);
			read(nntp_sock, buf, nbytes > BUFSIZ ? BUFSIZ : nbytes);
#ifdef HAVE_USLEEP
			usleep(500000);
#endif /* HAVE_USLEEP */
		} while (nbytes > 0);
		xfree(buf);
#endif /* FIONREAD */
		sprintf(cmd, "newsget.pl -fd %d \"%s\" \"%s\"",
		    nntp_sock,
		    up->filename,
		    up->url);
	} else
#endif /* HOLD_NNTP */
		sprintf(cmd, "newsget.pl \"%s\" \"%s\"",
		    up->filename,
		    up->url);
	rc = run_cmd(cmd);
#if HOLD_NNTP
	if (rc < 0) {		/* exited due to signal */
		close(nntp_sock);
		nntp_sock = -1;
	}
#endif /* HOLD_NNTP */
	return rc;
}

static int open_nntp_sock()
{
	char *nntpserver;
	struct sockaddr_in sa;
	struct hostent *h;
	int len;
	char c;
	int sock = -1;

	nntpserver = getenv("NNTPSERVER");
	if (nntpserver == NULL)
		nntpserver = "news";
	if ((h = gethostbyname(nntpserver)) == 0) {
		errorlog("Unknown host: %s\n", nntpserver);
		exit(1);
	}
	Log("Opening NNTP connection to %s\n", nntpserver);
	sock = socket(AF_INET, SOCK_STREAM, 0);
	if (sock < 0) {
		log_errno("socket");
		exit(1);
	}
	sa.sin_family = AF_INET;
	sa.sin_port = htons(NNTP_PORT);
	memcpy((char *) &sa.sin_addr, *(h->h_addr_list), h->h_length);
	/*sa.sin_addr  = inet_addr (inet_ntoa (*(h->h_addr_list))); */
	len = sizeof(sa);
	if (connect(sock, (struct sockaddr *) &sa, len) < 0) {
		log_errno(nntpserver);
		exit(1);
	}
	do
		read(sock, &c, 1);
	while (c != '\n');
	return sock;
}