url.h

harvest是一个下载html网页得机器人

/*
 *  url.h - URL Processing (parsing & retrieval)
 *
 *  $Id: url.h,v 2.1 1997/03/21 19:21:01 sxw Exp $
 *
 *  AUTHOR: Harvest derived
 *
 *  Harvest Indexer http://harvest.sourceforge.net/
 *  -----------------------------------------------
 *
 *  The Harvest Indexer is a continued development of code developed by
 *  the Harvest Project. Development is carried out by numerous individuals
 *  in the Internet community, and is not officially connected with the
 *  original Harvest Project or its funding sources.
 *
 *  Please mail [e-mail] if you are interested in participating
 *  in the development effort.
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; either version 2 of the License, or
 *  (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; if not, write to the Free Software
 *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */
/*
 *  ----------------------------------------------------------------------
 *  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.
 *
 */
#ifndef _URL_H_
#define _URL_H_

#include "config.h"
#include <time.h>

/*
 *  The supported URLs look like:
 *
 *      file://host/pathname
 *      gopher://host[:port][/TypeDigitGopherRequest]
 *      http://host[:port][/[pathname][#name][?search]]
 *      ftp://[user[:password]@]host[:port][/pathname]
 *
 *  where host is either a fully qualified hostname, an IP number, or
 *  a relative hostname.
 *
 *  For http, any '#name' or '?search' directives are ignored.
 *  For ftp, any user, password, or port directives are unsupported.
 */

struct url {
	char *url;		/* Complete, normalized URL */
	char *redir_from_url;	/* the original URL when REDIRECT'ed */
	char *raw_pathname;	/* pathname portion of the URL, w/ escapes */
	char *pathname;		/* pathname portion of the URL, w/o escapes */
	char *host;		/* fully qualified hostname */
	int type;		/* file, ftp, http, gopher, etc. */
	int port;		/* TCP/IP port */

/* Information for FTP/HTTP processing */
	char *user;		/* Login name for ftp */
	char *password;		/* password for ftp */

/* Information for Gopher processing */
	int gophertype;		/* Numeric type for gopher request */

/* Information for HTTP processing */
	char *http_version;	/* HTTP/1.0 Version */
	int   http_status_code;	/* HTTP/1.0 Status Code */
	char *http_reason_line;	/* HTTP/1.0 Reason Line */
	char *http_mime_hdr;	/* HTTP/1.0 MIME Response Header */

/* Information for local copy processing */
	char *filename;		/* local filename */
	char *shsafe_filename;	/* filename suitable within "'s of sh(1) */
	FILE *fp;		/* ptr to local filename */
	time_t lmt;		/* Last-Modification-Time */
	int flags;		/* bitfield */

#ifdef USE_MD5
	char *md5;		/* MD5 value of URL */
#endif

#ifdef HTTP_AUTHENTICATION
	char *auth_type;
	char *auth_realm;
	char *auth_str;
#endif
};
typedef struct url URL;

#define URL_FLAG_NONE		0
#define URL_FLAG_PASS_USERINFO	(1<<0)
#define URL_FLAG_LOCAL_MAPPED	(1<<1)
#define URL_FLAG_NEED_UNLINK	(1<<2)

#define URL_FLAG_SET(flag, bit) (flag |= bit)
#define URL_FLAG_CLR(flag, bit) (flag &= ~bit)


enum url_types {		/* Constants for URL types */
	URL_UNKNOWN,
	URL_FILE,		/* NOTE: the array default_URL_port[]	*/
	URL_FTP,		/* in src/common/url/url.c depends on	*/
	URL_GOPHER,		/* the order of this list.  Change one,	*/
	URL_HTTP,		/* change the other.			*/
	URL_NEWS,
	URL_NOP,
	URL_TELNET,
	URL_WAIS,
	URL_X,
	URL_MAILTO
};

#ifndef _PARAMS
#if defined(__STDC__) || defined(__cplusplus) || defined(__STRICT_ANSI__)
#define _PARAMS(ARGS) ARGS
#else /* Traditional C */
#define _PARAMS(ARGS) ()
#endif /* __STDC__ */
#endif /* _PARAMS */

URL *url_open _PARAMS((char *));
int url_read _PARAMS((char *, int, int, URL *));
int url_retrieve _PARAMS((URL *));
int url_confirm _PARAMS((URL *));
void url_close _PARAMS((URL *));

void init_url _PARAMS(());
void finish_url _PARAMS(());

void url_purge _PARAMS(());

URL *dup_url _PARAMS((URL *));
void print_url _PARAMS((URL *));

int http_get _PARAMS((URL *));
int ftp_get _PARAMS((URL *));
int ftp_get_auth _PARAMS((URL *));
int gopher_get _PARAMS((URL *));
int news_get _PARAMS((URL *));

char *rfc1738_escape _PARAMS((char *));
void rfc1738_unescape _PARAMS((char *));

char *url_parse_relative _PARAMS((char *, char*));

#ifdef USE_LOCAL_CACHE
void init_cache _PARAMS(());
char *lookup_cache _PARAMS((char *));
time_t lmt_cache _PARAMS((char *));
void add_cache _PARAMS((char *, char *, time_t));
void finish_cache _PARAMS(());
void expire_cache _PARAMS(());
#endif

#ifdef USE_CCACHE
void url_initCache _PARAMS((int, long));
void url_shutdowncache _PARAMS(());
#endif

extern struct _url_table {
        char *scheme;
        int port;
        int (*get_func) ();
} url_table[];

/* from db.c */
void urldb_init _PARAMS((char *));
char *urldb_getmd5 _PARAMS((char *));
void urldb_writesoif _PARAMS((char *, FILE *));
char *urldb_getrefs _PARAMS((char *));
int urldb_getlmt _PARAMS((char *));

#endif /* _URL_H_ */