html.h

harvest是一个下载html网页得机器人

/* $Id: HTML.h,v 2.2 2000/02/03 12:45:56 sxw Exp $
 */
/****************************************************************************
 * NCSA Mosaic for the X Window System                                      *
 * Software Development Group                                               *
 * National Center for Supercomputing Applications                          *
 * University of Illinois at Urbana-Champaign                               *
 * 605 E. Springfield, Champaign IL 61820                                   *
 * [e-mail]                                                     *
 *                                                                          *
 * Copyright (C) 1993, Board of Trustees of the University of Illinois      *
 *                                                                          *
 * NCSA Mosaic software, both binary and source (hereafter, Software) is    *
 * copyrighted by The Board of Trustees of the University of Illinois       *
 * (UI), and ownership remains with the UI.                                 *
 *                                                                          *
 * The UI grants you (hereafter, Licensee) a license to use the Software    *
 * for academic, research and internal business purposes only, without a    *
 * fee.  Licensee may distribute the binary and source code (if released)   *
 * to third parties provided that the copyright notice and this statement   *
 * appears on all copies and that no charge is associated with such         *
 * copies.                                                                  *
 *                                                                          *
 * Licensee may make derivative works.  However, if Licensee distributes    *
 * any derivative work based on or derived from the Software, then          *
 * Licensee will (1) notify NCSA regarding its distribution of the          *
 * derivative work, and (2) clearly notify users that such derivative       *
 * work is a modified version and not the original NCSA Mosaic              *
 * distributed by the UI.                                                   *
 *                                                                          *
 * Any Licensee wishing to make commercial use of the Software should       *
 * contact the UI, c/o NCSA, to negotiate an appropriate license for such   *
 * commercial use.  Commercial use includes (1) integration of all or       *
 * part of the source code into a product for sale or license by or on      *
 * behalf of Licensee to third parties, or (2) distribution of the binary   *
 * code or source code to third parties that need it to utilize a           *
 * commercial product sold or licensed by or on behalf of Licensee.         *
 *                                                                          *
 * UI MAKES NO REPRESENTATIONS ABOUT THE SUITABILITY OF THIS SOFTWARE FOR   *
 * ANY PURPOSE.  IT IS PROVIDED "AS IS" WITHOUT EXPRESS OR IMPLIED          *
 * WARRANTY.  THE UI SHALL NOT BE LIABLE FOR ANY DAMAGES SUFFERED BY THE    *
 * USERS OF THIS SOFTWARE.                                                  *
 *                                                                          *
 * By using or copying this Software, Licensee agrees to abide by the       *
 * copyright law and all other applicable laws of the U.S. including, but   *
 * not limited to, export control laws, and the terms of this license.      *
 * UI shall have the right to terminate this license immediately by         *
 * written notice upon Licensee's breach of, or non-compliance with, any    *
 * of its terms.  Licensee may be held legally responsible for any          *
 * copyright infringement that is caused or encouraged by Licensee's        *
 * failure to abide by the terms of this license.                           *
 *                                                                          *
 * Comments and questions are welcome and can be sent to                    *
 * [e-mail].                                                  *
 ****************************************************************************/

#ifndef HTML_H
#define HTML_H


/*
 * defines and structures used for the HTML parser, and the
 * parsed object list.
 */

/* Mark types */
#define	M_UNKNOWN	-1
#define	M_NONE		0
#define	M_TITLE		1
#define	M_HEADER_1	2
#define	M_HEADER_2	3
#define	M_HEADER_3	4
#define	M_HEADER_4	5
#define	M_HEADER_5	6
#define	M_HEADER_6	7
#define	M_ANCHOR	8
#define	M_PARAGRAPH	9
#define	M_ADDRESS	10
#define	M_PLAIN_TEXT	11
#define	M_UNUM_LIST	12
#define	M_NUM_LIST	13
#define	M_LIST_ITEM	14
#define	M_DESC_LIST	15
#define	M_DESC_TITLE	16
#define	M_DESC_TEXT	17
#define	M_PREFORMAT	18
#define	M_PLAIN_FILE	19
#define M_LISTING_TEXT	20
#define M_INDEX		21
#define M_MENU		22
#define M_DIRECTORY	23
#define M_IMAGE		24
#define M_FIXED		25
#define M_BOLD		26
#define M_ITALIC	27
#define M_EMPHASIZED	28
#define M_STRONG	29
#define M_CODE		30
#define M_SAMPLE	31
#define M_KEYBOARD	32
#define M_VARIABLE	33
#define M_CITATION	34
#define M_BLOCKQUOTE	35
#define M_STRIKEOUT	36
#define M_INPUT		37
#define M_FORM		38
#define M_HRULE		39
#define M_LINEBREAK	40
#define M_BASE		41
#define M_SELECT	42
#define M_OPTION	43
#define M_TEXTAREA	44
/* DFM ADDITIONS from New Mosaic*/
#define M_TABLE         45
#define M_CAPTION       46
#define M_TABLE_HEADER  47
#define M_TABLE_ROW     48
#define M_TABLE_DATA    49
#define M_SUP           50
#define M_SUB           51
#define M_FIGURE        52
#define M_COMMENT       53
#define M_DOC_HEAD      54 /* amb 2 */
#define M_UNDERLINED    55 /* amb 2 */
#define M_DOC_BODY      56 /* amb 2 */
#define M_FRAME         57
#define M_MAP           58 /* swp - client side ismap */
#define M_AREA          59 /* swp - client side ismap */
/* sxw - additions for META tags - use high numbers to stay out of the way */
#define M_META          100

/* syntax of Mark types */
#define	MT_TITLE	"title"
#define	MT_HEADER_1	"h1"
#define	MT_HEADER_2	"h2"
#define	MT_HEADER_3	"h3"
#define	MT_HEADER_4	"h4"
#define	MT_HEADER_5	"h5"
#define	MT_HEADER_6	"h6"
#define	MT_ANCHOR	"a"
#define	MT_PARAGRAPH	"p"
#define	MT_ADDRESS	"address"
#define	MT_PLAIN_TEXT	"xmp"
#define	MT_UNUM_LIST	"ul"
#define	MT_NUM_LIST	"ol"
#define	MT_LIST_ITEM	"li"
#define	MT_DESC_LIST	"dl"
#define	MT_DESC_TITLE	"dt"
#define	MT_DESC_TEXT	"dd"
#define	MT_PREFORMAT	"pre"
#define	MT_PLAIN_FILE	"plaintext"
#define MT_LISTING_TEXT	"listing"
#define MT_INDEX	"isindex"
#define MT_MENU		"menu"
#define MT_DIRECTORY	"dir"
#define MT_IMAGE	"img"
#define MT_FIXED	"tt"
#define MT_BOLD		"b"
#define MT_ITALIC	"i"
#define MT_EMPHASIZED	"em"
#define MT_STRONG	"strong"
#define MT_CODE		"code"
#define MT_SAMPLE	"samp"
#define MT_KEYBOARD	"kbd"
#define MT_VARIABLE	"var"
#define MT_CITATION	"cite"
#define MT_BLOCKQUOTE	"blockquote"
#define MT_STRIKEOUT	"strike"
#define MT_INPUT	"input"
#define MT_FORM		"form"
#define MT_HRULE	"hr"
#define MT_LINEBREAK	"br"
#define MT_BASE		"base"
#define MT_SELECT	"select"
#define MT_OPTION	"option"
#define MT_TEXTAREA	"textarea"

/*DFM ADDITIONS from NEW Mosaic*/
#define MT_FIGURE       "fig"
#define MT_TABLE        "table"
#define MT_CAPTION      "caption"
#define MT_TABLE_ROW    "tr"
#define MT_TABLE_HEADER "th"
#define MT_TABLE_DATA   "td"
#define MT_SUP          "sup"
#define MT_SUB          "sub"
#define MT_DOC_HEAD     "head" /* amb 2 */
#define MT_UNDERLINED   "u"    /* amb 2 */
#define MT_DOC_BODY     "body"
#define MT_FRAME        "frame"
#define MT_MAP          "map" /* swp - client side ismap */
#define MT_AREA         "area" /* swp - client side ismap */

/* sxw - additons for META tags */
#define MT_META         "meta"

/* anchor tags */
#define	AT_NAME		"name"
#define	AT_HREF		"href"
/*DFM ADDITIONS from NEW Mosaic*/
#define AT_SUBJECT      "subject"
#define AT_TITLE        "title"

/* sxw - additions for META tags */
#define MT_NAME         "name"
#define MT_CONTENT      "content"

struct mark_up {
	int type;
	int is_end;
	char *start;
	char *text;
	char *end;
	struct mark_up *next;
};

#endif /* HTML_H */

#ifndef _HTMLAMP_H_
#define _HTMLAMP_H_
/* HTMLamp.h */
/****************************************************************************
 * NCSA Mosaic for the X Window System                                      *
 * Software Development Group                                               *
 * National Center for Supercomputing Applications                          *
 * University of Illinois at Urbana-Champaign                               *
 * 605 E. Springfield, Champaign IL 61820                                   *
 * [e-mail]                                                     *
 *                                                                          *
 * Copyright (C) 1993, Board of Trustees of the University of Illinois      *
 *                                                                          *
 * NCSA Mosaic software, both binary and source (hereafter, Software) is    *
 * copyrighted by The Board of Trustees of the University of Illinois       *
 * (UI), and ownership remains with the UI.                                 *
 *                                                                          *
 * The UI grants you (hereafter, Licensee) a license to use the Software    *
 * for academic, research and internal business purposes only, without a    *
 * fee.  Licensee may distribute the binary and source code (if released)   *
 * to third parties provided that the copyright notice and this statement   *
 * appears on all copies and that no charge is associated with such         *
 * copies.                                                                  *
 *                                                                          *
 * Licensee may make derivative works.  However, if Licensee distributes    *
 * any derivative work based on or derived from the Software, then          *
 * Licensee will (1) notify NCSA regarding its distribution of the          *
 * derivative work, and (2) clearly notify users that such derivative       *
 * work is a modified version and not the original NCSA Mosaic              *
 * distributed by the UI.                                                   *
 *                                                                          *
 * Any Licensee wishing to make commercial use of the Software should       *
 * contact the UI, c/o NCSA, to negotiate an appropriate license for such   *
 * commercial use.  Commercial use includes (1) integration of all or       *
 * part of the source code into a product for sale or license by or on      *
 * behalf of Licensee to third parties, or (2) distribution of the binary   *
 * code or source code to third parties that need it to utilize a           *
 * commercial product sold or licensed by or on behalf of Licensee.         *
 *                                                                          *
 * UI MAKES NO REPRESENTATIONS ABOUT THE SUITABILITY OF THIS SOFTWARE FOR   *
 * ANY PURPOSE.  IT IS PROVIDED "AS IS" WITHOUT EXPRESS OR IMPLIED          *
 * WARRANTY.  THE UI SHALL NOT BE LIABLE FOR ANY DAMAGES SUFFERED BY THE    *
 * USERS OF THIS SOFTWARE.                                                  *
 *                                                                          *
 * By using or copying this Software, Licensee agrees to abide by the       *
 * copyright law and all other applicable laws of the U.S. including, but   *
 * not limited to, export control laws, and the terms of this license.      *
 * UI shall have the right to terminate this license immediately by         *
 * written notice upon Licensee's breach of, or non-compliance with, any    *
 * of its terms.  Licensee may be held legally responsible for any          *
 * copyright infringement that is caused or encouraged by Licensee's        *
 * failure to abide by the terms of this license.                           *
 *                                                                          *
 * Comments and questions are welcome and can be sent to                    *
 * [e-mail].                                                  *
 ****************************************************************************/


typedef struct amp_esc_rec {
	char *tag;
	char value;
} AmpEsc;

static AmpEsc AmpEscapes[] = {
	{"nbsp", ' '},
	{"lt", '<'},
	{"LT", '<'},
	{"gt", '>'},
	{"GT", '>'},
	{"amp", '&'},
	{"AMP", '&'},
	{"quot", '\"'},
	{"QUOT", '\"'},
	{"Agrave", '\300'},
	{"Aacute", '\301'},
	{"Acirc", '\302'},
	{"Atilde", '\303'},
	{"Auml", '\304'},
	{"Aring", '\305'},
	{"AElig", '\306'},
	{"Ccedil", '\307'},
	{"Egrave", '\310'},
	{"Eacute", '\311'},
	{"Ecirc", '\312'},
	{"Euml", '\313'},
	{"Igrave", '\314'},
	{"Iacute", '\315'},
	{"Icirc", '\316'},
	{"Iuml", '\317'},
	{"ETH", '\320'},
	{"Ntilde", '\321'},
	{"Ograve", '\322'},
	{"Oacute", '\323'},
	{"Ocirc", '\324'},
	{"Otilde", '\325'},
	{"Ouml", '\326'},

	{"?", '\327'}, /* ? */

	{"Oslash", '\330'},
	{"Ugrave", '\331'},
	{"Uacute", '\332'},
	{"Ucirc", '\333'},
	{"Uuml", '\334'},
	{"Yacute", '\335'},
	{"THORN", '\336'},
	{"szlig", '\337'},
	{"agrave", '\340'},
	{"aacute", '\341'},
	{"acirc", '\342'},
	{"atilde", '\343'},
	{"auml", '\344'},
	{"aring", '\345'},
	{"aelig", '\346'},
	{"ccedil", '\347'},
	{"egrave", '\350'},
	{"eacute", '\351'},
	{"ecirc", '\352'},
	{"euml", '\353'},
	{"igrave", '\354'},
	{"iacute", '\355'},
	{"icirc", '\356'},
	{"iuml", '\357'},
	{"eth", '\360'},
	{"ntilde", '\361'},
	{"ograve", '\362'},
	{"oacute", '\363'},
	{"ocirc", '\364'},
	{"otilde", '\365'},
	{"ouml", '\366'},

	{"?", '\367'}, /* ? */

	{"oslash", '\370'},
	{"ugrave", '\371'},
	{"uacute", '\372'},
	{"ucirc", '\373'},
	{"uuml", '\374'},
	{"yacute", '\375'},
	{"thorn", '\376'},
	{"yuml", '\377'},

	{NULL, '\0'},
};


#endif /* _HTMLAMP_H_ */