⭐ 欢迎来到虫虫下载站! | 📦 资源下载 📁 资源专辑 ℹ️ 关于我们
⭐ 虫虫下载站

📄 tag.java

📁 一个用java语言编写的网络爬虫程序
💻 JAVA
📖 第 1 页 / 共 2 页
字号:
     * converted with toHTMLAttributeName().      * @return copy of this tag with named attribute removed.  The copy is      * a region of a fresh page containing only the tag.      */    public Tag removeHTMLAttribute (String name) {        return replaceHTMLAttribute (name, null);    }        /**     * Copy this tag, setting an HTML attribute's value to TRUE.     * @param name Name of HTML attribute (e.g. "HREF").  Doesn't have to be     * converted with toHTMLAttributeName().      * @return copy of this tag with named attribute set to TRUE.  The copy is      * a region of a fresh page containing only the tag.      */    public Tag replaceHTMLAttribute (String name) {        return replaceHTMLAttribute (name, TRUE);    }        /**     * Copy this tag, setting an HTML attribute's value.     * @param name Name of HTML attribute (e.g. "HREF").  Doesn't have to be     * converted with toHTMLAttributeName().      * @param value New value for the attribute     * @return copy of this tag with named attribute set to value.       * The copy is      * a region of a fresh page containing only the tag.      */    public Tag replaceHTMLAttribute (String name, String value) {        name = toHTMLAttributeName (name);                if (!startTag)            return this; // illegal!                StringBuffer newstr = new StringBuffer ();        String[] newattrs = null;                newstr.append ('<');        newstr.append (tagName);        boolean foundit = false;                int len = htmlAttributes.length;        for (int i=0; i < len; ++i) {            String attrName = htmlAttributes[i];            String attrVal;                        // FIX: entity-encode attrVal            if (attrName == name) {                newattrs = htmlAttributes;                foundit = true;                if (value == null)                    continue;                attrVal = value;            }            else                attrVal = getLabel (attrName);                        newstr.append (' ');            newstr.append (attrName);            if (attrVal != TRUE) {                newstr.append ('=');                if (attrVal.indexOf ('"') == -1) {                    newstr.append ('"');                    newstr.append (attrVal);                    newstr.append ('"');                }                else {                    newstr.append ('\'');                    newstr.append (attrVal);                    newstr.append ('\'');                }            }        }        if (!foundit && value != null) {            // add new attribute at end            newstr.append (' ');            newstr.append (name);            if (value != name) {                newstr.append ('=');                if (value.indexOf ('"') == -1) {                    newstr.append ('"');                    newstr.append (value);                    newstr.append ('"');                }                else {                    newstr.append ('\'');                    newstr.append (value);                    newstr.append ('\'');                }            }            // append name to list of attribute names            newattrs = new String[len + 1];            System.arraycopy (htmlAttributes, 0, newattrs, 0, len);            newattrs[len] = name;        }                newstr.append ('>');        Tag newTag = new Tag (new Page (newstr.toString()), 0,                               newstr.length(), tagName, startTag);        newTag.names = names;        newTag.htmlAttributes = newattrs;        newTag.setLabel (name, value);                return newTag;    }    /**     * Commonly useful tag names.     * Derived from <a href="http://www.sandia.gov/sci_compute/elements.html">HTML Elements</a>      * at Sandia National Labs.      */    public static final String A = "a".intern();    public static final String ABBREV = "abbrev".intern();    public static final String ACRONYM = "acronym".intern();    public static final String ADDRESS = "address".intern();        public static final String APPLET = "applet".intern();    public static final String AREA = "area".intern();    public static final String B = "b".intern();    public static final String BASE = "base".intern();    public static final String BASEFONT = "basefont".intern();    public static final String BDO = "bdo".intern();    public static final String BGSOUND = "bgsound".intern();    public static final String BIG = "big".intern();    public static final String BLINK = "blink".intern();    public static final String BLOCKQUOTE = "blockquote".intern();    public static final String BODY = "body".intern();    public static final String BR = "br".intern();    public static final String CAPTION = "caption".intern();    public static final String CENTER = "center".intern();    public static final String CITE = "cite".intern();    public static final String CODE = "code".intern();    public static final String COL = "col".intern();    public static final String COLGROUP = "colgroup".intern();    public static final String COMMENT = "!".intern();    public static final String DD = "dd".intern();    public static final String DEL = "del".intern();    public static final String DFN = "dfn".intern();    public static final String DIR = "dir".intern();    public static final String DIV = "div".intern();    public static final String DL = "dd".intern();        public static final String DT = "dt".intern();    public static final String EM = "em".intern();    public static final String EMBED = "embed".intern();    public static final String FONT = "font".intern();    public static final String FRAME = "frame".intern();    public static final String FRAMESET = "frameset".intern();    public static final String FORM = "form".intern();    public static final String H1 = "h1".intern();    public static final String H2 = "h2".intern();    public static final String H3 = "h3".intern();    public static final String H4 = "h4".intern();    public static final String H5 = "h5".intern();    public static final String H6 = "h6".intern();    public static final String HEAD = "head".intern();    public static final String HR = "hr".intern();    public static final String HTML = "html".intern();    public static final String I = "i".intern();    public static final String IMG = "img".intern();    public static final String INPUT = "input".intern();    public static final String ISINDEX = "isindex".intern();    public static final String KBD = "kbd".intern();    public static final String LI = "li".intern();    public static final String LINK = "link".intern();    public static final String LISTING = "listing".intern();    public static final String MAP = "map".intern();    public static final String MARQUEE = "marquee".intern();    public static final String MENU = "menu".intern();    public static final String META = "meta".intern();    public static final String NEXTID = "nextid".intern();    public static final String NOBR = "nobr".intern();    public static final String NOEMBED = "noembed".intern();    public static final String NOFRAMES = "noframes".intern();    public static final String OBJECT = "object".intern();    public static final String OL = "ol".intern();    public static final String OPTION = "option".intern();    public static final String P = "p".intern();    public static final String PARAM = "param".intern();    public static final String PLAINTEXT = "plaintext".intern();    public static final String PRE = "pre".intern();    public static final String SAMP = "samp".intern();    public static final String SCRIPT = "script".intern();    public static final String SELECT = "select".intern();    public static final String SMALL = "small".intern();    public static final String SPACER = "spacer".intern();    public static final String STRIKE = "strike".intern();    public static final String STRONG = "strong".intern();    public static final String STYLE = "style".intern();    public static final String SUB = "sub".intern();    public static final String SUP = "sup".intern();    public static final String TABLE = "table".intern();    public static final String TD = "td".intern();    public static final String TEXTAREA = "textarea".intern();    public static final String TH = "th".intern();    public static final String TITLE = "title".intern();    public static final String TR = "tr".intern();    public static final String TT = "tt".intern();    public static final String U = "u".intern();    public static final String UL = "ul".intern();    public static final String VAR = "var".intern();    public static final String WBR = "wbr".intern();    public static final String XMP = "xmp".intern();        /**     * Length of longest tag name.     */    public static int MAX_LENGTH = 10;      // longest tag name is BLOCKQUOTE}

⌨️ 快捷键说明

复制代码 Ctrl + C
搜索代码 Ctrl + F
全屏模式 F11
切换主题 Ctrl + Shift + D
显示快捷键 ?
增大字号 Ctrl + =
减小字号 Ctrl + -