htmlplus.dtd

harvest是一个下载html网页得机器人

<!ELEMENT (SUP|SUB) - - (%text;)* -- superscripts and subscripts -->
<!ATTLIST (SUP|SUB)
        id      ID      #IMPLIED -- link destination --
        charset CDATA   #IMPLIED -- eg "ISO-2022-JP" for japanese -->

<!ELEMENT (FOOTNOTE|MARGIN) - - (%text;)* -(FOOTNOTE|MARGIN)>
<!ATTLIST (FOOTNOTE|MARGIN)
        id      ID      #IMPLIED -- link destination --
        charset CDATA   #IMPLIED -- eg "ISO-2022-JP" for japanese -->

<!-- RENDER only appears in the document head -->
<!ELEMENT RENDER -O EMPTY -- how to render unknown elements -->
<!ATTLIST RENDER
        id      ID      #IMPLIED -- to allow meta info  --
        tag     CDATA   #IMPLIED -- tag name --
        equiv   CDATA   #IMPLIED -- HTML+ equivalent tag name --
        style   NAMES   #IMPLIED -- space separated list of styles -->

<!-- Based on LaTeX's tabbing environment -->
<!ELEMENT TAB - O EMPTY>
<!ATTLIST TAB
        id      ID      #IMPLIED  -- used to set a tab stop --
        to      IDREF   #IMPLIED  -- move to previously defined tab stop --
        before  NUMBER  0         -- scaled em spaces before tab stop --
        after   NUMBER  0         -- scaled em spaces after tab stop -->

<!-- content is hidden, equivalent of LaTeX's \kill -->
<!ELEMENT HIDE - - (%text;) -(HIDE)>

<!ELEMENT QUOTE - - (P*) -- block quote -->
<!ATTLIST QUOTE
        id      ID      #IMPLIED -- link destination --
        charset CDATA   #IMPLIED -- eg "ISO-2022-JP" for japanese -->

<!ELEMENT ABSTRACT - - (P*) -- document summary -->
<!ATTLIST ABSTRACT
        id      ID      #IMPLIED -- link destination --
        charset CDATA   #IMPLIED -- eg "ISO-2022-JP" for japanese -->

<!-- often rendered with an icon in left margin,
     the role is shown before the first paragraph -->
<!ELEMENT NOTE - - (P*) -- admonishment -->
<!ATTLIST NOTE
        id      ID      #IMPLIED -- link destination --
        charset CDATA   #IMPLIED -- eg "ISO-2022-JP" for japanese --
        src     %URL;   #IMPLIED -- url for the icon --
        role (Simple|Tip|Note|Warning|Error) Simple >

<!-- change bars can bridge markup boundaries -->
<!ELEMENT CHANGED - O EMPTY>
<!ATTLIST CHANGED -- one of id or idref is always required --
        begin    ID      #IMPLIED -- signals beginning of changes --
        end      IDREF   #IMPLIED -- signals end of changes -->
]]>


<![ %HTML.figures [ <!ENTITY % HTML.captions "INCLUDE"> ]]>
<![ %HTML.tables [ <!ENTITY % HTML.captions "INCLUDE"> ]]>
<!ENTITY % HTML.captions "IGNORE">

<![ %HTML.captions [

<!ELEMENT CAPTION - - (%text;)+ -- table or figure caption -->
<!ATTLIST CAPTION
        id      ID      #IMPLIED
        align (top|bottom) #IMPLIED
        charset CDATA   #IMPLIED -- eg "ISO-2022-JP" for japanese -->
]]>

<![ %HTML.tables [

<!-- a pre-pass is needed to count columns and determine
     min/max widths before sizing to match window size -->

<!ELEMENT TABLE - - (CAPTION?, TR*) -- mixed headers and data -->
<!ATTLIST TABLE
        id      ID      #IMPLIED
        border (border) #IMPLIED -- draw borders --
        charset CDATA   #IMPLIED -- eg "ISO-2022-JP" for japanese -->

<!-- browsers should tolerate an omission of the first
  <TR> tag as it is implied by the context -->
<!ELEMENT TR - O (TH|TD)* -- acts like row separator -->
<!ATTLIST TR id ID #IMPLIED>

<!ELEMENT TH - O (%table;)* -- a header cell -->
<!ATTLIST TH
        id      ID      #IMPLIED
        colspan NUMBER    1      -- columns spanned --
        rowspan NUMBER    1      -- rows spanned --
        align (left|center|right) center
        alignon CDATA   #IMPLIED -- align on decimal point etc --
        nowrap (nowrap) #IMPLIED -- don't wrap words --
        charset CDATA   #IMPLIED -- eg "ISO-2022-JP" for japanese -->

<!ELEMENT TD - O (%table;)* -- a data cell -->
<!ATTLIST TD
        id      ID      #IMPLIED
        colspan NUMBER    1      -- columns spanned --
        rowspan NUMBER    1      -- rows spanned --
        align (left|center|right) center
        alignon CDATA   #IMPLIED -- align on decimal point etc --
        nowrap (nowrap) #IMPLIED -- don't wrap words --
        charset CDATA   #IMPLIED -- eg "ISO-2022-JP" for japanese -->
]]>

<![ %HTML.forms [

<!--
 The form contents are sent to the server upon pressing a submit
 button. Forms can be associated with scripts, e.g. to make one
 selection field effect which options are enabled for other fields.

 Clicking on a selection or typing into a text field result in events
 which are processed by the script. Event handlers are associated
 with each field or with the form itself. The script language is
 deliberately restricted to avoid any security issues.

 Fields can be disabled (greyed out) or marked as being in error.
 The MESSAGE element may be used by the server to set error messages.
 Servers can store state information in forms with hidden input fields.
 These are not displayed and can be used to hold transaction handles etc.
-->

<!ELEMENT FORM - - ((%main;)*, MESSAGE?) -(FORM) -- forms can't be nested -->
<!ATTLIST FORM
        id      ID      #IMPLIED
        action  %URL;   #IMPLIED -- defaults to URL for current doc --
        method  CDATA   #IMPLIED -- GET, PUT, POST, DELETE etc. --
        enctype CDATA   #IMPLIED -- encoding type for form transfers --
        script  %URL;   #IMPLIED -- locally executed event handlers --
        charset CDATA   #IMPLIED -- eg "ISO-2022-JP" for japanese -->

<!-- Types of INPUT field:
 text: one line text fields, size gives visible width of field in chars
       where value may grow beyond this up to MAX (MAXLENGTH) chars.
 password: like text fields but with no echo of typed characters
 checkbox: for simple yes/no choices
 radio: for one from many choices, each radio button in a group
        has the same NAME but a different VALUE.
 submit: Sends form to server. If the SRC attribute specifies an
       icon the point clicked is sent to the server as per ISMAP.
       The default NAME for this field is "Submit". The VALUE is used
       as the buttobn label. The NAME/VALUE are submitted with the form
       contents to allow servers to work out which button was pressed.
 reset: Resets fields to their initial values. The VALUE is used as the
       button label. The SRC attribute can be used for an icon button.
 int: for input of integers, SIZE attribute gives width of field
 float: for input of floating point numbers
 date: for input of dates
 url: for input of universal resource locators
 hidden: used by server for state info, opaque to client
 range: integer range from MIN to MAX, rendered as a slider etc.
 scribble: Pen input, which may include time and pressure info, the
        background can be initialised to an image with the SRC attribute
 audio: sound input with up to MAX seconds
-->
<!ELEMENT INPUT - O EMPTY>
<!ATTLIST INPUT
        id      ID      #IMPLIED -- to allow meta info  --
        name    CDATA   #IMPLIED -- attribute name (may not be unique) --
        type    (%fields) text   -- a wide variety of field types --
        charset CDATA   #IMPLIED -- eg "ISO-2022-JP" for japanese --
        size    CDATA   #IMPLIED -- visible size of text fields --
        min     NUMBER  #IMPLIED -- for range controls --
        max     NUMBER  #IMPLIED -- for range controls or text fields --
        maxlength NUMBER #IMPLIED -- max length of text fields (equiv to max)--
        value   CDATA   #IMPLIED -- attribute value (altered by user) --
        checked (checked) #IMPLIED -- for check boxes and radio buttons --
        disabled (disabled) #IMPLIED -- if grayed out --
        error   (error) #IMPLIED -- if in error --
        src      %URL;  #IMPLIED -- for SUBMIT, SCRIBBLE & AUDIO fields --
        alt     CDATA   #IMPLIED -- alternative text for VT100's etc --
        align (top|middle|bottom) top -- for IMAGE fields only -->

<!-- multiline text input fields, we probably will want
     to generalise this to accept arbitrary clipboard data
     e.g. hypertext and images, in addition to plain text -->
<!ELEMENT TEXTAREA - - RCDATA -- multi-line text fields -->
<!ATTLIST TEXTAREA
        id      ID      #IMPLIED -- to allow meta info  --
        name    CDATA   #IMPLIED -- attribute name (may not be unique) --
        cols    NUMBER  #IMPLIED -- visible width in characters --
        rows    NUMBER  #IMPLIED -- visible height in characters --
        wrap    (wrap)  #IMPLIED -- wrap input in text area --
        disabled (disabled) #IMPLIED -- if grayed out --
        error   (error) #IMPLIED -- if in error --
        charset CDATA   #IMPLIED -- eg "ISO-2022-JP" for japanese -->

<!--
     The EDIT attribute when present allows you to type and
     edit the selected option.

     The SRC attribute allows for graphical menus, e.g. users
     wanting to buy a house could click on each of the areas on
     a map that they were interested in.
 -->
<!ELEMENT SELECT - - (OPTION+) -- combo style selection lists -->
<!ATTLIST SELECT
        id      ID      #IMPLIED -- to allow meta info  --
        name    CDATA   #IMPLIED -- attribute name (may not be unique) --
        edit    NUMBER  #IMPLIED -- width of editable selection --
        multiple (multiple) #IMPLIED -- permits multiple selections --
        error   (error) #IMPLIED -- if in error --
        src      %URL;  #IMPLIED -- for graphical menus --
        charset CDATA   #IMPLIED -- eg "ISO-2022-JP" for japanese -->

<!-- The SHAPE attribute defines a region in the image that
     is specified by the SRC attribute for the SELECT element -->
<!ELEMENT OPTION - O RCDATA>
<!ATTLIST OPTION
        id      ID      #IMPLIED -- to allow meta info  --
        value   CDATA   #IMPLIED -- attribute value --
        selected (selected) #IMPLIED -- if initially selected --
        disabled (disabled) #IMPLIED -- if grayed out --
        shape   CDATA   #IMPLIED -- list of points for shaped region --
        charset CDATA   #IMPLIED -- eg "ISO-2022-JP" for japanese -->

<!--
 Scripts executed by the client need a way of displaying
 warning/error messages. We define an element so that the
 server too can initialise this one-per-form message area.
 Clients should preferably avoid displaying the message
 in-line, as the window size may prevent the user from 
 seeing the message.
 -->
<!ELEMENT MESSAGE - O RCDATA -- place for error/warning/info -->
<!ATTLIST MESSAGE
        id      ID      #IMPLIED -- to allow meta info  --
        status  (info|warning|error) info
        charset CDATA   #IMPLIED -- eg "ISO-2022-JP" for japanese -->
]]>

<![ %HTML.figures [

<!-- figures which subsume the role of the earlier IMG element.

  Behaves identically to IMG for align = top, middle or bottom.
  Otherwise figure is inserted after next line break (soft or hard).
  For align=left, the image is left aligned and text is flowed
  on the right of the image, and similarly for align=right, with
  no text flow for align=center (the default). The caption is
  placed under the image.

  Finer control of the vertical positioning relative to the text
  line is possible with the baseline attribute. When present, the
  figure acts like the IMG element but is shifted so that the baseline
  occurs at the specified number of pixels above the bottom of the image. 
  If this is given as a floating point number, it is interpreted as a
  fraction of the image height and must lie in the range (0.0 to 1.0)

  The <A> element is used for shaped buttons handled by browser,
  while the ISMAP mechanism sends pointer clicks/drags to server.
  The text contained by this element is used for text-only displays
  and authors should remember to provide effective descriptions,
  including label text for shaped buttons.
-->
<!ELEMENT FIG - - (CAPTION?, P*)>
<!ATTLIST FIG
        id      ID      #IMPLIED
        align   (top|middle|bottom|left|center|right) center -- position --
        baseline NUMBER #IMPLIED -- height of baseline above image bottom --
        ismap   (ismap) #IMPLIED -- server can handle mouse clicks/drags --
        src     %URL;   #IMPLIED -- link to image data --
        charset CDATA   #IMPLIED -- eg "ISO-2022-JP" for japanese -->
]]>

<!-- img is left in for at least the short term -->
<!ELEMENT IMG - O EMPTY>
<!ATTLIST IMG
        src     %URL;   #REQUIRED -- where to get image data --
        align   (top|middle|bottom) top  -- top, middle or bottom --
        baseline NUMBER #IMPLIED -- height of baseline above image bottom --
        alt     CDATA   #IMPLIED -- description for text-only displays --
        ismap   (ismap) #IMPLIED  -- send mouse clicks/drags to server -->

<![ %HTML.math [

<!-- Proposal for representing formulae

  Delimiters should stretch to match the size of the delimited
  object. <SUB> and <SUP> are used for subscripts and superscripts

                                          i j
      X <SUP>i</SUP>Y<SUP>j</SUP>  is   X  Y

  i.e. the space following the X disambiguates the binding.
-->

<!ELEMENT MATH - - (%formulae;)* -(MATH) -- math can't be nested -->
<!ATTLIST MATH id ID #IMPLIED>

<!-- Invisible brackets which may also be
     used for numerators and denominators:

                                   1 + X
     <BOX>1 + X<OVER>Y</BOX>  is  _______
                                     Y

                                 _____
     <BOX><OVER>X + Y</BOX>  is  X + Y
-->
<!ELEMENT BOX - - ((%formulae;)*, (OVER, (%formulae;)*)?)>

<!-- Horizontal line between numerator and denominator
     The symbol attribute allows authors to supply an
     entity name for an arrow symbol etc.
 -->
<!ELEMENT OVER - O EMPTY>
<!ATTLIST OVER symbol ENTITY #IMPLIED>

<!-- Roots - default to square root -->
<!ELEMENT ROOT - - (%formulae;)*>
<!ATTLIST ROOT root CDATA #IMPLIED>

<!-- LaTeX like arrays. The align attribute specifies
     a single letter for each column, which also determines
     how the column should be aligned, e.g. align=ccc"

        "l"     left
        "c"     center
        "r"     right
-->
<!ELEMENT ARRAY - - (ITEM)+>
<!ATTLIST ARRAY align CDATA #REQUIRED>

<!ELEMENT ITEM - O (%formulae;)*>

]]>

<!-- The END -->
]>

<HEAD>
    <BODY>
      <PROLOGUE>
        <P>this is some text
    </BODY>