html-hj.dtd

harvest是一个下载html网页得机器人

<!--
    Note that table cells can include nested tables.
    Missing cells are considered to be empty, while
    missing rows should be ignored, i.e. if a cell
    spans a row and there are no further TR elements
    then the implied row should be ignored.
-->

<!ELEMENT (%cell) - O %body.content>
<!ATTLIST (%cell)
        %attrs;
        colspan NUMBER    1      -- columns spanned --
        rowspan NUMBER    1      -- rows spanned --
        align  (%horiz.align) #IMPLIED -- horizontal alignment --
        valign (%vert.align) top -- vertical alignment --
        dp      CDATA    #IMPLIED  -- decimal point e.g. dp="," --
        nowrap (nowrap)  #IMPLIED  -- don't wrap words --
        axis CDATA #IMPLIED -- axis name, defaults to element content --
        axes CDATA #IMPLIED -- comma separated list of axis names --
        >

<!--====================== Figures ========================================-->

<!--
  The element contains text for use in non-graphical displays. Note that
  you can use the shape attribute in anchors to specify hotzones on images.
  This provides for local processing of pointer clicks and a unified method
  for dealing with graphical and non-graphical displays.

  Text is flowed around figures when the figure is left or right aligned.
  You can request the browser to move down until there is enough room for
  the next element, see the CLEAR and NEED attributes (in %needs)

  Figures offer a path towards embedding arbitrary information formats
  via some kind of OLE/OpenDoc mechanism.
-->

<!ELEMENT FIG - - (OVERLAY*, CAPTION?, FIGTEXT, CREDIT?) -(FIG|IMG)>
<!ATTLIST FIG
        %attrs;
        %needs;                  -- for control of text flow --
        src  %URI;  #REQUIRED    -- URI of document to embed --
        %url.link;               -- standard link attributes --
        %block.align;            -- horizontal alignment --
        noflow (noflow) #IMPLIED -- noflow around figure --
        width  NUMBER #IMPLIED   -- desired width in units --
        height NUMBER #IMPLIED   -- desired height in units --
        units (en|pixels) pixels -- specifies units as en's or pixels --
        imagemap (%URI) #IMPLIED -- pass background clicks to server --
        >
        
<!ELEMENT FIGTEXT O O %body.content -- dummy element -->

<!--
    Figure overlays. When combined with local caching, overlays
    provide a cheap way of modifying a larger base image sent as
    part of a previous page.
-->

<!ELEMENT OVERLAY - O EMPTY -- image overlay -->
<!ATTLIST OVERLAY
        src  %URI;  #REQUIRED    -- URI of image overlay --
        %url.link;               -- standard link attributes --
        units (en|pixels) pixels -- specifies units as en's or pixels --
        x      NUMBER   0        -- offset from left in units --
        y      NUMBER   0        -- offset from top in units --
        width  NUMBER #IMPLIED   -- desired width in units --
        height NUMBER #IMPLIED   -- desired height in units --
        imagemap (%URI) #IMPLIED -- pass background clicks to server --
        >

<!ELEMENT CREDIT - - (%text;)* -- source of image -->
<!ATTLIST CREDIT
        %attrs;
        >

<!--======================== Notes ========================================-->

<!--
The NOTE element is used for admonishments. The CLASS attribute
is used to differentiate NOTE's, e.g. Note, Caution or Warning.
-->

<!ELEMENT NOTE - - %body.content; -- admonishment -->
<!ATTLIST NOTE
        %attrs;
        src %URI;   #IMPLIED  -- URI of custom graphic --
        %url.link;            -- standard link attributes --
        %needs; -- for control of text flow --
        >

<!--======================== Footnotes ====================================-->

<!--
Typically rendered as popup note. These elements are referenced
by hypertext links specified with the anchor element.
-->
<!ELEMENT FN - - %body.content;>
<!ATTLIST FN %attrs;>

<!--======================== Math  ========================================-->

<!-- Use &thinsp; &emsp; etc for greater control of spacing. -->

<!-- Subscripts and Superscripts

  <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.
  The align attribute can be used for horizontal alignment,
  e.g. to explicitly place an index above an element:
                                              i
        X<sup align=center>i</sup>  produces  X

Short references are defined for superscripts, subscripts and boxes
to save typing when manually editing HTML math, e.g.

      x^2^    is mapped to   x<sup>2</sup>
      y_z_    is mapped to   y<sub>z</sub>
      {a+b}   is mapped to   <box>a + b</box>

Note that these only apply within the MATH element and can't be
used in normal text!
-->
<!ENTITY REF1   STARTTAG   "SUP">
<!ENTITY REF2   ENDTAG     "SUP">
<!ENTITY REF3   STARTTAG   "SUB">
<!ENTITY REF4   ENDTAG     "SUB">
<!ENTITY REF5   STARTTAG   "BOX">
<!ENTITY REF6   ENDTAG     "BOX">

<!USEMAP MAP1   MATH>
<!USEMAP MAP2   SUP>
<!USEMAP MAP3   SUB>
<!USEMAP MAP4   BOX>

<!SHORTREF MAP1 "^" REF1
                "_" REF3
                "{" REF5 >

<!SHORTREF MAP2 "^" REF2
                "_" REF3
                "{" REF5 >

<!SHORTREF MAP3 "_" REF4
                "^" REF1
                "{" REF5 >

<!SHORTREF MAP4 "}" REF6
                "^" REF1
                "_" REF3
                "{" REF5 >

<!--
 The inclusion of %math and exclusion of %notmath is used here
 to alter the content model for the B, SUB and SUP elements,
 to limit them to formulae rather than general text elements.
-->

<!ENTITY % mathvec "VEC|BAR|DOT|DDOT|HAT|TILDE" -- common accents -->
<!ENTITY % mathface "B|T|BT" -- control of font face -->
<!ENTITY % math "BOX|ABOVE|BELOW|%mathvec|ROOT|SQRT|ARRAY|SUB|SUP|%mathface">
<!ENTITY % formula "#PCDATA|%math">

<!ELEMENT MATH - - (#PCDATA)* -(%notmath) +(%math)>
<!ATTLIST MATH
        id      ID      #IMPLIED
        class    NAMES   #IMPLIED -- e.g. class=chem -->

<!-- The BOX element acts as brackets. Delimiters are optional and
     stretch to match the height of the box. The OVER element is used
     when you want a line between numerator and denominator. This line
     is suppressed with the alternative ATOP element. CHOOSE acts like
     ATOP but adds enclosing round brackets as a convenience for binomial
     coefficients. Note the use of { and } as shorthand for <BOX> and
     </BOX> respectively:

                           1 + X
     {1 + X<OVER>Y}  is   _______
                             Y

                                 a + b
     {a + b<ATOP>c - d} is  
                                 c - d

     The delimiters are represented using the LEFT and RIGHT
     elements as in:

     {[<LEFT>x + y<RIGHT>]}   is   [ x + y ]
     {(<LEFT>a<RIGHT>]}       is   (a]
     {||<LEFT>a<RIGHT>||}     is   || a ||

     Use &lbrace; and &rbrace; for "{" and "}" respectively as
     these symbols are used as shorthand for BOX, e.g.

     {&lbrace;<LEFT>a+b<RIGHT>&rbrace;}  is  {a+b}

     You can stretch definite integrals to match the integrand, e.g.

     {&int;<SUB>a</SUB><SUP>b</SUP><LEFT>{f(x)<over>1+x} dx}

            b
            /  f(x)
            | ----- dx
            / 1 + x
            a

     Note the complex content model for BOX is a work around
     for the absence of support for infix operators in SGML.

     You can get oversize delimiters with the SIZE attribute,
     for example <BOX SIZE=large>(<LEFT>...<RIGHT>)</BOX>

     Note that the names of common functions are recognized
     by the parser without the need to use "&" and ";" around
     them, e.g. int, sum, sin, cos, tan, ...
-->

<!ELEMENT BOX - - ((%formula)*, (LEFT, (%formula)*)?,
                   ((OVER|ATOP|CHOOSE), (%formula)*)?,
                   (RIGHT, (%formula)*)?)>
<!ATTLIST BOX
        size  (normal|medium|large|huge) normal -- oversize delims -->

<!ELEMENT (OVER|ATOP|CHOOSE|LEFT|RIGHT) - O EMPTY>

<!-- Horizontal line drawn ABOVE contents
     The symbol attribute allows authors to supply
     an entity name for an accent, arrow symbol etc.
     Generalisation of LaTeX's overline command.
     
     e.g. <above sym=ssmile>x</above>
     places an upwardly turning curve above the "x"
 -->

<!ELEMENT ABOVE - - (%formula)+>
<!ATTLIST ABOVE sym ENTITY #IMPLIED>

<!-- Horizontal line drawn BELOW contents
     The symbol attribute allows authors to 
     supply an entity name for an arrow symbol etc.
     Generalisation of LaTeX's underline command.
 -->

<!ELEMENT BELOW - - (%formula)+>
<!ATTLIST BELOW sym ENTITY #IMPLIED>

<!-- Convenience tags for common accents:
     vec, bar, dot, ddot, hat and tilde
-->

<!ELEMENT (%mathvec) - - (%formula)+>

<!--
  T and BT are used to designate terms which should
  be rendered in an upright font (& bold face for BT)
-->

<!ELEMENT (T|BT) - - (%formula)+>
<!ATTLIST (T|BT) class NAMES #IMPLIED>

<!-- Roots  e.g. <ROOT>3<OF>1+x</ROOT> -->

<!ELEMENT ROOT - - ((%formula)+, OF, (%formula)+)>
<!ELEMENT OF - O (%formula)* -- what the root applies to -->

<!ELEMENT SQRT - - (%formula)* -- square root convenience tag -->

<!-- LaTeX like arrays. The COLDEF attribute specifies
     a single capital letter for each column determining
     how the column should be aligned, e.g. coldef="CCC"

        "L"     left
        "C"     center
        "R"     right
        
     An optional separator letter can occur between columns
     and should be one of + - or =, e.g. "C+C+C+C=C".
     Whitespace within coldef is ignored. By default, the
     columns are all centered.
     
     The ALIGN attribute alters the vertical position of the
     array as compared with preceding and following expressions.

     Use LDELIM and RDELIM attributes for delimiter entities.
     When the LABELS attribute is present, the array is
     displayed with the first row and the first column as
     labels displaced from the other elements. In this case,
     the first element of the first row should normally be
     left blank.

     Use &vdots; &cdots; and &ddots; for vertical, horizontal
     and diagonal ellipsis dots. Use &dotfill; to fill an array
     cell with horizontal dots (e.g. for a full row).
     Note &ldots; places the dots on the baseline, while &cdots;
     places them higher up.
-->

<!ELEMENT ARRAY - - (ROW)+>
<!ATTLIST ARRAY
        align (top|middle|bottom) middle -- vertical alignment --
        coldef  CDATA   #IMPLIED  -- column alignment and separator --
        ldelim  CDATA   #IMPLIED  -- stretchy left delimiter --
        rdelim  CDATA   #IMPLIED  -- stretchy right delimiter --
        labels (labels) #IMPLIED  -- TeX's \bordermatrix style -->

<!ELEMENT ROW - O (ITEM)*>
<!ELEMENT ITEM - O (%formula)*>
<!ATTLIST ITEM
        align   CDATA  #IMPLIED  -- override coldef alignment --
        colspan NUMBER 1         -- merge columns as per TABLE --
        rowspan NUMBER 1         -- merge rows as per TABLE -->

<!--================ Document Head ========================================-->

<![ %HTML.Deprecated [
    <!ENTITY % head.content "TITLE & ISINDEX? & BASE? & STYLE?
                              & META* & LINK* & RANGE* & NEXTID?">
]]>

<!ENTITY % head.nextid "">

<!ENTITY % head.content "TITLE & ISINDEX? & BASE? & STYLE?
                              & META* & LINK* & RANGE*">

<!ELEMENT HEAD O O  (%head.content)>

<!ELEMENT LINK - O EMPTY>
<!ATTLIST LINK
        href %URI #REQUIRED
        %linkExtraAttributes; >
        
<!ELEMENT RANGE - O EMPTY>
<!ATTLIST RANGE
        id    ID    #IMPLIED  -- for naming marked range --
        class NAMES #IMPLIED  -- for subclassing --
        from  IDREF #REQUIRED -- start of marked range --
        until IDREF #REQUIRED -- end of marked range --
        >

<!ELEMENT ISINDEX - O EMPTY>
<!ATTLIST ISINDEX
        href   %URI  #IMPLIED -- server handling queries --
        prompt CDATA #IMPLIED -- prompt message -->

<!--
    The BASE element gives the base URL for
    dereferencing relative URLs, e.g.

         <BASE href="http://foo.com/images">
         ...
         <IMG SRC="bar.gif">

    The image is deferenced to

         http://foo.com/images/bar.gif
-->

<!ELEMENT BASE - O EMPTY>
<!ATTLIST BASE
        id   ID    #IMPLIED
        href %URI; #REQUIRED
        >

<![ %HTML.Deprecated [
    <!ELEMENT NEXTID - O EMPTY>
    <!ATTLIST NEXTID N CDATA #REQUIRED>
]]>

<!ELEMENT META - O EMPTY    -- Generic Metainformation -->
<!ATTLIST META
        http-equiv  NAME    #IMPLIED  -- HTTP response header name  --
        name        NAME    #IMPLIED  -- metainformation name       --
        content     CDATA   #REQUIRED -- associated information     --
        >

<!--
    A style sheet can be associated with the document using the
    LINK element, e.g. <LINK rel=style href="housestyle.dsssl">.
    Style overrides can be placed in the document head using the
    STYLE element, e.g.

        <style notation=dsssl-lite>
           dsss-lite stuff
        </style>

    Later on in the document you can use:

        <h2 class=bigcaps>Header with bigger than normal capitals</h2>
        <p class=abstract>A paragraph with a unique style of its own
        ...
    
    Statements in the given style notation 
        
    The tag names, class and id attributes are used in the style sheet
    notation to describe how to render matching elements.
-->

<!ENTITY % style-notations "dsssl-lite | w3c-style">

<!--
<!NOTATION dsssl-lite PUBLIC
      "ISO/IEC 10179:1995//NOTATION DSSSL Style Language//EN">
      
<!NOTATION w3c-style PUBLIC "IETF/RFC nnn/W3C Style Language//EN">
-->

<!ELEMENT STYLE - O (#PCDATA)>
<!ATTLIST STYLE
    notation NOTATION (%style-notations;) #REQUIRED
>

<!--================ Document Structure ===================================-->

<!ENTITY % html.content "HEAD, BODY">

<!ELEMENT HTML O O  (%html.content)>
<!ENTITY % version.attr 'VERSION CDATA #FIXED "%HTML.Version;"'>

<!-- suggested roles are: TOC, DOC, DOCPART, HITLIST, DIALOG -->

<!ATTLIST HTML
        %version.attr;       -- report DTD version to application --
        urn   CDATA #IMPLIED -- universal resource name for this document --
        class NAMES #IMPLIED -- role of this document, eg table of contents --
        >

<!-- The END -->