html-3.dtd

harvest是一个下载html网页得机器人

<!ENTITY % HTMLicons PUBLIC
  "-//IETF//ENTITIES icons for HTML//EN">
%HTMLicons;

<!--================ Entities for math symbols ============================-->

<!-- ISO subset chosen for use with the widely available Adobe math font -->

<!ENTITY % HTMLmath PUBLIC
  "-//IETF//ENTITIES Math and Greek for HTML//EN">
%HTMLmath;

<!--=================== Text Markup =======================================-->

<!ENTITY % font " U | S | TT | I | BIG | SMALL">

<!ENTITY % phrase "EM | STRONG | CODE | SAMP | KBD | VAR | CITE">

<!ENTITY % misc "Q | LANG | AU | DFN | PERSON | ACRONYM | ABBREV | INS | DEL">

<!ENTITY % special "TAB | MATH | A | IMG | BR">

<!ENTITY % notmath "%font | %phrase | %special | %misc">

<!ENTITY % text "#PCDATA | SUB | SUP | B | %notmath">


<!ENTITY % pre.exclusion "TAB|MATH|IMG|BIG|SMALL|SUB|SUP">

<!ELEMENT (%font|B|%phrase|%misc) - - (%text)+>
<!ATTLIST (%font|B|%phrase|%misc) %attrs;>

<!-- Subscripts and superscripts. The ALIGN attribute is only used for math -->

<!ELEMENT (SUB|SUP) - - (%text)+>
<!ATTLIST (SUB|SUP)
        %attrs;
        align (left|center|right) #IMPLIED
        >

<!-- Forced line break -->

<!ELEMENT BR    - O EMPTY>
<!ATTLIST BR
        %attrs;
        %needs; -- for control of text flow --
        >

<!-- Named left, center and right tab stops (independent of '\t' char) -->

<!ELEMENT TAB - O EMPTY>
<!ATTLIST TAB
        id       ID       #IMPLIED  -- defines named tab stop --
        indent   NUMBER   0         -- en units before new tab stop --
        to       IDREF    #IMPLIED  -- jump to named tab stop --
        align   (left|center|right|decimal) left
        dp      CDATA     #IMPLIED  -- decimal point e.g. dp="," --
        >

<!--================== Link Markup ========================================-->

<!--
     With HTML 3.0 you can use ID attributes on most elements for named
     link ends. The use of the NAME attribute on anchors is deprecated.

     Do we want to support arbitrary elements for link starts? This would
     involve adding HREF and related attributes to most elements.
-->

<![ %HTML.Deprecated [
    <!ENTITY % linkName "name CDATA #IMPLIED -- named link end --">
]]>

<!ENTITY % linkName "">


<!ENTITY % ToolBar "home|toc|index|glossary|copyright|
                    up|previous|next|help|bookmark"

        -- LINK RELationship values which are used to create toolbar
           buttons or menu items for navigation, where toc stands
           for table of contents and bookmark provides for an open
           ended set of links, i.e. you can use multiple bookmarks
           for key entry points. Use the optional TITLE attribute
           to override default names.
        -->

<!ENTITY % linkType "NAME"
        -- A definitive list will be specified at a later date.

           They are used

                a) by stylesheets to control how collections of
                   html nodes are rendered into printed documents

                b) for document specific toolbars/menus when used
                   with the LINK element in document head:

                    "home|toc|index|glossary|copyright|
                           up|previous|next|help|bookmark"

                   where toc stands for table of contents and
                   bookmark provides for an open ended set of links,
                   i.e. you can use several bookmarks for key entry
                   points. Use the optional TITLE attribute to
                   override default names.

                c) for hypertext paths or guided tours,
                   with REL=NODE and REL=PATH. 

                d) to make a link to a style sheet, e.g. rel=stylesheet
                   (used only with the LINK element).
                   
                e) to make a link to a separate banner, e.g. rel=banner
                   (used only with the LINK element).
        -->


<!ENTITY % linkExtraAttributes -- URN moved to %url.link --
       "rel %linkType #IMPLIED -- forward relationship type --
        rev %linkType #IMPLIED -- reversed relationship type
                                  to referent data --
        title   CDATA #IMPLIED -- advisory only --
        methods NAMES #IMPLIED -- supported public methods of the object:
                                        TEXTSEARCH, GET, HEAD, ... --
        ">

<![ %HTML.Deprecated [
    <!ENTITY % A.content "(%heading|%text)+">
]]>

<!ENTITY % A.content   "(%text)+">

<!ELEMENT A     - - %A.content -(A)>

<!ATTLIST A
        %attrs;
        href   %URI;  #IMPLIED
        %url.link;    -- standard link attributes --
        %linkName;     -- name attribute is deprecated; use ID instead --
        shape %SHAPE; #IMPLIED -- for shaped hotzones in FIGs --
        %linkExtraAttributes;
        >

<!--=================== Images ============================================-->

<!-- Desired widths are used for negotiating image size
     with the module responsible for painting the image.
     align=left or right cause image to float to margin
     and for subsequent text to wrap around image -->

<!ELEMENT IMG    - O EMPTY --  Embedded image -->
<!ATTLIST IMG
        %attrs;
        src  %URI;  #REQUIRED  -- URI of image to embed --
        %url.link;             -- standard link attributes --
        alt CDATA   #IMPLIED   -- for display in place of image --
        align  (top|middle|bottom|left|right) top -- relative to baseline
        --         width  NUMBER #IMPLIED -- desired width in en's or pixels --
        height NUMBER #IMPLIED -- desired height in en's or pixels --
        units  (en|pixels) pixels -- units for width and height --
        ismap (ismap) #IMPLIED -- pass clicks to server --
        >

<!--=================== Paragraphs=========================================-->

<!ELEMENT P     - O (%text)+>
<!ATTLIST P
        %attrs;
        align  (left|center|right|justify) #IMPLIED
        %needs; -- for control of text flow --
        nowrap (nowrap) #IMPLIED -- disable wordwrap --
        >

<!--=================== Headings, Titles, Sections ========================-->

<!ELEMENT HR    - O EMPTY -- customizable horizontal rule -->
<!ATTLIST HR
        %attrs;
        src     %URI;   #IMPLIED -- URI of custom rule graphic --
        %url.link;               -- standard link attributes --
        %needs; -- for control of text flow --
        >

<!--
  Headers can be numbered, although this is a matter for style sheets.
  The style sheet controls the numbering style:

     a) whether the parent numbering is inherited, e.g.  5.i.c
        where 5 is the current sequence number for H1 headers, and
        1 is the number for H2 headers and 3 for H3 headers.

     b) what style is used for current sequence number
        e.g. arabic, upperalpha, loweralpha, upperroman, lowerroman
        or a numbering scheme appropriate for the current language

  The skip attribute is used to skip over sequence numbers for items
  which have been left out of the list, e.g. skip=3 advances the
  sequence number past 3 omitted items. The seqnum sets the sequence
  number to a specified value. Note that the style sheet may take
  advantage of the sequence number for higher level headers.

  The dingbat or src attributes may be used to specify a bullet like
  image to be placed adjacent to the header. Defining this in the
  header element simplifies the document markup and avoids the need
  to use the clear or needs attribute in the following element to
  prevent it flowing around this image.
-->

<!ELEMENT ( %heading )  - -  (%text;)+>
<!ATTLIST ( %heading )
        %attrs;
        align  (left|center|right|justify) #IMPLIED
        %needs; -- for control of text flow --
        seqnum   NUMBER   #IMPLIED  -- starting sequence number --
        skip     NUMBER   0         -- skip seq nums for missing items --
        dingbat  ENTITY   #IMPLIED  -- dingbat entity from HTMLicons --
        src      %URI;  #IMPLIED  -- bullet defined by graphic --
        %url.link;                  -- standard link attributes --
        nowrap   (nowrap)  #IMPLIED -- disable wordwrap --
        >

<!ELEMENT TITLE - -  (#PCDATA)
          -- The TITLE element is not considered part of the flow of text.
             It should be displayed, for example as the page header or
             window title.
          -->

<!--=================== Text Flows ========================================-->

<!ENTITY % block
     "P | %list | DL
        | %preformatted
        | %blockquote
        | FORM | ISINDEX | FN
        | TABLE | FIG | NOTE">

<!--
  ((%block)* | (%text)*) would be much nicer as it would avoid the need
  for a <P> tag when all you want is a few words of text. The problem
  is that it also prevents: "<LI> <P>some text" since it forbids PCDATA
  and hence the white space between the <LI> and the <P>.
-->

<![ %HTML.Recommended [
    <!ENTITY % flow "(%block)*">
]]>

<!ENTITY % flow "(%text | %block)*">

<!ELEMENT PRE - - (%text)* -(%pre.exclusion)>

<!ATTLIST PRE
        %attrs;
        width NUMBER #implied
        %needs; -- for control of text flow --
        >

<![ %HTML.Obsoleted [

<!ENTITY % literal "CDATA"
        -- special non-conforming parsing mode where
           the only markup signal is the end tag
           in full. This will cause problems for
           standard SGML tools!
        -->

<!ELEMENT XMP - -  %literal>
<!ELEMENT LISTING - -  %literal>
<!ELEMENT PLAINTEXT - O %literal>

]]>

<!--=================== Lists =============================================-->

<!ELEMENT DL    - -  (LH?, (DT|DD)+) -- this is perhaps too lax? -->
<!ATTLIST DL
        %attrs;
        %needs; -- for control of text flow --
        compact (compact) #IMPLIED -- more compact style --
        >

<!ELEMENT DT    - O  (%text)+>
<!ELEMENT DD    - O  %flow;>
<!ATTLIST (DT|DD)
        %attrs;
        %needs; -- for control of text flow --
        >


<!ELEMENT (OL|UL) - -  (LH?, LI+) -- should we allow a list header ? -->

<!-- style sheet controls numbering style
    a) whether the parent numbering is inherited, e.g.  5.1.c
    b) what style is used for current sequence number
        e.g. arabic, upperalpha, loweralpha, upperroman, lowerroman
        or a numbering scheme for the current language
-->
<!ATTLIST OL
        %attrs;
        %needs; -- for control of text flow --
        continue (continue)  #IMPLIED   -- don't restart sequence number --
        seqnum    NUMBER     #IMPLIED   -- starting sequence number --
        compact (compact)    #IMPLIED   -- reduced interitem spacing --
        >

<!-- Unordered lists:

    o   single or multicolumn with
        horizontal or vertical wrapping

    o   plain or bulletted list items

    o   bullets can be customised via:
            - entities (dingbats in HTMLicons)
            - external graphic via URL
            - individual attributes on LI tags
-->
<!ATTLIST UL
        %attrs;
        %needs; -- for control of text flow --
        wrap (vert|horiz|none) none -- multicolumn list style --
        plain   (plain)  #IMPLIED   -- suppress bullets --
        dingbat  ENTITY  #IMPLIED   -- dingbat entity from HTMLicons --
        src     %URI;  #IMPLIED   -- bullet defined by graphic --
        %url.link;                  -- standard link attributes --
        compact (compact) #IMPLIED  -- reduced interitem spacing --
        >

<!ELEMENT LH - O (%text;)+ -- list header -->
<!ATTLIST LH %attrs;>

<!--
    For unordered lists, you can override the standard bullet with
    a custom graphic specified via a URI e.g. src="splash.gif" or
    a reference to one of the HTMLicons graphics e.g. dingbat=folder

    The skip attribute is used with ordered lists to skip over sequence
    numbers for items which have been left out of the list, e.g. skip=3
    advances the sequence number past 3 omitted items.
-->

<!ELEMENT LI - O %flow; -- list item -->
<!ATTLIST LI
        %attrs;
        %needs; -- for control of text flow --
        dingbat ENTITY #IMPLIED -- dingbat entity from HTMLicons --
        src  %URI; #IMPLIED   -- custom bullet graphic --
        %url.link;              -- standard link attributes --
        skip NUMBER 0           -- skip seq nums for missing items --
        >

<!-- DIR and MENU are now subsumed by UL with type=plain. Use the
     wrap attribute to control wrapping style for multicolumn lists -->

<![ %HTML.Deprecated [
    <!ELEMENT (DIR|MENU) - - (LI)+ -(%block)>
    <!ATTLIST (DIR|MENU)
        compact (compact) #IMPLIED>
]]>

<!--=================== Document Body =====================================-->