html-3.dtd

harvest是一个下载html网页得机器人

<![ %HTML.Recommended [
        <!ENTITY % body.content "(DIV|%heading|%block|HR|ADDRESS)*"
        -- <h1>Heading</h1>
           <p>Text ...
                is preferred to
           <h1>Heading</h1>
           Text ...
        -->
]]>

<!ENTITY % body.content "(DIV | %heading | %text | %block | HR | ADDRESS)*">

<!ELEMENT BODY O O  (BANNER?, BODYTEXT) +(SPOT)>
<!ATTLIST BODY
        %attrs;
        background %URI; #IMPLIED  -- texture tile for document background --
        >

<!ELEMENT BODYTEXT O O %body.content -- dummy element -->

<!-- 
  The BANNER element is used for a banner section which appears at
  the top of the window and doesn't scroll with window contents.
  This can be used for corporate logos, copyright statements and
  disclaimers, as well as customized navigation/search controls.
-->
<!ELEMENT BANNER - - %body.content>
<!ATTLIST BANNER %attrs; >

<!-- SPOT is used to insert IDs at arbitrary places
     e.g. for end points of a marked range (see RANGE) -->
<!ELEMENT SPOT - O EMPTY>
<!ATTLIST SPOT id ID #REQUIRED>

<!ELEMENT (%blockquote) - - (BODYTEXT, CREDIT?)>
<!ATTLIST (%blockquote)
        %attrs;
        %needs; -- for control of text flow --
        nowrap   (nowrap)  #IMPLIED -- disable wordwrap --
        >

<!ENTITY % address.content "((%text;)* | P*)">

<!ELEMENT ADDRESS - - %address.content>
<!ATTLIST ADDRESS
        %attrs;
        %needs; -- for control of text flow --
        >
        
<!--
  DIV can be used with the CLASS attribute to represent different
  kinds of container, e.g. chapter, section, abstract, appendix.
-->

<!ELEMENT DIV - - %body.content>
<!ATTLIST DIV
        %attrs;
        %needs; -- for control of text flow --
        align   (left|center|right) left -- alignment of following text --
        nowrap   (nowrap)  #IMPLIED -- disable wordwrap --
        >

<!--================ Forms ===============================================-->

<!--
    As HTML 2.0 plus a few extensions:

        a)  A RANGE control which varies between pair of values
            specified with the size attribute, e.g. SIZE="1, 10"

        b)  FILE widget for uploading one or more files to a server

        c)  SCRIBBLE on image widget that sends the "ink" to the server

        d)  SUBMIT/RESET buttons can now be customised with an image.
            This subsumes the IMAGE type which is now deprecated.

        e)  Graphical SELECTion menus are now supported, using
            the new SHAPE attribute on OPTION elements.

    Further extensions are in the pipeline (e.g. table entry,
    multiple data formats for textarea fields and client-side
    scripts with custom widgets) but will have to wait until
    the backlog of implementation work diminishes.
-->

<!ELEMENT FORM - - %body.content -(FORM) +(INPUT|SELECT|TEXTAREA)>
<!ATTLIST FORM
        action %URI #REQUIRED -- server-side form handler --
        method (%HTTP-Method) GET -- see HTTP specification --
        enctype %Content-Type; "application/x-www-form-urlencoded"
        script %URI #IMPLIED -- link to client-side script --
        >

<![ %HTML.Deprecated [
    <!ENTITY % InputType "(TEXT | PASSWORD | CHECKBOX | RADIO | SUBMIT
                   | RESET | RANGE | FILE | SCRIBBLE | HIDDEN | IMAGE)">
]]>

<!ENTITY % InputType "(TEXT | PASSWORD | CHECKBOX | RADIO | SUBMIT
                   | RESET | RANGE | FILE | SCRIBBLE | HIDDEN)">

<!ELEMENT INPUT - O EMPTY>
<!ATTLIST INPUT
        %attrs;
        type %InputType TEXT
        name  NAME  #IMPLIED       -- required for all but submit and reset --         
        value CDATA #IMPLIED       -- required for radio buttons & checkboxes --
        disabled (disabled) #IMPLIED -- read-only fields --
        error CDATA #IMPLIED       -- why field is in error --
        checked (checked) #IMPLIED -- for radio buttons and check boxes --
        size NUMBER #IMPLIED       -- visible width of TEXT fields --
        maxlength NUMBER #IMPLIED  -- max number of chars for TEXT fields --
        min %REAL #IMPLIED         -- lower limit for RANGE fields --
        max %REAL #IMPLIED         -- upper limit for RANGE fields --
        accept CDATA #IMPLIED      -- list of MIME types for file fields --
        src   %URI  #IMPLIED       -- for fields with background images --
        %url.link;                 -- standard link attributes --
        align  (top|middle|bottom|left|right) top
        >

<!--
  SRC attribute added for graphical selection menus
  The WIDTH, HEIGHT and UNITS attributes apply to the
  image specified by the SRC attribute.
 -->

<!ELEMENT SELECT - - (OPTION+) -(INPUT|TEXTAREA|SELECT)>
<!ATTLIST SELECT
        %attrs;
        name CDATA #REQUIRED
        multiple (multiple) #IMPLIED
        disabled (disabled) #IMPLIED -- read-only menu --
        error CDATA #IMPLIED   -- why selections are in error --
        src  %URI  #IMPLIED    -- for graphical selection menus --
        %url.link;             -- standard link attributes --
        width  NUMBER #IMPLIED -- desired width of in en's or pixels --
        height NUMBER #IMPLIED -- desired height in en's or pixels --
        units  (en|pixels) pixels -- units for width and height --
        align  (top|middle|bottom|left|right) top
        >

<!ELEMENT OPTION - O (#PCDATA)>
<!ATTLIST OPTION
        %attrs;
        selected (selected) #IMPLIED
        value  CDATA  #IMPLIED -- default to element content --
        shape %SHAPE; #IMPLIED -- for graphical selection menus --
        disabled (disabled) #IMPLIED -- unselectable option --
        error CDATA #IMPLIED   -- why this choice is in error --
        >

<!--
  Multi-line text input field. align=left or right
  causes the field to float to margin and for
  subsequent text to wrap around the field.
-->
     
<!ELEMENT TEXTAREA - - (#PCDATA) -(INPUT|TEXTAREA|SELECT)>
<!ATTLIST TEXTAREA
        %attrs;
        name CDATA #REQUIRED
        rows NUMBER #REQUIRED
        cols NUMBER #REQUIRED
        disabled (disabled) #IMPLIED -- read-only field --
        error CDATA #IMPLIED         -- why field is in error --
        align  (top|middle|bottom|left|right) top
        >

<!--======================= Captions ======================================-->

<!ELEMENT CAPTION - - (%text;)+ -- table or figure caption -->
<!ATTLIST CAPTION
        %attrs;
        align (top|bottom|left|right) #IMPLIED
        >
<!--======================= Tables ========================================-->

<!--
    Tables and figures can be aligned in several ways:

    bleedleft   flush left with the left (window) border
    left        flush left with the left text margin
    center      centered (text flow is disabled for this mode)
    right       flush right with the right text margin
    bleedright  flush right with the right (window) border
    justify     when applicable the table/figure should stretch
                to fill space between the text margins

    Note: text will flow around the table or figure if the browser
    judges there is enough room and the alignment is not centered
    or justified. The table or figure may itself be part of the
    text flow around some earlier figure. You can in this case use
    the clear or needs attributes to move the new table or figure
    down the page beyond the obstructing earlier figure. Similarly,
    you can use the clear or needs attributes with other elements
    such as headers and lists to move them further down the page.
-->

<!ENTITY % block.align
        "align  (bleedleft|left|center|right|bleedright|justify) center">

<!--
    The HTML 3.0 table model has been chosen for its simplicity
    and the ease in writing filters from common DTP packages.

    By default the table is automatically sized according to the
    cell contents and the current window size. Specifying the columns
    widths using the colspec attribute allows browsers to start
    displaying the table without having to wait for last row.

    The colspec attribute is a list of column widths and alignment
    specifications. The columns are listed from left to right with
    a capital letter followed by a number, e.g. COLSPEC="L20 C8 L40".
    The letter is L for left, C for center, R for right alignment of
    cell contents. J is for justification, when feasible, otherwise
    this is treated in the same way as L for left alignment.
    Column entries are delimited by one or more space characters.
    
    The number specifies the width in en's, pixels or as a
    fractional value of the table width, as according to the
    associated units attribute. This approach is more compact
    than used with most SGML table models and chosen to simplify
    hand entry. The width attribute allows you to specify the
    width of the table in pixels, en units or as a percentage
    of the space between the current left and right margins.

    To assist with rendering to speech, row and column headers
    can be given short names using the AXIS attribute. The AXES
    attribute is used to explicitly specify the row and column
    names for use with each cell. Otherwise browsers can follow
    up columns and left along rows (right for some languages)
    to find the corresponding header cells.

    Table content model: Braille limits the width of tables,
    placing severe limits on column widths. User agents need
    to render big cells by moving the content to a note placed
    before the table. The cell is then rendered as a link to
    the corresponding note.

    To assist with formatting tables to paged media, authors
    can differentiate leading and trailing rows that are to
    be duplicated when splitting tables across page boundaries.
    The recommended way is to subclass rows with the CLASS attribute
    For example: <TR CLASS=Header>, <TR CLASS=Footer> are used for
    header and footer rows. Paged browsers insert footer rows at
    the bottom of the current page and header rows at the top of
    the new page, followed by the remaining body rows.
-->

<!ELEMENT TABLE - - (CAPTION?, TR*) -- mixed headers and data -->
<!ATTLIST TABLE
        %attrs;
        %needs; -- for control of text flow --
        border (border) #IMPLIED -- draw borders --
        colspec CDATA   #IMPLIED -- column widths and alignment --
        units  (en|pixels|relative) en -- units for column widths --
        dp      CDATA   #IMPLIED -- decimal point e.g. dp="," --
        width NUMBER    #IMPLIED -- absolute or percentage width --
        %block.align;  -- horizontal alignment --
        noflow (noflow) #IMPLIED -- noflow around table --
        nowrap (nowrap) #IMPLIED -- don't wrap words --
        >

<!ENTITY % cell "TH | TD">
<!ENTITY % horiz.align "left|center|right|justify">
<!ENTITY % vert.align  "top|middle|bottom|baseline">

<!--
    Browsers should tolerate an omission of the first <TR>
    tag as it is implied by the context. Missing trailing
    <TR>s implied by rowspans should be ignored.

    The alignment attributes act as defaults for rows
    overriding the colspec attribute and being in turn
    overridden by alignment attributes on cell elements.
    Use valign=baseline when you want to ensure that text
    in different cells on the same row is aligned on the
    same baseline regardless of fonts. It only applies
    when the cells contain a single line of text.
-->

<!ELEMENT TR - O (%cell)* -- row container -->
<!ATTLIST TR
        %attrs;
        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 --
        >

<!--
    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 --
        >