diffbot dev customizing - this is in HAML, just saved without the extension (Gists don't allow subdirs apparently)

diffbot

!!!
%html{:lang => "en"}
  %head
    %meta{:charset => "utf-8"}/
    %title Customize Instructions
    %meta{:content => "width=device-width, initial-scale=1.0", :name => "viewport"}/
    / Default styles
    %link{:href => "/dev/css/bootstrap.min.css", :rel => "stylesheet"}/
    %link{:href => "/dev/css/fonts.css", :rel => "stylesheet"}/
    %link{:href => "/dev/css/default.css", :rel => "stylesheet"}/
    %link{:href => "/dev/css/help.css", :rel => "stylesheet"}/
  %body.help
    .container-fluid.popup
      .tabbable.tabs-left
        %ul.nav.nav-tabs
          %li.active
            %a{"data-toggle" => "tab", :href => "#basic"} Basic Selectors
          %li
            %a{"data-toggle" => "tab", :href => "#combinators"} Combinators
          %li
            %a{"data-toggle" => "tab", :href => "#pseudo"} Pseudo Selectors
          %li
            %a{"data-toggle" => "tab", :href => "#filters"} Filters
          / <li><a href="#tips" data-toggle="tab">Tips and Examples</a></li>
        .tab-content
          #basic.tab-pane.active
            %h3.page-header Basic Selectors
            %table.table.table-bordered{:border => "0", :cellpadding => "5"}
              %tbody
                %tr
                  %th{:align => "left"} Pattern
                  %th{:align => "left"} Matches
                  %th{:align => "left"} Example
                %tr
                  %td
                    %code *
                  %td any element
                  %td
                    %code *
                %tr
                  %td
                    %code tagname
                  %td elements with the given tag name
                  %td
                    %code> div
                    ,
                    %code p
                %tr
                  %td
                    %code namespace|type
                  %td
                    elements of type 'type' in the namespace
                    %i ns
                  %td
                    %code fb|name
                    finds
                    %code <fb:name>
                    elements
                %tr
                  %td
                    %code #id
                  %td elements with attribute ID of "id"
                  %td
                    %code> div#container
                    ,
                    %code #header
                %tr
                  %td
                    %code .class
                  %td elements with a class name of "class"
                  %td
                    %code> div.left
                    ,
                    %code .post-body
                %tr
                  %td
                    %code element[attr]
                    or
                    %code [attr]
                  %td elements with an attribute named "attr" (with any value)
                  %td
                    %code> a[href]
                    ,
                    %code [title]
                %tr
                  %td
                    %code element[attr=val]
                    or
                    %code [attr=val]
                  %td elements with an attribute named "attr" and value equal to "val"
                  %td
                    %code> img[width=500]
                    ,
                    %code a[rel=nofollow]
                %tr
                  %td
                    %code [^attrPrefix]
                  %td elements with an attribute name starting with "attrPrefix". Use to find elements with HTML5 datasets
                  %td
                    %code> [^data-]
                    ,
                    %code div[^data-]
                %tr
                  %td
                    %code [attr^=valPrefix]
                  %td elements with an attribute named "attr", and value starting with "valPrefix"
                  %td
                    %code a[href^=http:]
                %tr
                  %td
                    %code [attr$=valSuffix]
                  %td elements with an attribute named "attr", and value ending with "valSuffix"
                  %td
                    %code img[src$=.png]
                %tr
                  %td
                    %code [attr*=valContaining]
                  %td elements with an attribute named "attr", and value containing "valContaining"
                  %td
                    %code a[href*=/search/]
                %tr
                  %td
                    %code
                      [attr~=
                      %em> regex
                      ]
                  %td elements with an attribute named "attr", and value matching the regular expression
                  %td
                    %code img[src~=(?i)\\.(png|jpe?g)]
                %tr
                  %td{:colspan => "2"}
                    %em The above may be combined in any order
                  %td
                    %code div.header[title]
          #combinators.tab-pane
            %h3.page-header Combinators
            %table.table.table-bordered{:border => "0", :cellpadding => "5"}
              %tbody
                %tr
                  %th{:align => "left"} Pattern
                  %th{:align => "left"} Matches
                  %th{:align => "left"} Example
                %tr
                  %td
                    %code E F
                  %td an F element descended from an E element
                  %td
                    %code> div a
                    ,
                    %code .logo h1
                %tr
                  %td
                    %code E > F
                  %td an F direct child of E
                  %td
                    %code ol > li
                %tr
                  %td
                    %code E + F
                  %td an F element immediately preceded by sibling E
                  %td
                    %code> li + li
                    ,
                    %code div.head + div
                %tr
                  %td
                    %code E ~ F
                  %td an F element preceded by sibling E
                  %td
                    %code h1 ~ p
                %tr
                  %td
                    %code E, F, G
                  %td all matching elements E, F, or G
                  %td
                    %code a[href], div, h3
          #pseudo.tab-pane
            %h3.page-header Pseudo Selectors
            %table.table.table-bordered{:border => "0", :cellpadding => "5"}
              %tbody
                %tr
                  %th{:align => "left"} Pattern
                  %th{:align => "left"} Matches
                  %th{:align => "left"} Example
                %tr
                  %td
                    %code
                      \:lt(
                      %em> n
                      )
                  %td
                    elements whose sibling index is less than
                    %em n
                  %td
                    %code td:lt(3)
                    finds the first 2 cells of each row
                %tr
                  %td
                    %code
                      \:gt(
                      %em> n
                      )
                  %td
                    elements whose sibling index is greater than
                    %em n
                  %td
                    %code td:gt(1)
                    finds cells after skipping the first two
                %tr
                  %td
                    %code
                      \:eq(
                      %em> n
                      )
                  %td
                    elements whose sibling index is equal to
                    %em n
                  %td
                    %code td:eq(0)
                    finds the first cell of each row
                %tr
                  %td
                    %code
                      \:has(
                      %em> selector
                      )
                  %td
                    elements that contains at least one element matching the
                    %em selector
                  %td
                    %code div:has(p)
                    finds divs that contain p elements
                %tr
                  %td
                    %code
                      \:not(
                      %em> selector
                      )
                  %td
                    elements that do not match the
                    %em selector
                  %td
                    %code div:not(.logo)
                    finds all divs that do not have the "logo" class.
                    %br/
                    %code div:not(:has(div))
                    finds divs that do not contain divs.
                %tr
                  %td
                    %code
                      \:contains(
                      %em> text
                      )
                  %td elements that contains the specified text. The search is case insensitive. The text may appear in the found element, or any of its descendants.
                  %td
                    %code p:contains(jsoup)
                    finds p elements containing the text "jsoup".
                %tr
                  %td
                    %code
                      \:matches(
                      %em> regex
                      )
                  %td elements whose text matches the specified regular expression. The text may appear in the found element, or any of its descendants.
                  %td
                    %code td:matches(\\d+)
                    finds table cells containing digits.
                    %code div:matches((?i)login)
                    finds divs containing the text, case insensitively.
                %tr
                  %td
                    %code
                      \:containsOwn(
                      %em> text
                      )
                  %td elements that directly contains the specified text. The search is case insensitive. The text must appear in the found element, not any of its descendants.
                  %td
                    %code p:containsOwn(jsoup)
                    finds p elements with own text "jsoup".
                %tr
                  %td
                    %code
                      \:matchesOwn(
                      %em> regex
                      )
                  %td elements whose own text matches the specified regular expression. The text must appear in the found element, not any of its descendants.
                  %td
                    %code td:matchesOwn(\\d+)
                    finds table cells directly containing digits.
                    %code div:matchesOwn((?i)login)
                    finds divs containing the text, case insensitively.
                %tr
                  %td{:colspan => "2"}
                    %em The above may be combined in any order and with other selectors.
                  %td
                    %code .light:contains(name):eq(0)
          #filters.tab-pane
            %h3.page-header Filters
            %p You can choose to filter the output of your selector(s) using three filter types.
            %table.table.table-bordered{:border => "0", :cellpadding => "5"}
              %tbody
                %tr
                  %th{:align => "left"} Filter
                  %th{:align => "left"} Description
                %tr
                  %td
                    %strong Attribute
                  %td
                    Retrieves the specified attribute value of an element. For example, to extract the link (http://blog.diffbot.com) from the anchor tag
                    = succeed "," do
                      %code <a href="http://www.blog.diffbot.com" class="outbound">
                    you would enter
                    %code HREF
                    as your attribute filter. You can only use a single attribute filter per rule.
                %tr
                  %td
                    %strong Ignore
                  %td Ignores the specified selectors (and all descendants) if they are found within the primary CSS selector. You may use any of the selector formats specified in this help screen.
                %tr
                  %td
                    %strong Replace
                  %td Allows you to specify match and replace regular expressions to alter the output returned by the Diffbot API. To remove matching content, simply leave the "replace with" field blank.
          /
            <div class="tab-pane" id="tips">
            <h3 class="page-header">Tips and Examples</h3>
            <p>Here are some common usages for custom rules:</p>
            <table class="table table-bordered" border="0" cellpadding="5">
            <tbody>
            <tr>
            <th align="left">How to...?</th>
            <th align="left">Details</th>
            </tr>
            <tr>
            <td>Extract <code>META</code> values from a page.</td>
            <td>Use the <code>element[attr=val]</code> selector, along with an Attribute filter. For instance, to extract the Application Name from <code>&lt;meta name="application-name" content="Diffbot"&gt;</code>, use a selector of <code>meta[name=application-name]</code> and an Attribute filter of <code>content</code>.</td>
            </tr>
            <tr>
            <td>Repeat the same content from multiple domains.</td>
            <td>Use the <code>element[attr=val]</code> selector, along with an Attribute filter. For instance, to extract the Application Name from <code>&lt;meta name="application-name" content="Diffbot"&gt;</code>, use a selector of <code>meta[name=application-name]</code> and an Attribute filter of <code>content</code>.</td>
            </tr>
            </div>
    %script{:src => "/dev/js/libs/jquery/jquery-1.7.2.min.js"}
    %script{:src => "/dev/js/libs/bootstrap/bootstrap.min.js"}
    %script{:src => "/dev/js/libs/bootstrap/tab.js"}
    %script{:src => "//static.getclicky.com/js", :type => "text/javascript"}
    :javascript
      try{ clicky.init(66589068); }catch(e){}    %noscript
      %p
        %img{:alt => "Clicky", :height => "1", :src => "//in.getclicky.com/66589068ns.gif", :width => "1"}/