org.archive.modules.extractor.Hop

/**
* The kind of "hop" from one URI to another.  Each hop type can be
* represented by a single character; strings of these characters can
* appear in logs.  Eg, "LLLX" means that a URI was three normal links from
* a seed, and then one speculative link.
*
* @author pjack
*/

   /** Navigation links, like A/@HREF. */
    NAVLINK('L'),
   
    /** Implied prerequisite links, like dns or robots. */
    PREREQ('P'),
   
    /** Embedded links necessary to render the page, like IMG/@SRC. */
    EMBED('E'),
   
    /**
     * Speculative/aggressively extracted links, perhaps embed or nav,
     * as in javascript. 
     */
    SPECULATIVE('X'),
   
    /**
     * Referral/redirect links, like header 'Location:' on a 301/302 response.
     */
    REFER('R'),

    /**
     * Inferred/implied links -- not necessarily literally in the source
     * material, but deduced by convention.
     */
    INFERRED('I');

猜你喜欢

转载自sharehua.iteye.com/blog/1751379