mirror of
https://github.com/internetarchive/heritrix3.git
synced 2026-07-11 10:07:18 +00:00
158 lines
4.0 KiB
ReStructuredText
158 lines
4.0 KiB
ReStructuredText
Bean Reference
|
|
==============
|
|
|
|
.. note::
|
|
This reference is a work in progress and does not yet cover all available beans. For a more complete list of
|
|
Heritrix beans please refer to the `javadoc <https://www.javadoc.io/doc/org.archive.heritrix/heritrix-modules>`_.
|
|
|
|
Fetch Processors
|
|
----------------
|
|
|
|
FetchDNS
|
|
~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/fetcher/FetchDNS.java
|
|
|
|
FetchFTP
|
|
~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/fetcher/FetchFTP.java
|
|
|
|
FetchHTTP
|
|
~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/fetcher/FetchHTTP.java
|
|
|
|
FetchSFTP
|
|
~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/fetcher/FetchSFTP.java
|
|
|
|
FetchWhois
|
|
~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/fetcher/FetchWhois.java
|
|
|
|
Link Extractors
|
|
---------------
|
|
|
|
ExtractorChrome (contrib)
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../contrib/src/main/java/org/archive/modules/extractor/ExtractorChrome.java
|
|
|
|
ExtractorCSS
|
|
~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/extractor/ExtractorCSS.java
|
|
|
|
ExtractorDOC
|
|
~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/extractor/ExtractorDOC.java
|
|
|
|
ExtractorHTML
|
|
~~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/extractor/ExtractorHTML.java
|
|
|
|
AggressiveExtractorHTML
|
|
~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/extractor/AggressiveExtractorHTML.java
|
|
|
|
JerichoExtractorHTML
|
|
~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/extractor/JerichoExtractorHTML.java
|
|
|
|
ExtractorHTMLForms
|
|
~~~~~~~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/forms/ExtractorHTMLForms.java
|
|
|
|
ExtractorHTTP
|
|
~~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/extractor/ExtractorHTTP.java
|
|
|
|
ExtractorImpliedURI
|
|
~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/extractor/ExtractorImpliedURI.java
|
|
|
|
ExtractorJS
|
|
~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/extractor/ExtractorJS.java
|
|
|
|
KnowledgableExtractorJS (contrib)
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../contrib/src/main/java/org/archive/modules/extractor/KnowledgableExtractorJS.java
|
|
|
|
ExtractorMultipleRegex
|
|
~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/extractor/ExtractorMultipleRegex.java
|
|
|
|
ExtractorPDF
|
|
~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/extractor/ExtractorPDF.java
|
|
|
|
ExtractorPDFContent (contrib)
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../contrib/src/main/java/org/archive/modules/extractor/ExtractorPDFContent.java
|
|
|
|
ExtractorRobotsTxt
|
|
~~~~~~~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/extractor/ExtractorRobotsTxt.java
|
|
|
|
ExtractorSitemap
|
|
~~~~~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/extractor/ExtractorSitemap.java
|
|
|
|
ExtractorSWF
|
|
~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/extractor/ExtractorSWF.java
|
|
|
|
ExtractorUniversal
|
|
~~~~~~~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/extractor/ExtractorUniversal.java
|
|
|
|
ExtractorURI
|
|
~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/extractor/ExtractorURI.java
|
|
|
|
ExtractorXML
|
|
~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/extractor/ExtractorXML.java
|
|
|
|
ExtractorYoutubeDL (contrib)
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../contrib/src/main/java/org/archive/modules/extractor/ExtractorYoutubeDL.java
|
|
|
|
ExtractorYoutubeFormatStream (contrib)
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../contrib/src/main/java/org/archive/modules/extractor/ExtractorYoutubeFormatStream.java
|
|
|
|
ExtractorYoutubeChannelFormatStream (contrib)
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../contrib/src/main/java/org/archive/modules/extractor/ExtractorYoutubeChannelFormatStream.java
|
|
|
|
TrapSuppressExtractor
|
|
~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. bean-doc:: ../modules/src/main/java/org/archive/modules/extractor/TrapSuppressExtractor.java
|