quick-sum.cf

harvest是一个下载html网页得机器人

#
#  quick-sum.cf - Regular Expressions to quickly extract attributes/values
#
#  Type	<TAB> Attribute	<TAB> RE 
#

#
#  ReferBibliographic - for use with refer bibliographies
#
ReferBibliographic	Author			^%A[ \t]+.*$
ReferBibliographic	City			^%C[ \t]+.*$
ReferBibliographic	Date			^%D[ \t]+.*$
ReferBibliographic	Editor			^%E[ \t]+.*$
ReferBibliographic	Comments		^%H[ \t]+.*$
ReferBibliographic	Issuer			^%I[ \t]+.*$
ReferBibliographic	Journal			^%J[ \t]+.*$
ReferBibliographic	Keywords		^%K[ \t]+.*$
ReferBibliographic	Label			^%L[ \t]+.*$
ReferBibliographic	Number			^%N[ \t]+.*$
ReferBibliographic	Comments		^%O[ \t]+.*$
ReferBibliographic	Page-Number		^%P[ \t]+.*$
ReferBibliographic	Unpublished-Info	^%R[ \t]+.*$
ReferBibliographic	Series-Title		^%S[ \t]+.*$
ReferBibliographic	Title			^%T[ \t]+.*$
ReferBibliographic	Volume			^%V[ \t]+.*$
ReferBibliographic	Abstract		^%X[ \t]+.*$

#
#  Below is the same as the default configuration...
#
Command		Keywords		^#.*$
#
Font		Keywords		^[cC][oO][mM][mM][eE][nN][tT][ \t]+.*$
#
Mail		Author			^From:[ \t]+.*$
Mail		Title			^Subject:[ \t]+.*$
Mail		Received-By		^To:[ \t]+.*$
#
Makefile	Keywords		^[-.A-Za-z]+:.*$
Makefile	Keywords		^#[ \t]+.*$
#
Bibliographic	Author			^%A[ \t]+.*$
Bibliographic	Title			^%T[ \t]+.*$
#
News		Author			^From:[ \t]+.*$
News		Title			^Subject:[ \t]+.*$
News		Abstract		^Summary:[ \t]+.*$
News		Keywords		^Keywords:[ \t]+.*$
News		Keywords		^Organization:[ \t]+.*$
News		Keywords		^Newsgroups:[ \t]+.*$
#
Patch		Keywords		^Index: .*$
Patch		Keywords		^diff[ \t]+.*$
#
Perl		Keywords		^sub[ \t]+.*{$
Perl		Keywords		^#[ \t]+.*$
#
README		Full-Text		^.*$