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 
#
Bibliographic	Author			^%A[ \t]+.*$
Bibliographic	Title			^%T[ \t]+.*$
#
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]+.*$
#
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		^.*$