AI时代，找源码已成为过去式，纪念我过去的十年0(回)
69天前
还有人吗2(回)
87天前会python真的可以为所欲为0(回)
567天前
这里还有人吗2(回)
752天前这里还有人吗0(回)
752天前
每天面对着电脑屏幕，敲打键盘。我所面对的并不只是代码，而是一种生活方式。0(回)
977天前#----------------------------- |
use HTML::LinkExtor; |
$parser = HTML::LinkExtor->new ( undef, $base_url ); |
$parser->parse_file ( $filename ); |
@links = $parser->links; |
foreach $linkarray ( @links ) |
{ |
my @element = @$linkarray; |
my $elt_type = shift @element; |
# element type |
# possibly test whether this is an element we're interested in |
while (@element) { |
# extract the next attribute and its value |
my ($attr_name, $attr_value) = splice(@element, 0, 2); |
# ... do something with them ... |
} |
} |
#----------------------------- |
<A HREF="http://www.perl.com/">Home page</A> |
<IMG SRC="images/big.gif" LOWSRC="images/big-lowres.gif"> |
#----------------------------- |
[ |
[ a, href => "http://www.perl.com/" ], |
[ img, src => "images/big.gif", |
lowsrc => "images/big-lowres.gif" ] |
] |
#----------------------------- |
if ($elt_type eq 'a' && $attr_name eq 'href') { |
print "ANCHOR: $attr_value\n" |
if $attr_value->scheme =~ /http|ftp/; |
} |
if ($elt_type eq 'img' && $attr_name eq 'src') { |
print "IMAGE: $attr_value\n"; |
} |
#----------------------------- |
# download the following standalone program |
#!/usr/bin/perl -w |
# xurl - extract unique, sorted list of links from URL |
use HTML::LinkExtor; |
use LWP::Simple; |
$base_url = shift; |
$parser = HTML::LinkExtor->new(undef, $base_url); |
$parser->parse(get($base_url))->eof; |
@links = $parser->links; |
foreach $linkarray (@links) { |
my @element = @$linkarray; |
my $elt_type = shift @element; |
while (@element) { |
my ($attr_name , $attr_value) = splice(@element, 0, 2); |
$seen{$attr_value}++; |
} |
} |
for (sort keys %seen) { print $_, "\n" } |
#----------------------------- |
#% xurl http://www.perl.com/CPAN |
#ftp://ftp@ftp.perl.com/CPAN/CPAN.html |
# |
#http://language.perl.com/misc/CPAN.cgi |
# |
#http://language.perl.com/misc/cpan_module |
# |
#http://language.perl.com/misc/getcpan |
# |
#http://www.perl.com/index.html |
# |
#http://www.perl.com/gifs/lcb.xbm |
#----------------------------- |
<URL:http://www.perl.com> |
#----------------------------- |
@URLs = ($message =~ /<URL:(.*?)>/g); |
#----------------------------- |
by: 发表于：2017-09-18 17:49:34 顶(0) | 踩(0) 回复
？？
回复评论