#----------------------------- |
use LWP::Simple; |
$content = get ( $URL ); |
#----------------------------- |
use LWP::Simple; |
unless ( defined ( $content = get $URL ) ) |
{ |
die "could not get $URL\n" ; |
} |
#----------------------------- |
# download the following standalone program |
#!/usr/bin/perl -w |
# titlebytes - find the title and size of documents |
use LWP::UserAgent; |
use HTTP::Request; |
use HTTP::Response; |
use URI::Heuristic; |
my $raw_url = shift or die "usage: $0 url\n" ; |
my $url = URI::Heuristic::uf_urlstr ( $raw_url ); |
$| = 1; |
# to flush next line |
printf "%s =>\n\t" , $url ; |
my $ua = LWP::UserAgent->new(); |
$ua ->agent ( "Schmozilla/v9.14 Platinum" ); |
# give it time, it'll get there |
my $req = HTTP::Request->new(GET => $url ); |
$req ->referer( "http://wizard.yellowbrick.oz" ); |
# perplex the log analysers |
my $response = $ua ->request( $req ); |
if ( $response ->is_error()) { |
printf " %s\n" , $response ->status_line; |
} else { |
my $count ; |
my $bytes ; |
my $content = $response ->content(); |
$bytes = length $content ; |
$count = ( $content =~ tr /\n/\n/); |
printf "%s (%d lines, %d bytes)\n" , $response ->title(), $count , $bytes ; } |
#----------------------------- |
#% titlebytes http://www.tpj.com/ |
#http://www.tpj.com/ => |
# The Perl Journal (109 lines, 4530 bytes) |
#----------------------------- |
by: 发表于:2017-09-18 17:49:12 顶(0) | 踩(0) 回复
??
回复评论