抓捕腾讯音乐MV前100页的点击量
[root@dou ~]# cat 2.pl
#!/usr/local/bin/perl
use strict;
use Web::Scraper;
use URI;
my $num;
my $total;
my @pathnums = (0..99);
my @xpathnums = (1..28);
my @firstnums = (0..9) x 10;
my $firstnum = 0;
my $file = "tengxun";
my $i = 0;
foreach my $pathnum (@pathnums) {
my $html = "http://v.qq.com/mvlist/$firstnums[$firstnum]/22\_-1\_-1\_-1\_-1\_1\_$pathnum\_0\_28.html";
my $uri = URI->new($html);
foreach my $xpathnum (@xpathnums) {
my $xpath = "//\*\[\@id=\"content\"\]/ul/li\[$xpathnum\]/p\[2\]/span";
my $scraper = scraper {
process "$xpath",'key' => 'TEXT';
};
my $result = $scraper->scrape($uri);
$num = $result->{key};
open (my $fh,'>>',"$file") or die "can't create file $file: $!\n";
print "hello $i++\n";
print $fh "$pathnum ------ $xpathnum\n";
print $fh "$num\n";
$total += $result->{key};
}
$firstnum += 1;
}
print "$total\n";
转载于:https://blog.51cto.com/perfect/1068604