以前写的淘宝卖家卖出商品数量价格查询小工具 - Chinaunix

#!/usr/bin/perl -w
#####################################
#淘宝卖家卖出商品数量价格查询 #
#BY cgi.net <loveme1314@sakuras.cn> #
#http://blog.sakuras.cn #
#####################################
use strict;
use LWP::UserAgent;
use HTTP::Cookies;
use HTML::TreeBuilder;
#use HTTP::Request;
#use Data::Dumper;
$|=1;
my $url='http://rate.taobao.com/user-rate-a2af4af68a32e8f046e8703fed064284.htm';
#查询天数
my $day = 7;
#设置显示列表
my %conf = (
num => 1,
tite => 1,
price => 1,
url => 0,
);
###########################################################
$url =~ /rate\-(.*)\.htm/;
my $user = $1;
my @ns_headers = (
'User-Agent' => 'Mozilla/4.76 [en] (Win2000; U)',
'Accept' => 'image/gif, image/x-xbitmap, image/jpeg,
image/pjpeg, image/png, */*',
'Accept-Charset' => 'iso-8859-1,*,utf-8',
'Accept-Language' => 'en-US',
);
#只查看好评过的商品
our $good_url = "http://rate.taobao.com/user-rate-$user--detailed|1--goodNeutralOrBad|1--timeLine|-$day--receivedOrPosted|0--buyerOrSeller|0.htm#RateType";
our %count;
while ( $good_url )
{
#print '>>1' . $good_url ."\r\n";
_get_data ( $good_url );
}
#生成列表清单并排序
map { $count{$_}->{sort} = sprintf('%s', $count{$_}->{'num'} ) } keys %count;
my @marksorted = sort { $count{$b}->{sort} <=> $count{$a}->{sort} } keys %count;
foreach ( @marksorted )
{
$count{$_}->{'num'} = '' unless $conf{num} ;
$count{$_}->{'tite'} = '' unless $conf{tite} ;
$count{$_}->{'price'} = '' unless $conf{price} ;
$count{$_}->{'url'} = '' unless $conf{url} ;
print sprintf ("%u\t%s\t%s\t%s\r\n",$count{$_}->{'num'},$count{$_}->{'tite'},$count{$_}->{'price'},$count{$_}->{'url'});
}
exit;
sub _get_data
{
my $good_url_new = shift || exit;
#开始访问页面
my $browser=LWP::UserAgent->new;
my $tree = new HTML::TreeBuilder;
my $resp =$browser->get($good_url_new,@ns_headers);
die $resp->message ,$resp->status_line unless $resp->is_success;
$tree->parse( $resp->content );
#获取物品价格
our @prices;
foreach my $tmp2 ( $tree->look_down( '_tag' , 'span' , 'class' , 'price' ) )
{
push @prices , $tmp2;
}
#获取物品名称
foreach my $tmp1 ( $tree->look_down( '_tag' , 'p' , 'class' , 'exp' ) )
{
my $list = $tmp1->look_down('_tag', 'a');
my $tmp2 = shift @prices;
my $list2 = $tmp2->look_down('_tag', 'em');
#$list->dump();
#$list2->dump();
count($list->attr('title'),$list->attr('href'),$list2->as_text);
$tmp1->delete;
}
#获取总页数
my $pages = 0;
foreach ( $tree->look_down( '_tag', 'a',
sub {
if ($_[0]->as_HTML('<>&',' ',{}) =~ /\&gt\;\&gt\;/ig)
{$pages = $_[0]->attr('href')}
}
) ){};
$tree = undef;
#print '>>2' . $pages . "\r\n";
if ( $pages ) {
$good_url = $pages;
}
else{ $good_url = $pages ;}
}
sub count
{
my ($tite,$url,$price) = @_;
my $id = _return_id($url);
#print $id . "\n";
if ( exists $count{$id} )
{
++($count{$id}->{'num'}) ;
}
else{
$count{$id} = { 'num' =>1 , 'tite' => $tite , 'url' => $url ,'price' => $price };
}
}
sub _return_id
{
my $content = shift;
#$content =~ /auction1\.taobao\.com\/auction\/snap_detail\.htm\?trade_id=(\d+)&auction_id=([0-9a-z]+)/ig;
$content =~ /auction_id=([0-9a-z]+)/ig;
return $1;
}

复制代码