php 利用curl，正则表达式做的一个php蜘蛛抓取器(2)

std.php

<?php
global $std;
$std = array(
    'url' => '[0-9a-zA-Z\.\:\-\/%_#;&]+',
    'img' => '/(?is)<img.*?src=(?:[\'"]{0,1})([0-9a-zA-Z\.\:\-\/%_#;&]+)(?:[\'"]{0,1}).*?>/',
);

test.php

<?php
/**      
 * test.php
 *
 * @author     xzfred <xzfred@gmail.com>
 * @copyright  2009 fengone.com
 * @created    2010-12-07 .
 * @version    $Id: php.php 3 2008-10-10 07:49:21Z fred $
 * SVNPath     $HeadURL: http://192.168.0.16/svn/vim/skeletons/php.php $         
 */
/*
include_once "std.php";
include_once "lady_163_com.php";
 */
include_once $GLOBALS['g_dir_core'] . "get.php";

//================================================================================
include_once DIR_HOST_TAG . '/tuku_ent_china_com.php';
$obj = new FcHtmlParse($site);
$c = $obj->parse(file_get_contents("http://tuku.ent.china.com/fun/html/2011-08-23/181703.xml"));
echo "\n\n\n ===================\n";
echo $c['field']['tag1'][0];
echo "\n\n\n ===================\n";
var_dump($c);

exit();
//列表测试
$obj = new FcHtmlParse($site_list);
$c = $obj->parse(file_get_contents("http://tuku.ent.china.com/fun/html/3569_1.html"));
var_dump($c);
exit();
/*

$obj = new FcHtmlGet($site);
$c = $obj->getPage('http://star.pclady.com.cn/entertainment/ss/1106/703240.html');
var_dump($c);

$obj = new FcHtmlGet($site);
$c = $obj->getPage('http://star.pclady.com.cn/entertainment/ss/1106/703240.html');
var_dump($c);

$obj = new FcHtmlParse($site);
$img_obj = new FcHtmlImgUpload($site);

$data = file_get_contents("e:/b.html");
$c = $obj->parse($data);
$ic = $img_obj->upload($c['tag']['tag1'][0]);
var_dump($ic);

$data = file_get_contents("e:/a.html");
$c = $obj->parse($data);
$ic = $img_obj->upload($c['tag']['tag1'][0]);
var_dump($ic);
 */

//var_dump($c['tag']['tag1']);

tuku_ent_china_com.php

<?php
include_once $GLOBALS['g_dir_core'] . 'host/std.php';

$site = array(
    'aname'     => '中华网娱乐图库',
    'domain'    => 'tuku.ent.china.com',
    'dirname'   => '目录名称，用于匹配基于目录不同的正文',
    'gettype'   => 'default',
    //获取主文件
    'creg'      => '/(?si)(<list>.*?<\/list>)/',
    'code'      => 'utf-8',
    'sub'       => '获取子目录正则',
    'content'   => 'tag1',
    'img_upload'=> array('tag1' => ''),
    //下一页
    'reg_next'  => '/(?is)<a class="next" href="(\w+:\/\/\w+.qq.com\/\w+\/\d+\/.*?\.\w+)">下一页<\/a>/',
    'key0'      => '/(?is)<meta name="keywords" content="([^"]*?)".*?\/>/',
    'key0_ap'   => array(array(',', '|'), ' '),
    'tag0'      => '/(?is)title="([^"]*?)"/',
    'tag0_arp'  => array(
        array(
            '/(?is)\(图\)/',
            '/(?is)\"/',
            '/(?is)独家：/',
            '/(?is)独家:/',
            '/(?is)(《|》)/',
        ),
        array(
            '', '', '', '', '',
        )
    ),
    'tag1'      => '/(?is)<list>(.*?)<\/list>/',
    'tag1_brp'  => array(
        array(
            '/(?is)\s*<Image title="([^"]*?)" name="" imgurl="[^"]*?" httpurl="([^"]*?)" id="\d+" time="[^"]*?" intro="([^"]*?)" commentsuburl="[^"]*?" commentshowurl="[^"]*?" link="[^"]*?"\/>\s*/'
        ),
        array(
            '<p style="text-align: center;"><img src="$2" alt="$1" /></p>
             <p style="text-align: center;">$1</p>
             <p style="text-indent: 24px;">$3</p>'
        )
    ),
    'tag1_arp'  => array(
        array(
            '/(?is)<p style="text-indent: 24px;">([^<^>]*?)<\/p>/',
            '/(?is)\<br\/\>/',
        ),
        array(
            '<p style="text-indent: 24px;">$1</p><div style="page-break-after: always;"><span style="display: none;"> </span></div>',
            '',
        )
    ),
    'strip'     => array('tag1' => ''),
    //网名
    'tag3'      => '/(?is)<span class="auth">([^<^>]*?)<\/span>/',
    'tag4'      => '/(?is)(中华网)/'
);

$map = array(
    'tag'       => 'key0',
    'title'     => 'tag0',
    'content'   => 'tag1',
    'author'    => 'tag3',
    'source'    => 'tag4'
);

$site_list = array(
    'aname'     => '中华网娱乐图库',
    'domain'    => 'tuku.ent.china.com',
    'gettype'   => 'default',
    'creg'      => '/(?si)<div class="PicGroupListIndex">(.*?)<div class="MainBtm"><\/div>/',
    'code'      => 'utf-8',
    'reg_next'  => '/(?si)<li class="next"><a href="([^"]+?)" target="_self">下一页<\/a><\/li>/',
    //链接
    'tag0'      => '/(?is)<div class="ImgTitle"><a href="([^"]*?)" target="_blank"><span>.*?<\/span>[^<^>]*?<\/a><\/div>/',
    'tag0_brp'      => array(
        array(
            '/(?is)\.htm/',
        ),
        array(
            '.xml'
        )
    ),
    //标题
    'tag1'      => '/(?is)<div class="ImgTitle"><a href="[^"]*?" target="_blank"><span>.*?<\/span>([^<^>]*?)<\/a><\/div>/',
    'tag1_arp'  => array(
        array(
            '/(?is)\(图\)/',
            '/(?is)\"/',
            '/(?is)独家：/',
            '/(?is)独家:/',
            '/(?is)(《|》)/',
        ),
        array(
            '', '', '', '', '',
        )
    ),
);

$list_map = array(
    'url'       => 'tag0',
    'title'     => 'tag1',
);

$site_list_sub = array();