PHP implementation of thief program example

CREATE TABLE `article`.`article` ( 
`id` MEDIUMINT( 8 ) UNSIGNED NOT NULL AUTO_INCREMENT PRIMARY KEY , 
`title` VARCHAR( 255 ) CHARACTER SET utf8 COLLATE utf8_general_ci NOT NULL , 
`date` VARCHAR( 50 ) NOT NULL , 
`author` VARCHAR( 100 ) CHARACTER SET utf8 COLLATE utf8_general_ci NOT NULL , 
`source` VARCHAR( 100 ) CHARACTER SET utf8 COLLATE utf8_general_ci NOT NULL , 
`content` TEXT NOT NULL 
) ENGINE = MYISAM CHARACTER SET utf8 COLLATE utf8_general_ci;

<?php 
/** 
* 抓取“华强电子网”资讯程序 
* author Lee. 
* Last modify $Date: 2012-1-3 15:39:35 $ 
*/ 
header(&#39;Content-Type:text/html;Charset=utf-8&#39;); 
$mysqli = new mysqli(&#39;localhost&#39;, &#39;root&#39;, &#39;1715544&#39;, &#39;article&#39;); # 数据库连接，请手动修改您自己的数据库信息 
$mysqli->set_charset(&#39;UTF8&#39;); # 设置数据库编码 
function data($url) { 
  global $mysqli; 
  $result = file_get_contents($url); # $result 获取 url 链接内容（注意：这里是文章列表链接） 
  $pattern = &#39;/<li><span class="box_r">.+<\/span><a href="([^"]+)" title=".+" >.+<\/a><\/li>/Usi&#39;; # 取得文章 url 的匹配正则 
  preg_match_all($pattern, $result, $arr); # 把文章列表 url 分配给数组$arr(二维数组) 
  foreach ($arr[1] as $val) { 
    $val = &#39;http://www.hqew.com&#39; . $val; # 真实文章 url 地址 
    $re = file_get_contents($val); # $re 为文章 url 的内容 
    $pa = &#39;/<p id="article">\s+<h1>(.+)<\/h1>\s+<p id="article\_extinfo">\s+发布:\s+(.+)\s+\|\s+作者:\s+(.+)\s+\|\s+来源:\s+(.*?)\s+<span style="display:none" >.+<p id="article_body">\s*(.+)\s+<\/p>\s+<\/p><!--article end-->/Usi&#39;; # 取得文章内容的正则 
    preg_match_all($pa, $re, $array); # 把取到的内容分配到数组 $array 
    $content = trim($array[5][0]);  
    $con = array( 
        &#39;title&#39;=>mysqlString($array[1][0]), 
        &#39;date&#39;=>mysqlString($array[2][0]),  
        &#39;author&#39;=>mysqlString(stripAuthorTag($array[3][0])), 
        &#39;source&#39;=>mysqlString($array[4][0]),  
        &#39;content&#39;=>mysqlString(stripContentTag($content)) 
      ); 
    $sql = "INSERT INTO article(title,date,author,source,content) VALUES (&#39;{$con[&#39;title&#39;]}&#39;,&#39;{$con[&#39;date&#39;]}&#39;,&#39;{$con[&#39;author&#39;]}&#39;,&#39;{$con[&#39;source&#39;]}&#39;,&#39;{$con[&#39;content&#39;]}&#39;)"; 
    $row = $mysqli->query($sql); # 添加到数据库 
    if ($row) { 
      echo &#39;add success!&#39;; 
    } else { 
      echo &#39;add failed!&#39;; 
    } 
  } 
} 
/** 
 * stripOfficeTag($v) 对文章内容进行过滤，比如：去掉文章中的链接，过滤掉没用的 HTML 标签…… 
 * @param string $v 
 * @return string 
 */ 
function stripContentTag($v){ 
  $v = str_replace(&#39;<p> </p>&#39;, &#39;&#39;, $v); 
  $v = str_replace(&#39;<p />&#39;, &#39;&#39;, $v); 
  $v = preg_replace(&#39;/<a href=".+" target="\_blank"><strong>(.+)<\/strong><\/a>/Usi&#39;, &#39;\1&#39;, $v); 
  $v = preg_replace(&#39;%(<span\s*[^>]*>(.*)</span>)%Usi&#39;, &#39;\2&#39;, $v); 
  $v = preg_replace(&#39;%(\s+class="Mso[^"]+")%si&#39;, &#39;&#39;, $v); 
  $v = preg_replace(&#39;%( style="[^"]*mso[^>]*)%si&#39;, &#39;&#39;, $v); 
  $v = preg_replace(&#39;/<b><\/b>/&#39;, &#39;&#39;, $v); 
  return $v; 
} 
 
/** 
 * stripTitleTag($title) 对文章标题进行过滤 
 * @param string $v 
 * @return string 
 */ 
function stripAuthorTag($v) { 
  $v = preg_replace(&#39;/<a href=".+" target="\_blank">(.+)<\/a>/Usi&#39;, &#39;\1&#39;, $v); 
  return $v; 
} 
 
/** 
 * mysqlString($str) 过滤数据 
 * @param string $str 
 * @return string 
 */ 
function mysqlString($str) { 
  return addslashes(trim($str)); 
} 
 
/** 
 * init($min, $max) 入口程序方法，从 $min 页开始取，到 $max 页结束 
 * @param int $min 从 1 开始 
 * @param int $max 
 * @return string 返回 URL 地址 
 */ 
function init($min=1, $max) { 
  for ($i=$min; $i<=$max; $i++) { 
    data("http://www.hqew.com/info-c10-{$i}.html"); 
  } 
} 
init(1, 500); // 程序入口，从第一页开始抓，抓取500页 
?>