php 抓取网页内容与图片

例子1：

<?php
 include_once("curl.php");/*这个文件要自己配置好*/
 header("content-type:text/html;charset=utf8");
  $pattern_title ="/<title>(.+)<//title>/";//标题匹配
  $pattern_code = "/<tr><td><p>(.+)<//p><script/";//网页内容匹配
  $url="http://www.freewl.com/freezcm/2011/0413/3185.html";//根网址
  
 $DATA_CONTENT = CurlGet($url); 
 
 $num=preg_match_all($pattern_title, $DATA_CONTENT, $match_title);
 
 for($i=0;$i<$num;$i++){
  echo strlen($match_title[1][$i])."--".$match_title[1][$i]."<br />";
 }
 echo "<hr />";
 
 /*$trans = array("  "=>"，", "<br />"=>"。");
 $TRANS_CONTENT = strtr($DATA_CONTENT, $trans);
 echo $TRANS_CONTENT;
 */
 
$DATA_CONTENT=preg_replace('//s(?=/s)/', ' ', $DATA_CONTENT);//(?=pattern) 正向预查
   $DATA_CONTENT=preg_replace('/[/n/r/t]/', '/r/n', $DATA_CONTENT);//回车换行
   $DATA_CONTENT=preg_replace('/ /', ' ', $DATA_CONTENT); 


 $num=preg_match_all($pattern_code, $DATA_CONTENT, $match_code);
 
 for($i=0;$i<$num;$i++){
  echo $match_code[1][$i]."<br />";  
 }
 
?>
 

例子2：

 <?php
/*
author: ssh_kobe
date: 20110615
*/
set_time_limit(0);//抓取不受时间限制


function get_pic($pic_url) {
//获取图片二进制流
$data=CurlGet($pic_url);


/*利用正则表达式得到图片链接
$pattern_src = '/<img.*?\"([^\"]*(jpg|bmp|jpeg|gif)).*?>/';*/
$pattern_src = '/<img.*?src\=\"(.*\.jpg).*?>/';//只匹配jpg格式的图片
$num = preg_match_all($pattern_src, $data, $match_src);
$arr_src=$match_src[1];//获得图片数组

//get_name($arr_src);
get_name_2($arr_src);

echo 'End!!!<br>';
return 0;
}


function get_pic_2($pic_url, $base_site) {
//获取图片二进制流
$data=CurlGet($pic_url);


/*利用正则表达式得到图片链接*/
$pattern_src = '/<img.*?\"([^\"]*jpg).*?>/';//只匹配jpg格式的图片
$num = preg_match_all($pattern_src, $data, $match_src);
$arr_src=$match_src[1];//获得图片数组

$arr_src=rev_site($arr_src, $base_site);
get_name($arr_src);

echo 'End!!!<br>';
return 0;
}


/* 将图片相对地址改为绝对地址 */
function rev_site($site_list, $base_site){
    foreach($site_list as $site_item) {
        if (preg_match('/^http/', $site_item)) {
            $return_list[] = $site_item;
        }else{
            $return_list[] = $base_site.$site_item;
}
    }
    return $return_list;
}


/*得到图片类型，并将其保存到与该文件同一目录*/
function get_name($pic_arr)
{
    //图片类型
$pattern_type = '/(\.(jpg|bmp|jpeg|gif|png))/';    

    foreach($pic_arr as $pic_item){//循环取出每幅图的地址
        $num = preg_match_all($pattern_type,$pic_item,$match_type);
        $pic_name = get_unique().$match_type[1][0];//改时微秒时间戳命名
        //以流的形式保存图片
        $write_fd = @fopen($pic_name,"wb");        
        @fwrite($write_fd, CurlGet($pic_item));
        @fclose($write_fd);
        echo "OK..";
    }
    return 0;
}


function get_name_2($pic_arr)
{
    //图片编号和类型
$pattern_type = '/.*\/(.*?)$/';    

    foreach($pic_arr as $pic_item){//循环取出每幅图的地址
        $num = preg_match_all($pattern_type,$pic_item,$match_type);
        //以流的形式保存图片
        $write_fd = @fopen($match_type[1][0],"wb");        
        @fwrite($write_fd, CurlGet($pic_item));
        @fclose($write_fd);
        echo 'OK..';
    }
    return 0;
}


//通过微秒时间获得唯一ID
function get_unique(){
list($msec, $sec) = explode(" ",microtime());
return $sec.intval($msec*1000000);
}


//抓取网页内容
function CurlGet($url){
$url=str_replace('&amp;','&',$url);
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_HEADER, false);

//curl_setopt($curl, CURLOPT_REFERER,$url);
curl_setopt($curl, CURLOPT_USERAGENT, "Mozilla/4.0 (compatible; MSIE 6.0; SeaPort/1.2; Windows NT 5.1; SV1; InfoPath.2)");
curl_setopt($curl, CURLOPT_COOKIEJAR, 'cookie.txt');
curl_setopt($curl, CURLOPT_COOKIEFILE, 'cookie.txt');
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($curl, CURLOPT_FOLLOWLOCATION, 0);
$values = curl_exec($curl);
curl_close($curl);
return $values;
}
?><?php /* author: ssh_kobe date: 20110602 shortage: 如果网页中的图片路径不是绝对路径，就无法抓取 */ set_time_limit(0);//抓取不受时间限制 $URL='http://pp.baidu.com/';//任意网址 get_pic($URL); function get_pic($pic_url) { //获取图片二进制流 $data=CurlGet($pic_url); /*利用正则表达式得到图片链接*/ $pattern_src = '/<img.*?/"([^/"]*(jpg|bmp|jpeg|gif)).*?>/'; $num = preg_match_all($pattern_src, $data, $match_src); $arr_src=$match_src[1];//获得图片数组 get_name($arr_src); echo "<br>finished!!!"; return 0; } /*得到图片类型，并将其保存到与该文件同一目录*/ function get_name($pic_arr) { //图片类型 $pattern_type = '/(/.(jpg|bmp|jpeg|gif|png))/'; foreach($pic_arr as $pic_item){//循环取出每幅图的地址 $num = preg_match_all($pattern_type,$pic_item,$match_type); $pic_name = get_unique().$match_type[1][0];//改时微秒时间戳命名 //以流的形式保存图片 $write_fd = @fopen($pic_name,"wb"); @fwrite($write_fd, CurlGet($pic_item)); @fclose($write_fd); echo "[OK]..!"; } return 0; } //通过微秒时间获得唯一ID function get_unique(){ list($msec, $sec) = explode(" ",microtime()); return $sec.intval($msec*1000000); } //抓取网页内容 function CurlGet($url){ $url=str_replace('&amp;','&',$url); $curl = curl_init(); curl_setopt($curl, CURLOPT_URL, $url); curl_setopt($curl, CURLOPT_HEADER, false); //curl_setopt($curl, CURLOPT_REFERER,$url); curl_setopt($curl, CURLOPT_USERAGENT, "Mozilla/4.0 (compatible; MSIE 6.0; SeaPort/1.2; Windows NT 5.1; SV1; InfoPath.2)"); curl_setopt($curl, CURLOPT_COOKIEJAR, 'cookie.txt'); curl_setopt($curl, CURLOPT_COOKIEFILE, 'cookie.txt'); curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1); curl_setopt($curl, CURLOPT_FOLLOWLOCATION, 0); $values = curl_exec($curl); curl_close($curl); return $values; } ?>