文章采集代码

Posted 2021-03-18 jthb

<?php
    //1.告诉采集页面的地址
    $url = ‘http://www.zgjiemeng.com/dongwu/‘;
    //2.读取采集页面地址
    $str = file_get_contents($url);
   // echo $str;
   
echo     ‘<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />‘;
    //3.定义采集文章链接区域的正则
    $pattern_qu = ‘/<ul class="list2 clearfix">([Ss]*?)</ul>/‘;


    //4.进行正则匹配 将文章区域的链接匹配到
    preg_match($pattern_qu,$str,$match_url);
   // var_dump($match_url[1]);
    
    
    preg_match_all ("/<li>(.*)</li>/U", $match_url[1], $pat_array);
print_r( $pat_array[0][1]); 
    
    
    preg_match_all ("/<li><a target="_blank" title="(.*)" href="(.*)">(.*)</a></li>/U", $pat_array[0][1], $pat_array);
print_r($pat_array); 
    //preg_match_all("/(<([w]+)[^>]*>)(.*?)(</\2>)/", $match_url[1], $matches, PREG_SET_ORDER);
//print_r($matches );

die;
    
    
    preg_match($pattern_qu,$match_url[1],$match_url);
    
    var_dump($match_url);
    
    die;
    
    
 
    //5.定义匹配文章链接的正则
    $pattern_url = ‘/<as+href="(.*?)"s+title/S‘;
    //6.匹配文章的链接地址
    preg_match_all($pattern_url,$match_url[1],$match);
    var_dump($match);
    
    die;
    $num = 1;
    //7.遍历匹配到的所有文章内容地址
    foreach($match[1] as $k=>$v){
        //echo $v.‘<br/>‘;
        //7.1循环打开文章内容地址
        $content = file_get_contents($v);
        //7.2定义匹配文章内容的正则
        $con_pattern = ‘/<divs+class="ad"></div>(.*?)<spans+id="supports"s+class="praise"/Ss‘;
        //7.3定义匹配文章标题的正则
        $title_pattern = ‘/<title>(.*?)</title>/Ss‘;
        //7.4进行文章内容的匹配
         preg_match($con_pattern,$content,$newCon);
        //var_dump($newCon);exit;
        //7.5进行文章标题的匹配
        preg_match($title_pattern,$content,$newTitle);
        //var_dump($newTitle);
        //7.6组成字符串
        $newStr = $newTitle[0].‘<meta charset="utf-8" />‘.$newCon[1];
        //7.7写入到指定文件中保存
        file_put_contents(‘./collect/‘.$num.‘.html‘,$newStr);
        $num ++;
    }