php文章采集方法
<?php //文章采集方法一 /* $res = fopen("http://www.huanqiu.com/","r");
$data =''; while($strcon = fgets($res)){ $data .= $strcon; } fclose($res);*/ //文章采集方法二 $data = file_get_contents("http://www.huanqiu.com/"); $data1 = file_get_contents("http://china.huanqiu.com/article/2017-02/10136020.html"); $data2 = file_get_contents("http://opinion.huanqiu.com/editorial/2017-02/10135124.html"); $data3 = file_get_contents("http://world.huanqiu.com/exclusive/2017-02/10137395.html"); //标题正则 $div_preg = '/<div id="block_id_42876" class="admin_block" blockid="42876">[\s\S]+?<\/div>/'; $title_preg = '/<h4>[\s\S]+?<\/h4>/'; //内容正则 $con_preg = '/<div class="conText">[\s\S]+?<!-- 左侧 end -->/'; //得到返回的数组数据 preg_match($div_preg,$data,$arr); preg_match($con_preg,$data1,$arr1); preg_match($con_preg,$data2,$arr2); preg_match($con_preg,$data3,$arr3); //匹配数据里所有需要的标签内容
preg_match_all($title_preg,$arr[0],$arrT); ?> <!DOCTYPE html>bjrongjinhuiyin<html lang="en"> <head> <meta charset="UTF-8"> <title>文章采集</title> <style type="text/css"> ul,li{ margin: 0; padding: 0; list-style:none; } .con{ width: 420px; height: 460px; float: left; margin-right: 20px; overflow: auto; border: 2px solid #ccc; border-radius: 10px; box-shadow: 4px 5px 3px #aaa; } </style> </head> <body> <ul> <?php foreach ($arrT[0] as $key => $value):?> <li><?php echo $value;?></li> <?php endforeach;?> </ul> <ul> <div class='con'><?php echo $arr1[0];?></div> <div class='con'><?php echo $arr2[0];?></div> <div class='con'><?php echo $arr3[0];?></div> </ul> </body> </html>
