php去除标签爬取内容
$data=DB::table('novel_sections')->where('novel_id',188699)->take(2)->get();
$data=json_decode($data,true);
foreach ($data as $k=>$v)
{
$lines['title'] = $v['title'];
$lines['content'] = file_get_contents($v['content']);
$content_02 = htmlspecialchars_decode($lines['content']);//把一些预定义的 HTML 实体转换为字符
$content_03 = str_replace(" ","",$content_02);//将空格替换成空
$lines['content'] = strip_tags($content_03);//函数剥去字符串中的 HTML、XML 以及 PHP 的标签,获取纯文本内容
//$con = mb_substr($contents, 0, 100,"utf-8");//返回字符串中的前100字符串长度的字符
$arr[]=$lines;
}
file_put_contents("C:/3.txt",serialize($arr));
file_put_contents("C:/3.txt",json_encode($arr));
$datas = json_decode(file_get_contents("C:/3.txt"));
print_r($datas);
<?php
$url = "http://www.jb51.net";
$contents = file_get_contents($url);
//如果出现中文乱码使用下面代码
//$getcontent = iconv("gb2312", "utf-8",$contents);
echo $contents;
?>