几种获取html字符串中所有超链接地址代码
$ss = "<a href='1.gif'>d</a>adfxx<a href="dir.html">dir</a>";
print_r(gethref($ss));
function gethref($temp){
preg_match_all('/<a.*?(?: |t|r|n)?href=['"]?(.+?)['"]?(?:(?: |t|r|n)+.*?)?>(.+?)</a.*?>/sim',$temp,$a);
return $a[1];
}
//下面所有a连接
$htm = preg_replace( "@<a(.*?)</a>@is","$1",$ss);
print_r($htm);
//比较全的提取url连接地址
$url="http://www.jzread.com";
$html=file_get_contents($url,"r");
preg_match_all ("/(<a)(.*)(href=)([^>]*)(>)([^<]*)(<)([^>]*)(>)/", $html, $matches);
for ($i=0;$i<count($matches[0]);$i++)
{
echo "|||".$matches[2][$i]."||".$matches[3][$i].$matches[4][$i]."||".$matches[6][$i]."||".$matches[8][$i]."<br>";
}//提取文章字符串中所有链接地址
preg_match_all('/(?<=href=")[wd.:/]*/',$str,$fstr);
时间: 2024-10-10 07:21:01