欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页  >  后端开发

采集 php 文章采集正则代码

程序员文章站 2022-06-17 10:56:13
...
复制代码 代码如下:


//采集html
function getwebcontent($url){
$ch = curl_init();
$timeout = 10;
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, $timeout);
curl_setopt ($ch, CURLOPT_FOLLOWLOCATION, 1);
$contents = trim(curl_exec($ch));
curl_close($ch);
return $contents;
}
//获得标题和url
$string =
getwebcontent('http://www.***.com/learn/zhunbeihuaiyun/jijibeiyun/2');
//正则匹配

  • 获取标题和地址
    preg_match_all ("/
  • (.*)/",$string, $out, PREG_SET_ORDER);
    foreach($out as $key => $value){
    $article['title'][] = $out[$key][2];
    $article['link'][] = "http://www.***.com/learn/article/".$out[$key][1];
    }
    //根据url获取文章内容
    foreach($article['link'] as $key=>$value){
    $content_html = getwebcontent($article['link'][$key]);
    preg_match("/

    相关文章

    相关视频


  • 相关标签: 采集