采集新浪新闻php插件

今天没事，就分享一个采集新浪新闻PHP插件接口，可用于火车头采集，比较简单，大家可以研究！

新浪新闻实时动态列表为：https://news.sina.com.cn/roll/?qq-pf-to=pcqq.group#pageid=153&lid=2968&k=&num=50&page=1

<?php
 function curl_sina($url){
    $header = array (
  0 => 'Accept: */*',
  1 => 'Accept-Encoding: gzip, deflate, br',
  2 => 'Accept-Language: zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',
  3 => 'Connection: keep-alive',
  4 => 'Host: feed.mix.sina.com.cn',
  5 => 'Referer: https://news.sina.com.cn/roll/?qq-pf-to=pcqq.group',
  6 => 'User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:55.0) Gecko/20100101 Firefox/55.0 FirePHP/0.7.4',
  7 => 'x-insight: activate',
);
    $postData = '';
    // $cookie = 'Cookie: UOR=,news.sina.com.cn,; ULV=1545891095102:2:2:2:10.71.2.95_1545891091.345391:1545891089621; SINAGLOBAL=10.71.2.95_1545891091.345389; Apache=10.71.2.95_1545891091.345391; NEWSCENTER=78565b88b160488188f3c4bb7622647b; lxlrttp=1545098194'; //需要cookie的话去掉这行的注释
    $timeout = 10;
 
    $ch  = curl_init($url);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);       //返回数据不直接输出
    curl_setopt($ch, CURLOPT_ENCODING, "gzip");        //指定gzip压缩
    curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);    //302/301
    //SSL
    if(substr($url, 0, 8) === 'https://') {
        curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
        curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, false);
        //error:14077458:SSL routines:SSL23_GET_SERVER_HELLO:reason(1112)解决
        //值有0-6，请参考手册，值1不行试试其他值
        //curl_setopt($ch, CURLOPT_SSLVERSION, 1);
    }
    //post数据
    if(!empty($postData)) {
        curl_setopt($ch, CURLOPT_POST, 1);               //发送POST类型数据
        curl_setopt($ch, CURLOPT_POSTFIELDS, $postData); //POST数据，$post可以是数组（multipart/form-data），也可以是拼接参数串（application/x-www-form-urlencoded）
    }
    if(!empty($cookie)) {
        $header[] = $cookie;
    }
    if(!empty($header)) {
        curl_setopt($ch, CURLOPT_HTTPHEADER, $header);     //使用header头信息
    }
    //超时时间
    curl_setopt($ch, CURLOPT_TIMEOUT, (int)$timeout);
    //执行
    $content = curl_exec($ch);
    if($error = curl_error($ch)) {
        //log error
        error_log($error);
    }
    curl_close($ch);
 
    // $content 是请求结果
return $content;
 }
 
  
 //$u='https://feed.mix.sina.com.cn/api/roll/get?pageid=153&lid=2510&k=&num=50&page=1';
 if($LabelArray['PageType']=='List'){        
        $content=curl_sina($LabelUrl); //获取到的当前列表源码内容
        $resarr = json_decode($content, true);
$resdata = $resarr['result']['data'];
$us='';
foreach($resdata as $k => $v){
        $us.='<b>'.$v['url'].'</b>';
        $LabelArray['Html']='str'.$us.'go';
}
 
 }
 //$LabelArray['Html']=curl_sina($LabelUrl); //获取到的当前列表源码内容
echo serialize($LabelArray);
?>

接口主要获取列表有限制！这个插件就是获取列表地址的，另外分享我新上线的测试的技术专题文摘：http://zhimo.yuanzhumuban.cc/blog/