关于网页内容抓取问题的请教.

紫色田园 2019-10-12 12:15:47

本人网站上有一个头条文章页内容的抓取功能
========================================

	

        function https_request($url, $data = null, $referer = "", $type = "Content-Type: application/json", $cookie_file = "")

	{

		$curl = curl_init();

		curl_setopt($curl, CURLOPT_URL, $url);

		curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, True);

		curl_setopt($curl, CURLOPT_SSL_VERIFYHOST, True);



		if(!empty($referer)) {

			curl_setopt($curl, CURLOPT_REFERER, $referer);  

		}



		if ($data != null)

		{

			curl_setopt($curl, CURLOPT_CUSTOMREQUEST, "POST");

			curl_setopt($curl, CURLOPT_POST, 1);

			if(!empty($data)) {

				curl_setopt($curl, CURLOPT_POSTFIELDS, $data);

			}



			$arr = array();

			$arr[] = 'Content-Length: ' . strlen($data);

			if(!empty($type))

			{

				$arr[] = $type;

			}

			curl_setopt($curl, CURLOPT_HTTPHEADER,  $arr);

		}



		curl_setopt($curl, CURLOPT_RETURNTRANSFER, TRUE);

		curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true);

		if(!empty($cookie_file)) {

			curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_file);

			curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_file);

			//echo $cookie_file;

		}

		$output = curl_exec($curl);

		curl_close($curl);

		return $output;

	}

这个功能代码一直可用，上上周的时候发现不能用了，已抓取不到页面的内容，返回的内容如下：
========================================================
<!DOCTYPE html><html lang=en><head><meta charset=UTF-8><meta name=viewport content="width=device-width,initial-scale=1"><meta http-equiv=X-UA-Compatible content="ie=edge"><link rel="shortcut icon" href=//s3a.pstatp.com/toutiao/resource/ntoutiao_web/static/image/favicon_5995b44.ico type=image/x-icon><title>今日头条</title></head><body><p></p></body></html>

body里面是空的。
试了用基它方法，比如
==========================================
$content = file_get_contents($url);
和
$readContent = fopen($url,"rb");
$content = stream_get_contents($readContent);
fclose($readContent);

也不行。请教各位大大们，还有什么其它方法可以抓取到头条文章的内容吗？
示例头条URL：https://m.toutiao.com/i6744865260068422156/?utm_source=xiaochengxu&w2atif=1&channel=news_hot

在线等，给200分。

...全文