视频演示:https://thumbsnap.com/qkDgKM5o
网址信息:https://www.toutiao.com/video/7418557232318513703/
我使用PHP的url获取一个网页的时候,它的网页内容一直在跳动,不能获取完整,我知道可能是使用了js动态创建的,但有技术或方法可以获取完整的内容吗?谢谢了
[ol]/*
* 今日头条video页面的文件头
**/
function toutiao_html_header($url)
{
$header = array(
"Host: https://www.toutiao.com",
"Referer: {$url}",
"set-cookie: tt_webid=7421001700129736202; path=/; expires=Sun, 09 Feb 2025 04:22:07 GMT; domain=toutiao.com; secure; httponly",
'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
'Accept-Language:zh-CN,zh;q=0.9,en;q=0.8',
'cookie: ******************************************************************************',
"User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36",
);
return $header;
}
/**
* 模拟浏览器开始访问请求,这个用于今日头条视频的页面内容获取
*/
function fetch_toutiao_video_html($url)
{
$header = toutiao_html_header($url);
$timeout = 40;
$ch = curl_init($url);
curl_setopt($ch, CURLOPT_FAILONERROR, true);
//设置请求头信息
#curl_setopt($ch, CURLOPT_HTTPHEADER, $header);
curl_setopt($ch, CURLOPT_HEADER, $header);
//不取得返回头信息
#curl_setopt($ch, CURLOPT_HEADER, 0);
// 关闭https验证
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, false);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($ch, CURLOPT_ENCODING, "");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, false);
curl_setopt($ch, CURLOPT_AUTOREFERER, true);
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, $timeout);
curl_setopt($ch, CURLOPT_TIMEOUT, $timeout);
curl_setopt($ch, CURLOPT_REFERER, $header[1]);
curl_setopt($ch, CURLOPT_MAXREDIRS, 10);
curl_setopt($ch, CURLOPT_USERAGENT, $header[6]);
$content = curl_exec($ch);
if (curl_errno($ch)) {
echo 'Error:' . curl_error($ch);
} else {
return $content;
}
curl_close($ch);
}[/ol]复制代码