//抓取该页面的数据
$url = "http://xxxxxxx";
$curl = curl_init($url);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($curl, CURLOPT_CONNECTTIMEOUT, 10);
curl_setopt($curl, CURLOPT_ENCODING, "gzip");
$contents = curl_exec($curl);
curl_close($curl);
$contents = mb_convert_encoding($contents, 'UTF-8', 'UTF-8,GBK,GB2312,BIG5' );
$contents = \Helper\CFunctionHelper::DeleteHtml($contents);
if (!preg_match_all("@
@", $contents, $tables)) {die("匹配表格失败");
}
//dd($tables[1][1]);
if (!preg_match_all("@
]+>(.*?)@", $tables[1][1], $tr)) {die("匹配tr失败");
}
// var_dump($tr[1][0]);
// die();
$data = [];
foreach($tr[1] as $value){
$bonusData = strip_tags(str_replace('', '|', str_replace(" ", '', $value)));
$issue = 0;
$recommend = "";
$kaijiang = "";
$result = "";
try {
list($issue, $recommend, $kaijiang,$result) = explode('|', $bonusData);
} catch (\ErrorException $e) {
die("发生异常:".$e->getMessage());
}
array_push($data,['issue'=>$issue,'recommend'=>$recommend,'kaijiang'=>$kaijiang,'result'=>$result]);
}
dd($data);
/**
* 去掉html中的换行和空格
* @param type $str
* @return type
*/
public static function DeleteHtml($str)
{
$str = trim($str); //清除字符串两边的空格
$str = preg_replace("/\t/","",$str); //使用正则表达式替换内容,如:空格,换行,并将替换为空。
$str = preg_replace("/\r\n/","",$str);
$str = preg_replace("/\r/","",$str);
$str = preg_replace("/\n/","",$str);
$str = preg_replace("\n[^\
$str = preg_replace("/ /","",$str);
$str = preg_replace("/ /","",$str); //匹配html中的空格
return trim($str); //返回字符串
}