采集指定页面的标题，关键字

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
public function classdate(){
       
        $find = thinkDb::table('classa')->field('id,folder,ClassBasicInfo')->select();
        $arr = [];
        foreach ($find as $key => $value) {
            $arr[$key]['url'] = 'http://www.xxx.com/' . $value['folder'];
            $arr[$key]['id'] =$value['id'];
        }
        return $arr;
    } 

public function curl(){
       
        set_time_limit(0);
        $ch = array();
        $res = array();
        $conn = array();

        $html=[];
        $urls =$this->classdate();
        foreach ($urls as $key => $url) {
            $ch = curl_init($url['url']);
            curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
            $result = curl_exec($ch);
            curl_close($ch);
            $html[$key]['id']= $url['id'];
            $html[$key]['title'] = preg_match('!<title>(.*?)</title>!i', $result, $matches) ? $matches[1] : '';
            $html[$key]['keywords'] = preg_match('/<METAs+name="keywords"s+content="([wW]*?)"/si', $result, $matches) ? $matches[1] : '';
            $html[$key]['desc'] = preg_match('/<METAs+name="description"s+content="([wW]*?)"/si', $result, $matches) ? $matches[1] : '';
            $update = thinkDb::table('classa')->where('id', $url['id'])->update([
                'title'=>$html[$key]['title'],
                'keywords' =>$html[$key]['keywords'],
                'desc'=>$html[$key]['desc'],
            ]);
        }
        dump($html);
    }