PHP抓取网页获取特定信息

    <?php 
    
    /** * 抓取网页
     */
    function catch_html($url) {
    	$urlR = parse_url($url);
    	$domain = $urlR['scheme'].'://'.$urlR['host'].'/';
    	$headers=array(
    		"Accept: application/json, text/javascript, */*; q=0.01",
    		"Content-Type: application/x-www-form-urlencoded; charset=UTF-8",
    		"Origin: {$domain}",
    		"Referer: {$url}",
    		"User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36",
    	);
    	
    	$curl = curl_init();
    	curl_setopt($curl, CURLOPT_URL, $url);//设置抓取的url
    	curl_setopt($curl, CURLOPT_HTTPHEADER, $headers);//指定头部参数
    	curl_setopt($curl, CURLOPT_HEADER, 0);//设置头文件的信息作为数据流输出
    	//设置获取的信息以文件流的形式返回，而不是直接输出。
    	curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
    	curl_setopt($curl, CURLOPT_ACCEPT_ENCODING, "gzip,deflate");
    	//重要！
    	curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, FALSE); // https请求 不验证证书和hosts
    	curl_setopt($curl, CURLOPT_SSL_VERIFYHOST, FALSE);
    	curl_setopt($curl,CURLOPT_USERAGENT,"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)"); //模拟浏览器代理
    	$data = curl_exec($curl);//执行命令
    	curl_close($curl);//关闭URL请求
    	$data = mb_convert_encoding($data, 'UTF-8', 'UTF-8,GBK,GB2312,BIG5');//使用该函数对结果进行转码
    	
    	return $data;
    }
    
    /** * 正则匹配，获取标签内容
     */
    function get_tag_data($html,$tag,$attr,$value=''){ 
    	$regex = $value ? "/<$tag.*?$attr=\"$value\".*?>(.*?)<\/$tag>/is" :  "/<$tag.*?$attr=\".*?$value.*?\".*?>(.*?)<\/$tag>/is";
    preg_match_all($regex,$html,$matches,PREG_PATTERN_ORDER); 
    return $matches[1];//返回值为数组 ,查找到的标签内的内容
    }
    
    
    $url = 'https://www.cnblogs.com/';
    $html = catch_html($url);
    //echo $html;die;
    
    
    //匹配标题：<a class="post-item-title" href="https://www.cnblogs.com/lyl-star/p/15410719.html" target="_blank">数据库系统之实体完整性约束</a>
    $titles = get_tag_data($html,'a','class','post-item-title');
    
    
    //匹配作者：<a href="https://www.cnblogs.com/lyl-star/" class="post-item-author"><span>lyl-star</span></a>
    $authors = get_tag_data($html,'a','class','post-item-author');
    //['<span>lyl-star</span>']，
    foreach($authors as &$author){
    	$author = str_replace('<span>','',$author);
    	$author = str_replace('</span>','',$author);
    }
    
    $list = [
    	'titles' => $titles,
    	'authors' => $authors,
    ];
    
    echo '<pre>'; print_r($list); die;
    
    
    
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
    
    AI助手