php实现爬取知乎神回复数据——做成小程序上线

知乎真是一个神奇的地方，经常会看到很多令人忍俊不禁的神回复，初看之下拍案叫绝，细思之下更是回味无穷。这篇文章主要介绍了php实现爬取知乎神回复简单爬虫代码分享（看了网上的python版本改写的，写的又臭又长），选取了几个比较感兴趣的话题进行爬取，其中比较有趣的还是程序员相关的话题。

知乎神回复都有些什么特点呢？我们先来观察一下：

大家看出什么规律了么？短小精辟有没有？赞同很多有没有？所以爬取知乎神回复我们只要爬取那些赞同多又字数少的回答就可以。直接上代码：

public function getZHData($value='')
    {
      // IT $topic_ids = [19551556,19551052,19551151,19582090,19584190,19551137];
        // 生活方式 $topic_ids=[19550429,19556784,19575422,19592882,19559915,19587000,19579062,19563237,19588633,19569846,19606425];
        $topic_ids=[19554827,19562832,19559052,19552439,19558415,19580121,19594304,19555667,19555495,19604473,19624659];
		for ($i=0; $i <count($topic_ids) ; $i++) { 
			$this->get_answers($topic_ids[$i]);
		}
		return 1;
    } 
    function get_answers($topic_id)
	{
		$page_no = 0;
		while (1) {
			$is_end = $this->get_answers_by_page($topic_id, $page_no);
		    $page_no += 1;
		    if($is_end){
		    	break;
		    }
		}
	}

	function get_answers_by_page($topic_id, $page_no){
		DB::insert("insert into isread (topic_id,page_no) values(?,?)",[$topic_id, $page_no]);	
		$offset = $page_no * 10;
	    $url = "https://www.zhihu.com/api/v4/topics/".$topic_id. "/feeds/essence?include=data%5B%3F(target.type%3Dtopic_sticky_module)%5D.target.data%5B%3F(target.type%3Danswer)%5D.target.content%2Crelationship.is_authorized%2Cis_author%2Cvoting%2Cis_thanked%2Cis_nothelp%3Bdata%5B%3F(target.type%3Dtopic_sticky_module)%5D.target.data%5B%3F(target.type%3Danswer)%5D.target.is_normal%2Ccomment_count%2Cvoteup_count%2Ccontent%2Crelevant_info%2Cexcerpt.author.badge%5B%3F(type%3Dbest_answerer)%5D.topics%3Bdata%5B%3F(target.type%3Dtopic_sticky_module)%5D.target.data%5B%3F(target.type%3Darticle)%5D.target.content%2Cvoteup_count%2Ccomment_count%2Cvoting%2Cauthor.badge%5B%3F(type%3Dbest_answerer)%5D.topics%3Bdata%5B%3F(target.type%3Dtopic_sticky_module)%5D.target.data%5B%3F(target.type%3Dpeople)%5D.target.answer_count%2Carticles_count%2Cgender%2Cfollower_count%2Cis_followed%2Cis_following%2Cbadge%5B%3F(type%3Dbest_answerer)%5D.topics%3Bdata%5B%3F(target.type%3Danswer)%5D.target.annotation_detail%2Ccontent%2Crelationship.is_authorized%2Cis_author%2Cvoting%2Cis_thanked%2Cis_nothelp%3Bdata%5B%3F(target.type%3Danswer)%5D.target.author.badge%5B%3F(type%3Dbest_answerer)%5D.topics%3Bdata%5B%3F(target.type%3Darticle)%5D.target.annotation_detail%2Ccontent%2Cauthor.badge%5B%3F(type%3Dbest_answerer)%5D.topics%3Bdata%5B%3F(target.type%3Dquestion)%5D.target.annotation_detail%2Ccomment_count&limit=10&offset=".$page_no;
	    // echo $url;die;
	    $curl = curl_init();
        curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
        curl_setopt($curl, CURLOPT_TIMEOUT, 500);
        curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, false);
        curl_setopt($curl, CURLOPT_SSL_VERIFYHOST, false);
        curl_setopt($curl, CURLOPT_URL, $url);
        $res = curl_exec($curl);
        curl_close($curl);
        $res = json_decode($res, true);
	    if($res){
	    	 $is_end = $res["paging"]["is_end"];
	        if(array_key_exists("data",$res)){
	        	$data =$res["data"];
	        }else{
	        	return $is_end;
	        }
	    }else{
	    	return false;
	    }       
	    for ($i=0; $i < count($data); $i++) {	    	
	    	$question_title;
	    	$target = $data[$i]["target"];
	    	if(array_key_exists("question",$target)){
	    		$question_title =$target["question"]["title"];
	    	}else{
	    		echo "string\n";
	    		continue;
	    	}	    		    	
	    	$anwser_con = $data[$i]["target"]["content"];
	    	$voteup_count = $data[$i]["target"]["voteup_count"];
	    	$id = $data[$i]["target"]["id"]; 
	    	$voteup_count = strval($voteup_count);	    	
	    	if(strlen($anwser_con)<200 &&$voteup_count>1000 ){
	    	   $sql1 = "select * from question_a where anwser_id='$id'";	    		
	    	   $is_save = DB::select($sql1);	    	   
	    	   if(count($is_save)<1){
	    	   	   $sql = "INSERT INTO question_a (question_title,anwser_con,voteup_count,topic_id,anwser_id)
	    	   		 values (?,?,?,?,?)";
				   DB::insert($sql,[$question_title,$anwser_con,$voteup_count,4,$id]);
	    	   }else{
	    	   	echo "已经有了";
	    	   }				
	    	}
	    }
	    return $is_end;
	}

上面代码直接执行getZHData即可，其中DB是数据库实例，换成你们自己的就ok了。
数据爬好，然后用小程序渲染出来，我这里申请的小程序是个人的，选择信息查询类目，可以通过审核上线额。
下面是小程序效果图

小程序名叫**“支呼神回复”** (知乎是不能用的)，可以在微信->发现->小程序 中搜索到，也可以保存到微信扫描下面二维码（手机扫描）