PHP爬虫微博热搜实时监控

工作闲暇之余微博上了解一下正在发生的事情，查看微博热搜发现界面需要一直手动刷新，于是想到了实时统计图展示，用现有的技术进行数据爬取，实时监控

1、先获取HTML内容
function getUrlContent($url){//通过url获取html内容
	$ch = curl_init();
	curl_setopt($ch,CURLOPT_URL,$url);
	curl_setopt($ch,CURLOPT_USERAGENT,"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1 )");
	curl_setopt($ch,CURLOPT_HEADER,1);
	curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);
	$output = curl_exec($ch);
	curl_close($ch);
	return $output;
 }
 
2、获取数据，通过正则方式，table标签转换数组
function getTable($html) {
  preg_match_all("/<table>[\s\S]*?<\/table>/i",$html,$table);
  $table = $table[0][0];
	$table = preg_replace("'<table[^>]*?>'si","",$table);
	$table = preg_replace("'<tr[^>]*?>'si","",$table);
	$table = preg_replace("'<td[^>]*?>'si","",$table);
	$table = str_replace("</tr>","{tr}",$table);
	$table = str_replace("</td>","{td}",$table);
	//去掉 HTML 标记
	$table = preg_replace("'<[/!]*?[^<>]*?>'si","",$table);
	//去掉空白字符
	$table = preg_replace("'([rn])[s]+'","",$table);
	$table = str_replace(" ","",$table);
	$table = str_replace(" ","",$table);
	$table = explode('{tr}', $table);
	array_pop($table);
	foreach ($table as $key=>$tr) {
	  // 自己可添加对应的替换
	  $tr = str_replace("\n\n","",$tr);
		$td = explode('{td}', $tr);
		array_pop($td);
		$td_array[] = $td;
	}
	return $td_array;
}

3、数据整理返回前端
$html = getUrlContent("https://s.weibo.com/top/summary?Refer=top_hot&topnav=1&wvr=6");
$table = getTable($html);
$table = array_slice($table,2); # 把前面多余部分截掉
echo json_encode($table);

4、数据展示柱状图echarts.js
function CreateBar(keywords,value){
  //初始化echarts实例
	var myChart = echarts.init(document.getElementById('chartmain'));
	myChart.on('click',function(param){
	window.open('#');
  });
  //指定图标的配置和数据
	var option = {
		title:{
			text:''
		},
		tooltip:{},
		grid:{
		  top:"15%",
		  left:"16%",
		  bottom:"5%"
		},
		legend:{
			data:['热搜词']
		},
		xAxis:{
		},
		yAxis:{
		  data:keywords
		},
		series:[{
			name:'搜索量',
			type:'bar',
			itemStyle: {
				normal: {
					color: '#ff9406'
				}
		  },
			data:value
		}]
	};
	myChart.setOption(option);
}

5、ajax请求数据
function GetData(){
  $.ajax({
	type: "post",        //数据提交方式（post/get）
	url: "weibo.php",    //提交到的url
	dataType: "json",    //返回的数据类型格式

	success: function(msg){
	  //返回成功的回调函数
	  if(msg!=''){
		var data = eval(msg); //将返回的json数据进行解析，并赋给data
		var keywords = [];
		var value = [];
		for(var i=0; i < 20; i++){ // 取TOP20
		  keywords.push(data[i][1].split('\n')[0]);
		  value.push(Number(data[i][1].split('\n')[1]));
		}
		CreateBar(keywords.reverse(),value.reverse());
		setInterval("GetData()",10000); // 间隔10S
	   }
	  },
	  error:function(msg){
		//返回失败的回调函数
		console.log(msg);
		setInterval("GetData()",30000); // 间隔30S
	  }
  });
}