今日主要对论文的关键进行了分类处理，将相似的关键词合并成一个研究领域，将前十个热门的研究领域列出，并可以看个研究领域的热词。
<html> <head> <meta charset="utf-8"> <script src='https://cdn.jsdelivr.net/npm/echarts@5/dist/echarts.min.js'></script> <!-- <script src="../../echarts/dist/echarts.js"></script> --> <script src='../static/js/echarts-wordcloud.js'></script> <script src="../static/js/jquery.js"></script> <script src="../static/js/echarts.min.js"></script> <link rel="stylesheet" type="text/css" href="../static/css/paper.css" /> </head> <body> <style> html, body{ width: 100%; height: 100%; margin: 0; } </style> <div class="under" align="center"> <div class="top10"> <table> <thead> <th>热门领域TOP10</th> <th>名次</th> <th>操作</th> </thead> <tbody> </tbody> </table> </div> <h2 id="title">热门领域热词统计</h2> <div class="linecharbox" id="line"> </div> </div> <script> var chart = echarts.init(document.getElementById('line')); var option = { // backgroundColor: '#fff', tooltip: { trigger: 'axis', axisPointer: { lineStyle: { color: { type: 'linear', x: 0, y: 0, x2: 0, y2: 1, colorStops: [{ offset: 0, color: 'rgba(0, 255, 233,0)' }, { offset: 0.5, color: 'rgba(255, 255, 255,1)', }, { offset: 1, color: 'rgba(0, 255, 233,0)' }], global: false } }, }, }, xAxis: [{ show: true, type: 'category', axisLine: { show: true }, splitArea: {// show: true, color: '#f00', lineStyle: { color: '#f00' }, }, axisLabel: { color: '#f00' }, splitLine: { show: false }, boundaryGap: false, data: ['A', 'B', 'C', 'D', 'E', 'F'], }], grid: { x: '5%', y: '5%', x2: '5%', y2: '5%', borderWidth: 1 }, yAxis: [{ type: 'value', splitNumber: 4, splitLine: { show: true, lineStyle: { color: 'rgba(255,255,255,0.1)' } }, axisLine: { show: true, }, axisLabel: { show: true, textStyle: { color: '#f00', }, }, axisTick: { show: false, }, }], series: [{ name: "领域论文", type: 'line', smooth: true, //是否平滑 // showAllSymbol: false, symbol: 'circle', symbolSize: 2, lineStyle: { normal: { color: "#00b3f4", }, }, itemStyle: { color: "#00b3f4", }, areaStyle: { normal: { color: new echarts.graphic.LinearGradient(0, 0, 0, 1, [{ offset: 0, color: 'rgba(0,179,244,0.3)' }, { offset: 1, color: 'rgba(0,179,244,0)' } ], false), shadowColor: 'rgba(0,179,244, 0.9)', shadowBlur: 20 } }, data: [502.84, 205.97, 332.79, 281.55, 398.35, 214.02, ] },] }; chart.setOption(option); window.onresize = chart.resize; </script> <script> function get_date_top(){ $.ajax({ url: "/key_word_class", success: function (data) { option.xAxis[0].data=data.name; option.series[0].data=data.value; chart.setOption(option); }, error: function (xhr, type, errorThrown) { } }) } function get_top10(){ $.ajax({ url: "/top_10", success: function (data) { $(".top10 tbody").empty(); for (var i = 0; i < data.data.length; i++) { str=i+1+"" appendHtmlBody = "<tr><td>"+data.data[i][0]+"</td><td>"+str+"</td><td><button type='button' onclick='get_class("+'"'+data.data[i][0]+'"'+")'>领域热词</button></td></tr>" $(".top10 tbody").append(appendHtmlBody); } }, error: function (xhr, type, errorThrown) { } }) } function leave_out(str){ if(str.length>=30) { str=str.substring(0,30)+"..." } return str } function get_class(str){ var title=document.getElementById("title") $.ajax({ url: "/top_10_class", data:{ top_word:str }, success: function (data) { title.innerHTML = str+"领域热词统计"; option.xAxis[0].data=data.name; option.series[0].data=data.value; chart.setOption(option); }, error: function (xhr, type, errorThrown) { } }) } get_date_top() get_top10() </script> </body> </html>
#获取top10热词 @app.route("/top_10") def top_10(): word_num=util.word_cloud_top() word_cloud_num=[] flag=0; for i in word_num: if(' ' in i[0]): word_cloud_num.append([i[0],i[1]]) flag=flag+1; if(flag>9): break return jsonify({"data":word_cloud_num}) #获取top_10的子热词 @app.route("/top_10_class") def top_10_class(): word_cloud_num = [] word_cloud = [] top_word=request.values.get("top_word") word_num = util.get_top_10_class(top_word) for i in word_num: word_cloud.append(i[0]) word_cloud_num.append(i[1]) return jsonify({"name": word_cloud,"value":word_cloud_num})
#获取top10的子热词 def get_top_10_class(str): word_all = [] word_num = {} top_word_list=[] sql= "select title from paper_data where title like '%"+str+"%'" res = query(sql) for i in res: print(i) np_extractor = NPExtractor(i[0][1:]) result = np_extractor.extract() word_all=word_all+result for item in word_all: if(item not in word_num): word_num[item]=word_all.count(item) c = Counter(word_num) top_word_list=c.most_common() print(top_word_list) return top_word_list
