【大修bug】添加csv表格原始数据，修改词频统计函数bug

model/cipingTotal.csv

@@ -0,0 +1,100 @@
+('哈哈', 1236)
+('哈哈哈', 537)
+('哈哈哈哈', 157)
+('真的', 154)
+('期待', 89)
+('喜欢', 89)
+('doge', 88)
+('宝宝', 87)
+('可爱', 79)
+('第一', 73)
+('演唱', 71)
+('亲亲', 71)
+('苦涩', 70)
+('啊啊啊', 68)
+('抱抱', 64)
+('cry', 64)
+('宝贝', 62)
+('姐姐', 51)
+('花花', 50)
+('送花', 48)
+('开心', 47)
+('加油', 47)
+('老师', 46)
+('call', 45)
+('特别', 42)
+('一个', 42)
+('抓狂', 40)
+('嘻嘻', 39)
+('心心', 38)
+('悲伤', 38)
+('世界', 37)
+('感觉', 35)
+('孩子', 35)
+('朋友', 34)
+('鲜花', 34)
+('开学', 34)
+('好好', 34)
+('演唱会', 33)
+('感谢', 32)
+('憧憬', 31)
+('学季', 31)
+('快乐', 30)
+('漂亮', 30)
+('中国', 30)
+('音乐', 29)
+('电影', 28)
+('莲花', 28)
+('骄阳', 28)
+('视频', 27)
+('老公', 27)
+('老婆', 27)
+('值得', 26)
+('好看', 26)
+('消失', 26)
+('希望', 25)
+('呜呜', 25)
+('少年', 25)
+('东西', 25)
+('实力', 24)
+('评论', 24)
+('舞台', 24)
+('生活', 24)
+('单身', 24)
+('努力', 23)
+('唯一', 23)
+('幸福', 23)
+('时间', 23)
+('超级', 23)
+('辈子', 22)
+('童年', 22)
+('时代', 22)
+('可怜', 21)
+('不见', 21)
+('工作', 21)
+('有人', 21)
+('终于', 21)
+('粉丝', 21)
+('国家', 21)
+('callcallcall', 21)
+('永远', 21)
+('太阳', 20)
+('直播', 20)
+('小时', 20)
+('星期', 20)
+('安全', 20)
+('代言', 19)
+('支持', 19)
+('彩虹', 19)
+('妈妈', 18)
+('华为', 18)
+('优秀', 18)
+('好像', 18)
+('越来', 18)
+('大人', 18)
+('父母', 18)
+('害怕', 18)
+('安哥', 18)
+('加班', 18)
+('一点', 18)
+('一场', 17)

spider/navData.csv

@@ -0,0 +1,60 @@
+typeName,gid,containerid
+热门,102803,102803
+同城,1028032222,102803_2222
+榜单,102803600169,102803_ctg1_600169_-_ctg1_600169
+男篮,102803600279,102803_ctg1_600279_-_ctg1_600279
+明星,1028034288,102803_ctg1_4288_-_ctg1_4288
+车展,1028035188,102803_ctg1_5188_-_ctg1_5188
+搞笑,1028034388,102803_ctg1_4388_-_ctg1_4388
+情感,1028031988,102803_ctg1_1988_-_ctg1_1988
+周末,102803600195,102803_ctg1_600195_-_ctg1_600195
+电影,1028033288,102803_ctg1_3288_-_ctg1_3288
+社会,1028034188,102803_ctg1_4188_-_ctg1_4188
+电视剧,1028032488,102803_ctg1_2488_-_ctg1_2488
+美食,1028032688,102803_ctg1_2688_-_ctg1_2688
+俄乌局势,102803600267,102803_ctg1_600267_-_ctg1_600267
+国际,1028036288,102803_ctg1_6288_-_ctg1_6288
+深度,102803600155,102803_ctg1_600155_-_ctg1_600155
+财经,1028036388,102803_ctg1_6388_-_ctg1_6388
+读书,1028034588,102803_ctg1_4588_-_ctg1_4588
+摄影,1028034988,102803_ctg1_4988_-_ctg1_4988
+颜值,102803600165,102803_ctg1_600165_-_ctg1_600165
+体育,1028031388,102803_ctg1_1388_-_ctg1_1388
+数码,1028035088,102803_ctg1_5088_-_ctg1_5088
+综艺,1028034688,102803_ctg1_4688_-_ctg1_4688
+时尚,1028034488,102803_ctg1_4488_-_ctg1_4488
+星座,1028031688,102803_ctg1_1688_-_ctg1_1688
+军事,1028036688,102803_ctg1_6688_-_ctg1_6688
+股市,1028031288,102803_ctg1_1288_-_ctg1_1288
+房产,1028035588,102803_ctg1_5588_-_ctg1_5588
+家居,1028035888,102803_ctg1_5888_-_ctg1_5888
+萌宠,1028032788,102803_ctg1_2788_-_ctg1_2788
+科技,1028032088,102803_ctg1_2088_-_ctg1_2088
+科普,1028035988,102803_ctg1_5988_-_ctg1_5988
+动漫,1028032388,102803_ctg1_2388_-_ctg1_2388
+运动健身,1028034788,102803_ctg1_4788_-_ctg1_4788
+旅游,1028032588,102803_ctg1_2588_-_ctg1_2588
+瘦身,1028036488,102803_ctg1_6488_-_ctg1_6488
+好物,102803600094,102803_ctg1_600094_-_ctg1_600094
+历史,1028036788,102803_ctg1_6788_-_ctg1_6788
+艺术,1028035488,102803_ctg1_5488_-_ctg1_5488
+美妆,1028031588,102803_ctg1_1588_-_ctg1_1588
+法律,1028037388,102803_ctg1_7388_-_ctg1_7388
+设计,1028035388,102803_ctg1_5388_-_ctg1_5388
+健康,1028032188,102803_ctg1_2188_-_ctg1_2188
+音乐,1028035288,102803_ctg1_5288_-_ctg1_5288
+游戏,1028034888,102803_ctg1_4888_-_ctg1_4888
+新时代,1028037968,102803_ctg1_7968_-_ctg1_7968
+校园,102803600177,102803_ctg1_600177_-_ctg1_600177
+收藏,1028038189,102803_ctg1_8189_-_ctg1_8189
+政务,1028035788,102803_ctg1_5788_-_ctg1_5788
+养生,1028036588,102803_ctg1_6588_-_ctg1_6588
+育儿,1028033188,102803_ctg1_3188_-_ctg1_3188
+抽奖,102803600037,102803_ctg1_600037_-_ctg1_600037
+教育,102803600080,102803_ctg1_600080_-_ctg1_600080
+婚恋,1028031788,102803_ctg1_1788_-_ctg1_1788
+舞蹈,1028038788,102803_ctg1_8788_-_ctg1_8788
+辟谣,1028036988,102803_ctg1_6988_-_ctg1_6988
+公益,102803600057,102803_ctg1_600057_-_ctg1_600057
+问答,1028037977,102803_ctg1_7977_-_ctg1_7977
+三农,1028037188,102803_ctg1_7188_-_ctg1_7188

utils/getEchartsData.py

@@ -1,21 +1,22 @@
 from utils.getPublicData import *
+from snownlp import SnowNLP
 articleList = getAllArticleData()
 commentList = getAllCommentsData()
 
-def getTypeList():# 返回爬取到的所有文章的类型（已去重）
+def getTypeList():
     return list(set([x[8] for x in getAllArticleData()]))
 
-def getArticleByType(type):# 根据特定文章类型筛选文章
+def getArticleByType(type):
     articles = []
     for i in articleList:
         if i[8] == type:
             articles.append(i)
     return articles
 
-def getArticleCharLikeCount(type):# 统计特定类型文章的点赞数分布
+def getArticleCharLikeCount(type):
     articles = getArticleByType(type)
     xData = ['0-100','100-1000','1000-5000','5000-15000','15000-30000','30000-50000','50000-~']
-    yData = [0 for x in range(len(xData))]# 初始化为长度和xData相同但是每一个元素都是零的列表
+    yData = [0 for x in range(len(xData))]
     for article in articles:
         likeCount = int(article[1])
         if likeCount < 100:
@@ -34,10 +35,10 @@ def getArticleCharLikeCount(type):# 统计特定类型文章的点赞数分布
             yData[6] += 1
     return xData,yData
 
-def getArticleCharCommentsLen(type):# 统计特定类型文章的评论数分布
+def getArticleCharCommentsLen(type):
     articles = getArticleByType(type)
     xData = ['0-100','100-500','500-1000','1000-1500','1500-3000','3000-5000','5000-10000','10000-15000','15000-~']
-    yData = [0 for x in range(len(xData))]# 初始化为长度和xData相同但是每一个元素都是零的列表
+    yData = [0 for x in range(len(xData))]
     for article in articles:
         commentLen = int(article[2])
         if commentLen < 100:
@@ -60,7 +61,7 @@ def getArticleCharCommentsLen(type):# 统计特定类型文章的评论数分布
             yData[8] += 1
     return xData,yData
 
-def getArticleCharRepotsLen(type):# 统计特定类型文章的转发数分布
+def getArticleCharRepotsLen(type):
     articles = getArticleByType(type)
     xData = ['0-100','100-300','300-500','500-1000','1000-2000','2000-3000','3000-4000','4000-5000','5000-10000','10000-15000','15000-30000','30000-70000','70000-~']
     yData = [0 for x in range(len(xData))]
@@ -92,14 +93,14 @@ def getArticleCharRepotsLen(type):# 统计特定类型文章的转发数分布
             yData[11] += 1
     return xData,yData
 
-def getIPCharByArticleRegion():#统计文章发布地域的分布情况
+def getIPCharByArticleRegion():
     articleRegionDic = {}
     for i in articleList:
-        if i[4] != '无':# 如果ip为确定值的话就进行下一步
+        if i[4] != '无':
-            if i[4] in articleRegionDic.keys():
+            if articleRegionDic.get(i[4],-1) == -1:
-                articleRegionDic[i[4]] += 1
-            else:
                 articleRegionDic[i[4]] = 1
+            else:
+                articleRegionDic[i[4]] += 1
     resultData = []
     for key,value in articleRegionDic.items():
         resultData.append({
@@ -108,14 +109,14 @@ def getIPCharByArticleRegion():#统计文章发布地域的分布情况
         })
     return resultData
 
-def getIPCharByCommentsRegion():#统计评论发布地域的分布情况
+def getIPCharByCommentsRegion():
     commentRegionDic = {}
     for i in commentList:
         if i[3] != '无':
-            if i[3] in commentRegionDic.keys():
+            if commentRegionDic.get(i[3],-1) == -1:
-                commentRegionDic[i[3]] += 1
-            else:
                 commentRegionDic[i[3]] = 1
+            else:
+                commentRegionDic[i[3]] += 1
     resultData = []
     for key,value in commentRegionDic.items():
         resultData.append({
@@ -124,35 +125,33 @@ def getIPCharByCommentsRegion():#统计评论发布地域的分布情况
         })
     return resultData
 
-def getCommentCharDataOne():# 统计评论点赞数的分布情况
+def getCommentCharDataOne():
     xData = []
     rangeNum = 20
-    for item in range(100):
+    for item in range(1,100):
         xData.append(str(rangeNum * item) + '-' + str(rangeNum * (item + 1)))
     yData = [0 for x in range(len(xData))]
     for comment in commentList:
-        for item in range(100):
+        for item in range(99):
-            if int(comment[2]) < rangeNum * (item + 1):
+            if int(comment[2]) < rangeNum * (item + 2):
                 yData[item] += 1
                 break
     return xData,yData
 
-def getCommentCharDataTwo():# 统计评论数据中不同性别的数量
+def getCommentCharDataTwo():
     genderDic = {}
     for i in commentList:
-        if i[6] in genderDic.keys():
+        if genderDic.get(i[6],-1) == -1:
-            genderDic[i[6]] += 1
-        else:
             genderDic[i[6]] = 1
-    resultData = []
+        else:
-    for key,value in genderDic.items():
+            genderDic[i[6]] += 1
-        resultData.append({
+    resultData = [{
-            'name':key,
+        'name':x[0],
-            'value':value
+        'value':x[1]
-        })
+    } for x in genderDic.items()]
     return resultData
 
-def getYuQingCharDataOne():# 统计热词中正面、中性、负面的数量
+def getYuQingCharDataOne():
     hotWordList = getAllHotWords()
     xData = ['正面','中性','负面']
     yData = [0,0,0]
@@ -164,19 +163,19 @@ def getYuQingCharDataOne():# 统计热词中正面、中性、负面的数量
             yData[1] += 1
         elif emotionValue < 0.5:
             yData[2] += 1
-    finalData = [{
+    bieData = [{
         'name':x,
         'value':yData[index]
     } for index,x in enumerate(xData)]
-    return xData,yData,finalData
+    return xData,yData,bieData
 
-def getYuQingCharDataTwo():# 统计评论列表和文章列表中的情感值
+def getYuQingCharDataTwo():
     xData = ['正面', '中性', '负面']
-    finalData1 = [{
+    bieData1 = [{
         'name':x,
         'value':0
     } for x in xData]
-    finalData2 = [{
+    bieData2 = [{
         'name': x,
         'value': 0
     } for x in xData]
@@ -184,27 +183,27 @@ def getYuQingCharDataTwo():# 统计评论列表和文章列表中的情感值
     for comment in commentList:
         emotionValue = SnowNLP(comment[4]).sentiments
         if emotionValue > 0.5:
-            finalData1[0]['value'] += 1
+            bieData1[0]['value'] += 1
         elif emotionValue == 0.5:
-            finalData1[1]['value'] += 1
+            bieData1[1]['value'] += 1
         elif emotionValue < 0.5:
-            finalData1[2]['value'] += 1
+            bieData1[2]['value'] += 1
     for artile in articleList:
         emotionValue = SnowNLP(artile[5]).sentiments
         if emotionValue > 0.5:
-            finalData2[0]['value'] += 1
+            bieData2[0]['value'] += 1
         elif emotionValue == 0.5:
-            finalData2[1]['value'] += 1
+            bieData2[1]['value'] += 1
         elif emotionValue < 0.5:
-            finalData2[2]['value'] += 1
+            bieData2[2]['value'] += 1
-    return finalData1,finalData2
+    return bieData1,bieData2
 
-def getYuQingCharDataThree():# 提取前10个热词及其对应的出现频率
+def getYuQingCharDataThree():
     hotWordList = getAllHotWords()
-    xData = []
+    x1Data = []
-    yData = []
+    y1Data = []
     for i in hotWordList[:10]:
-        xData.append(i[0])
+        x1Data.append(i[0])
-        yData.append(int(i[1]))
+        y1Data.append(int(i[1]))
-    return xData,yData
+    return x1Data,y1Data