爬取冰冰B站千條評論，看看大家說了什麼

首頁>技術>小純程式設計2021-01-03 16:58

爬取冰冰B站千條評論，看看大家說了什麼

資料分析

import pandas as pd1

data = pd.read_excel(r"bingbing.xlsx")data.head()12

資料預處理資料描述

data.describe()1

等級點贊count1180.0000001180.000000mean4.4813562200.617797std1.04137910872.524850min2.0000001.00000025%4.0000004.00000050%5.0000009.00000075%5.000000203.750000max6.000000158457.000000

刪除空值

data.dropna()1

使用者性別等級評論點贊0食貧道男6[呆][呆][呆]你來了嘿！1584571畢導THU男6我是冰冰僅有的3個關注之一[tv_doge]我和冰冰貼貼1484392老師好我叫何同學男6[熱詞系列_知識增加]896343央視網快看保密6冰冰來了！我們要失業了嗎[doge][doge]1183704廈門大學保密5哇歡迎冰冰！！！66196..................1175黑旗魚保密511小時一百萬，好快[驚訝]51176是你的益達哦男6冰冰粉絲上漲速度：11小時107.3萬，平均每小時上漲9.75萬，每分鐘上漲1625，每秒鐘...51177快樂風男崔斯特男4軍訓的時候去了趟廁所，出來忘記是哪個隊伍了。看了up的影片才想起來，是三連[doge][滑稽]51178很認真的大熊男5我覺得冰冰主持春晚應該問題不大吧。[OK]51179飛拖鞋呀吼保密5《論一個2級號如何在2020年最後一天成為百大up主》5

1180 rows × 5 columns

刪除空值

data.drop_duplicates()1

1179 rows × 5 columns

視覺化點贊TOP20

df1 = data.sort_values(by="點贊",ascending=False).head(20)1

from pyecharts import options as optsfrom pyecharts.charts import Barfrom pyecharts.faker import Fakerc1 = (    Bar()    .add_xaxis(df1["評論"].to_list())    .add_yaxis("點贊數", df1["點贊"].to_list(), color=Faker.rand_color())    .set_global_opts(        title_opts=opts.TitleOpts(title="評論熱度Top20"),        datazoom_opts=[opts.DataZoomOpts(), opts.DataZoomOpts(type_="inside")],    )    .render_notebook())c1123456789101112131415

等級分佈

data.等級.value_counts().sort_index(ascending=False)1

6    1655    5024    3123    1382     63Name: 等級, dtype: int64123456

from pyecharts import options as optsfrom pyecharts.charts import Piefrom pyecharts.faker import Fakerc2 = (    Pie()    .add(        "",        [list(z) for z in zip([str(i) for i in range(2,7)], [63,138,312,502,165])],        radius=["40%", "75%"],    )    .set_global_opts(        title_opts=opts.TitleOpts(title="等級分佈"),        legend_opts=opts.LegendOpts(orient="vertical", pos_top="15%", pos_left="2%"),    )    .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))    .render_notebook())c212345678910111213141516171819

性別分佈

data.性別.value_counts().sort_index(ascending=False)1

from pyecharts import options as optsfrom pyecharts.charts import Piefrom pyecharts.faker import Fakerc4 = (    Pie()    .add(        "",        [list(z) for z in zip(["男","女","保密"], ["404",'103','673'])],        radius=["40%", "75%"],    )    .set_global_opts(        title_opts=opts.TitleOpts(title="性別分佈"),        legend_opts=opts.LegendOpts(orient="vertical", pos_top="15%", pos_left="2%"),    )    .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))    .render_notebook()    )c41234567891011121314151617181920

繪製詞雲圖

from wordcloud import WordCloudimport jiebafrom tkinter import _flattenfrom matplotlib.pyplot import imreadfrom PIL import Image, ImageDraw, ImageFontimport matplotlib.pyplot as plt123456

with open('stoplist.txt', 'r', encoding='utf-8') as f:    stopWords = f.read()with open('停用詞.txt','r',encoding='utf-8') as t:    stopWord = t.read()total = stopWord.split() + stopWords.split()12345

def my_word_cloud(data=None, stopWords=None, img=None):    dataCut = data.apply(jieba.lcut)  # 分詞    dataAfter = dataCut.apply(lambda x: [i for i in x if i not in stopWords])  # 去除停用詞    wordFre = pd.Series(_flatten(list(dataAfter))).value_counts()  # 統計詞頻    mask = plt.imread(img)    plt.figure(figsize=(20,20))    wc  = WordCloud(scale=10,font_path='C:/Windows/Fonts/STXINGKA.TTF',mask=mask,background_color="white",)    wc.fit_words(wordFre)    plt.imshow(wc)    plt.axis('off')12345678910

my_word_cloud(data=data["評論"],stopWords=stopWords,img="1.jpeg")1

資料收集

透過之前部落格的學習，想必大家已經對Python網路爬蟲有了瞭解，希望大家動手實踐，這裡就不放程式碼啦，建議參考：

劇多

爬取冰冰B站千條評論，看看大家說了什麼