大家，我是K同学啊！
近期一部《长津湖》火爆朋友圈，被各种安利，咱一个人也不想跑电影院去霸个情侣座，就老老实实分析一下影评，看看大家的“观后感”是吧~ 首先定位目标网页
“
”
上爬虫，抓取下面四个字段
然后使用pandas对导入数据并做简单的处理
import pandas as pd
import os
file_path = os.path.join("douban.csv")
#读取test.csv文件中的A、B列，若不设置usecols参数，默认读取全部数据。
df = pd.read_csv(open(file_path,'r',encoding='utf-8'), names=["用户名","星评","评论时间","评论"])
df.head()
star_num = df.星评.value_counts()
star_num = star_num.sort_index()
star_num
力荐 112
推荐 35
该用户未星评 2
较差 14
还行 37
Name: 星评, dtype: int64
豆瓣短评评分占比
from pyecharts.charts import Pie, Bar, Line, Page
from pyecharts import options as opts
from pyecharts.globals import SymbolType
# 数据对
data_pair = [list(z) for z in zip([i for i in star_num.index], star_num.values.tolist())]
# 饼图
pie1 = Pie(init_opts=opts.InitOpts(width='800px', height='400px'))
pie1.add('', data_pair, radius=['35%', '60%'])
pie1.set_global_opts(title_opts=opts.TitleOpts(title='豆瓣短评评分占比'),
legend_opts=opts.LegendOpts(orient='vertical', pos_top='15%', pos_left='2%')
)
pie1.set_series_opts(label_opts=opts.LabelOpts(formatter='{b}:{d}%'))
pie1.render_notebook()
在这里插入图片描述
评论数量走势图
# 折线图
line1 = Line(init_opts=opts.InitOpts(width='800px', height='400px'))
line1.add_xaxis(comment_date.index.tolist())
line1.add_yaxis('', comment_date.values.tolist(),
#areastyle_opts=opts.AreaStyleOpts(opacity=0.5),
label_opts=opts.LabelOpts(is_show=False))
line1.set_global_opts(title_opts=opts.TitleOpts(title='评论数量走势图'),
# toolbox_opts=opts.ToolboxOpts(),
visualmap_opts=opts.VisualMapOpts(max_=140))
line1.set_series_opts(linestyle_opts=opts.LineStyleOpts(width=4))
line1.render_notebook()
9月30号上映，9月29号就开始造势了，30号达到高峰，但是1号似乎势头大减啊。
词云图
正面
import jieba
def get_cut_words(content_series):
# 读入停用词表
stop_words = []
with open(r"hit_stopwords.txt", 'r', encoding='utf-8') as f:
lines = f.readlines()
for line in lines:
stop_words.append(line.strip())
# 添加关键词
my_words = ['长津湖', '志愿军']
for i in my_words:
jieba.add_word(i)
# 自定义停用词
my_stop_words = ['电影',"长津湖","战争"]
stop_words.extend(my_stop_words)
# 分词
word_num = jieba.lcut(content_series.str.cat(sep='。'), cut_all=False)
# 条件筛选
word_num_selected = [i for i in word_num if i not in stop_words and len(i)>=2]
return word_num_selected
text1 = get_cut_words(content_series=df[(df.星评=='力荐')|(df.星评=='推荐')]['评论'])
text1[:5]
['牺牲', '冰雪', '战士', '应该', '遗忘']
import stylecloud
from IPython.display import Image # 用于在jupyter lab中显示本地图片
# 绘制词云图
stylecloud.gen_stylecloud(text=' '.join(text1),
max_words=1000,
collocations=False,
font_path=r'经典综艺体简.ttf',
icon_name='fas fa-thumbs-up',
size=360,
output_name='豆瓣正向评分词云图.png')
Image(filename='豆瓣正向评分词云图.png')
负面
text2 = get_cut_words(content_series=df[(df.星评=='还行')|(df.星评=='较差')]['评论'])
text2[:5]
['有点', '失望', '剧情', '一如既往', '人物']
# 绘制词云图
stylecloud.gen_stylecloud(text=' '.join(text2),
max_words=1000,
collocations=False,
font_path=r'经典综艺体简.ttf',
icon_name='fas fa-thumbs-down',
size=350,
output_name='豆瓣负向评分词云图.png')
Image(filename='豆瓣负向评分词云图.png')
