如何基于Python爬取隐秘的角落评论

def get_comment_html(movieId, movieName, lastId):#将获取评论的json源码，保存到txt文件中
  url = "http://sns-comment.iqiyi.com/v3/comment/get_comments.action?"
  params = {
    "types":"time",
    "business_type":"17",
    "agent_type":"118",
    "agent_version":"9.11.5",
    "authcookie":"authcookie"
  }
  for item in params:
    url = url + item + "=" + params[item] + "&"
  url = url + "content_id=" + movieId+ "&last_id=" + lastId
  #url 为拼接好的评论地址  

  headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36",
    "Accept": "application/json, text/javascript",
    "Referer": "https://www.iqiyi.com/v_19rxtiliso.html?vfm=2008_aldbd&fv=p_02_01",

  }
  response = requests.get(url, headers=headers)  
  filename = movieId + movieName+".txt"
  if response.status_code == 200:    
    with open(filename,"a",encoding='utf-8') as f:
      f.write(response.text+"\n")
    #将获取的评论json源码保存到txt文件，一次写入一行，表示获取的这一页的评论      
  else:
    print("request error")
  print("爬取第{}页评论".format(file_lines(filename)))
  time.sleep(0.5)  
  last_id = parseData(response.text) #解析并获取下一个id  
  if last_id != "End":
    get_comment_html(movieId, movieName, parseData(response.text))
  else:
    print("已到结尾")
    #continue#结束整个程序
  return None

from pyecharts.charts import Bar ##导入需要使用的图表
from pyecharts import options as opts ##导入配置项

comment_num3 = df["集数"].value_counts().sort_index()

x_line3 = comment_num3.index.to_list()
y_line3 = comment_num3.values.tolist()

bar1=(
   Bar(init_opts=opts.InitOpts(width='800px', height='350px')) ##定义为柱状图
   .add_xaxis(x_line3) ##X轴的值
   .add_yaxis('评论数',y_line3) ##y的值和y的一些数据配置项
   .set_global_opts(title_opts=opts.TitleOpts(title='《隐秘的角落》1-12集评论数量'))
  
   )
                                    
bar1.render("bar3.html") ###输出html文件

from pyecharts.charts import Line ##导入需要使用的图表
from pyecharts import options as opts ##导入配置项

comment_num = df["留言时间"].str.split(' ').str[0].value_counts().sort_index()


x_line1 = [i.replace('2020-','') for i in comment_num.index.to_list()] 
y_line1 = comment_num.values.tolist()

# 绘制面积图
line1 = Line(init_opts=opts.InitOpts(width='1200px', height='600px'))
line1.add_xaxis(x_line1)
line1.add_yaxis('', y_line1,
        markpoint_opts=opts.MarkPointOpts(data=[
          opts.MarkPointItem(type_='max', name='最大值'),
          opts.MarkPointItem(type_='min', name='最小值')
        ])) 
line1.set_global_opts(title_opts=opts.TitleOpts('《隐秘的角落》开播10天内评论走势'), 
           xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate='30')),
           #visualmap_opts=opts.VisualMapOpts(max_=12673)
           ) 
line1.set_series_opts(label_opts=opts.LabelOpts(is_show=True), 
           linestyle_opts=opts.LineStyleOpts(width=2))
line1.render("Line.html")

from pyecharts.charts import Bar ##导入需要使用的图表
from pyecharts import options as opts ##导入配置项

comment_num2 = df["留言时间"].str.split(' ').str[1].str.split(":").str[0].value_counts().sort_index()

x_line2 = comment_num2.index.to_list()
y_line2 = comment_num2.values.tolist()

bar1=(
   Bar(init_opts=opts.InitOpts(width='800px', height='350px')) ##定义为柱状图
   .add_xaxis(x_line2) ##X轴的值
   .add_yaxis('评论数',y_line2) ##y的值和y的一些数据配置项
   .set_global_opts(title_opts=opts.TitleOpts(title='《隐秘的角落》0-23时评论数量'))
  
   )
                                    
bar1.render("bar2.html") ###输出html文件

def comment_word_group(strings): #评论字数分组函数
  if len(strings)<=10:
    length = 0
  elif len(strings) > 10 and len(strings)<=30:
    length = 1
  elif len(strings) >30 and len(strings) <=50:
    length = 2
  else:
    length = 3
  return length

df["留言数量组别"] = df["留言内容"].apply(lambda x:comment_word_group(x))#评论字数分组

lengthData = df.groupby(['留言数量组别'])["留言内容"].count()#评论字数分组统计

from pyecharts.charts import Bar ##导入需要使用的图表
from pyecharts import options as opts ##导入配置项

attr = ["10字以内","10~30字","30~50字","50字以上"] #X轴
v1 = lengthData.values.tolist() #Y轴

bar1=(
   Bar(init_opts=opts.InitOpts(width='800px', height='350px')) ##定义为柱状图
   .add_xaxis(attr) ##X轴的值
   .add_yaxis('评论数量',v1) ##y的值和y的一些数据配置项
   .set_global_opts(title_opts=opts.TitleOpts(title='《隐秘的角落》评论字数分布'))  
   )                                    
bar1.render("bar.html") ###输出html文件

#词云
from PIL import Image
from wordcloud import WordCloud,ImageColorGenerator,STOPWORDS
import jieba
import matplotlib.pyplot as plt
import numpy as np

contents = df["留言内容"].str.cat(sep=" ")
contents

sw = set(STOPWORDS)
sw.add("这个")
sw.add("什么")

cut_text2 = " ".join(jieba.lcut(contents))

background_image = np.array(Image.open("bg.png"))

wc = WordCloud(font_path=r'C:\Windows\Fonts\simhei.ttf',
        background_color='White',
        max_words=3000,
        width=1000,
        height=500,
        scale=1,
        stopwords=sw,#停用词
        mask = background_image
        )
#font_path：设置字体，max_words：出现的最多词数量，mask参数=图片背景，必须要写上，另外有mask参数再设定宽高是无效的
wc.generate(cut_text2)
wc.to_file("a2.jpg")


#将图绘制出来
plt.imshow(wc)
plt.axis("off") 
plt.show()