如何用Python对某娅偷逃税进行微博舆情分析~

key = input("请输入爬取关键字:")
for page in range(1,10):
  params = (
      ('containerid', f'100103type=1&q={key}'),
      ('page_type', 'searchall'),
      ('page', str(page)),
  )

  response = requests.get('https://m.weibo.cn/api/container/getIndex', headers=headers, params=params)

r = response.text
title = re.findall('"page_title":"(.*?)"',r)
comments_count = re.findall('"comments_count":(.*?),',r)
attitudes_count = re.findall('"attitudes_count":(.*?),',r)
for i in range(len(title)):
  print(eval(f"'{title[i]}'"),comments_count[i],attitudes_count[i])

for i in range(len(title)):
   try:
       with open(f'{key}.csv', 'a', newline='') as f:
           writer = csv.writer(f)
           writer.writerow([eval(f"'{title[i]}'"),comments_count[i],attitudes_count[i],reposts_count[i],created_at[i].split()[-1],created_at[i].split()[1],created_at[i].split()[2],created_at[i].split()[0],created_at[i].split()[3]])
   except:
       pass

import pandas as pd

df = pd.read_csv('薇娅.csv',encoding='gbk')
print(df.head(10))

c = []
for i in list(df['月']):
   if i == 'Nov':
       c.append(11)
   elif i == 'Dec':
       c.append(12)
   elif i == 'Apr':
       c.append(4)
   elif i == 'Jan':
       c.append(1)
   elif i == 'Oct':
       c.append(10)
   else:
       c.append(7)
df['月'] = c
df.to_csv('薇娅.csv',encoding='gbk',index=False)

df.info()

from pyecharts.charts import Bar
from pyecharts import options as opts
from collections import Counter # 统计词频
c=[]
d={}
a = 0
for i in list(df['月']):
    if i == 12:
        if list(df['日'])[a] notin c:
            c.append(list(df['日'])[a])
    a+=1
a = 0
for i in c:
    d[i]=0

for i in list(df['月']):
    if i == 12:
        d[list(df['日'])[a]]+=1
    a += 1
columns = []
data = []
for k,v in d.items():
    columns.append(k)
    data.append(v)
bar = (
        Bar()
        .add_xaxis(columns)
        .add_yaxis("条数", data)
        .set_global_opts(title_opts=opts.TitleOpts(title="每日微博数量"))
    )
bar.render("词频.html")

import pandas as pd
df = pd.read_csv('weiya.csv',encoding='gbk')
c=[]
d={}
a = 0
for i in list(df['时']):
    if i notin c:
        c.append(i)
a = 0
for i in c:
    d[i]=0

for i in list(df['时']):
    d[i]+=1

print(d)
from collections import Counter # 统计词频
from pyecharts.charts import Bar
from pyecharts import options as opts
columns = []
data = []
for k,v in d.items():
    columns.append(k)
    data.append(v)
bar = (
        Bar()
        .add_xaxis(columns)
        .add_yaxis("时间", data)
        .set_global_opts(title_opts=opts.TitleOpts(title="时间分布"))
    )
bar.render("词频.html")

from imageio import imread
import jieba
from wordcloud import WordCloud, STOPWORDS
with open("weiya.txt",encoding='utf-8') as f:
    job_title_1 = f.read()
with open('停用词表.txt','r',encoding='utf-8') as f:
    stop_word = f.read()
word = jieba.cut(job_title_1)
words = []
for i in list(word):
    if i notin stop_word:
        words.append(i)
contents_list_job_title = " ".join(words)
wc = WordCloud(stopwords=STOPWORDS.add("一个"), collocations=False,
               background_color="white",
               font_path=r"K:\苏新诗柳楷简.ttf",
               width=400, height=300, random_state=42,
               mask=imread('xin.jpg', pilmode="RGB")
               )
wc.generate(contents_list_job_title)
wc.to_file("推荐语.png")