轉自微信公眾號《資料森麟》
直接上程式碼：

# 呼叫相關包
import json
import random
import requests
import time
import pandas as pd
import os
from pyecharts import Bar, Geo, Line, Overlap
import jieba
from scipy.misc import imread
from wordcloud import WordCloud, ImageColorGenerator
import  matplotlib.pyplot as plt
from collections import
 
 Counter

# 設定headers和cookie
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win32; x32; rv:54.0) Gecko/20100101 Firefox/54.0',
    'Connection': 'keep-alive'
}
cookies = '你的Cookies'
cookie = {}
for line in cookies.split(';'):
    name, value = cookies.strip().split('=', 1)
    cookie[name] = value

# 爬取資料
 

tomato = pd.DataFrame(columns=['data', 'score', 'city', 'comment', 'nick'])
for i in range(0, 1000):
    j = random.randint(1, 1000)
    print(str(i) + ' ' + str(j))
    try:
        time.sleep(2)
        url = 'http://m.maoyan.com/mmdb/comments/movie/1212592.json?_v_=yes&offset=' + str(j)
        html = requests.
 
get(url=url, cookies=cookie, headers=headers).content
        data = json.loads(html.decode('utf-8'))['cmts']
        for item in data:
            tomato = tomato.append({'data': item['time'].split(' ')[0],
                                    'city': item['cityName'],
                                    'score': item['score'],
                                    'comment': item['content'],
                                    'nick': item['nick']}, ignore_index=True)

        tomato.to_excel('西虹市首富.xlsx', index=False)
    except:
        continue

# 可以直接讀取已經爬取的資料進行分析
tomato_com = pd.read_excel('西虹市首富.xlsx')
grouped = tomato_com.groupby(['city'])
grouped_pct = grouped['score']

# 全國熱力圖
city_com = grouped_pct.agg(['mean', 'count'])
city_com.reset_index(inplace=True)
city_com['mean'] = round(city_com['mean'], 2)
data = [(city_com['city'][i], city_com['count'][i]) for i in range(0, city_com.shape[0])]
geo = Geo('《西虹市首富》全國熱力圖', title_color="#fff",
          title_pos="center", width=1200, height=600, background_color='#404a59')
attr, value = geo.cast(data)
geo.add("", attr, value, type="heatmap", visual_range=[0, 200],
        visual_text_color="#fff", symbol_size=10, is_visualmap=True,
        is_roam=False)
geo.render('西虹市首富.html')

# 主要城市評論數與評分
city_main = city_com.sort_values('count', ascending=False)[0:20]
attr = city_main['city']
v1 = city_main['count']
v2 = city_main['mean']
line = Line("主要城市評分")
line.add("城市", attr, v2, is_stack=True, xaxis_rotate=30, yaxis_min=4.2,
        mark_point=['min', 'max'], xaxis_interval=0, line_color='lightblue',
        line_width=4, mark_point_textcolor='black', mark_point_color='lightblue',
         is_splitline_show=False)
bar = Bar("主要城市評論數")
bar.add("城市", attr, v1, is_stack=True, xaxis_rotate=30, yaxis_min=4.2,
        xaxis_interval=0, is_splitline_show=False)
overlap = Overlap()
overlap.add(bar)
overlap.add(line, yaxis_index=1, is_add_yaxis=True)
overlap.render('主要城市評論數_平均分.html')

# 主要城市評分全國分佈
city_score_area = city_com.sort_values('count', ascending=False)[0:30]
city_score_area.reset_index(inplace=True)
data = [(city_score_area['city'][i], city_score_area['mean'][i]) for i in range(0, city_score_area.shape[0])]
geo = Geo('《西虹市首富》全國主要城市打分圖', title_color="#fff", title_pos="center",
          width=1200, height=600, background_color='#404a59')
attr, value = geo.cast(data)
geo.add("", attr, value, visual_range=[4.4, 4.8],
        visual_text_color="#fff", symbol_size=15, is_visualmap=True, is_roam=False)
geo.render('西虹市首富全國主要城市打分圖.html')

# 主要城市評分降序
city_score = city_main.sort_values('mean', ascending=False)[0:20]
attr = city_score['city']
v1 = city_score['mean']
line = Line("主要城市評分")
line.add("城市", attr, v1, is_stack=True, xaxis_rotate=30, yaxis_min=4.2, mark_point=['min', 'max'], xaxis_interval=0,
            line_color='lightblue', line_width=4, mark_point_textcolor='black',
         mark_point_color='lightblue', is_splitline_show=False)
line.render('主要城市評分.html')

# 繪製詞雲
tomato_str = ' '.join(tomato_com['comment'])
words_list = []
word_generator = jieba.cut_for_search(tomato_str)
for word in word_generator:
    words_list.append(word)
words_list = [k for k in words_list if len(k)>1]
back_color = imread('西紅柿.jpg')
wc = WordCloud(background_color='white',
            max_words=200,
            mask=back_color,
            max_font_size=300,
            font_path="C:/Windows/Fonts/SimHei.ttf",
            random_state=42,
            )
tomato_count = Counter(words_list)
wc.generate_from_frequencies(tomato_count)
image_colors = ImageColorGenerator(back_color)
plt.figure()
plt.imshow(wc.recolor(color_func=image_colors))
plt.axis('off')
plt.savefig('wordcloud.png', dpi=200)
plt.show()