《爱情公寓》电影，让我十年的情怀，一瞬间都喂了狗

作者

丁彦军

来源

恋习Python

如需转载，请联系原作者授权。

import requests
import time 
import random
import json

#获取每一页数据
def get_one_page(url):

    response = requests.get(url=url)
    if response.status_code == 200:
        return response.text
    return None

#解析每一页数据
def parse_one_page(html):

    data = json.loads(html)['cmts']#获取评论内容
    for item in data:
        yield{
        'date':item['time'].split(' ')[0],
        'nickname':item['nickName'],
        'city':item['cityName'],
        'rate':item['score'],
        'conment':item['content']
        }

#保存到文本文档中
def save_to_txt():
    for i in range(1,1001):

        print("开始保存第%d页" % i)
        url = 'http://m.maoyan.com/mmdb/comments/movie/1175253.json?_v_=yes&offset=' + str(i)

        html = get_one_page(url)
        for item in parse_one_page(html):
            with open('爱情公寓.txt','a',encoding='utf-8') as f:
                f.write(item['date'] + ','+item['nickname'] +','+item['city'] +','
                    +str(item['rate']) +',' +item['conment']+'n')
                #time.sleep(random.randint(1,100)/20)
                time.sleep(2)

#去重重复的评论内容
def delete_repeat(old,new):
    oldfile = open(old,'r',encoding='utf-8')
    newfile = open(new,'w',encoding='utf-8')
    content_list = oldfile.readlines() #获取所有评论数据集
    content_alread = [] #存储去重后的评论数据集

    for line in content_list:
        if line not in content_alread:
            newfile.write(line+'n')
            content_alread.append(line)

if __name__ == '__main__':
    save_to_txt()
    delete_repeat(r'爱情公寓_old.txt',r'爱情公寓_new.txt')

from wordcloud import WordCloud,STOPWORDS
import pandas as pd 
import jieba
import matplotlib.pyplot as plt 
#import seaborn as sns
from pyecharts import Geo,Style,Line,Bar,Overlap

f = open('爱情公寓_new.txt',encoding='utf-8')
data = pd.read_csv(f,sep=',',header=None,encoding='utf-8',names=['date','nickname','city','rate','comment'])

city = data.groupby(['city'])
rate_group = city['rate']
city_com = city['rate'].agg(['mean','count'])
#print(city_com)
city_com.reset_index(inplace=True)
city_com['mean'] = round(city_com['mean'],2)

#热力图分析
data_map = [(city_com['city'][i],city_com['count'][i]) for i in range(0,city_com.shape[0])]
#print(data_map)
style = Style(title_color="#fff",title_pos = "center",
            width = 1200,height = 600,background_color = "#404a59")

geo = Geo("《爱情公墓》粉丝人群地理位置","数据来源：恋习Python",**style.init_style)

while True:
    try:
        attr,val = geo.cast(data_map)
        geo.add("",attr,val,visual_range=[0,20],
                visual_text_color="#fff",symbol_size=20,
                is_visualmap=True,is_piecewise=True, 
                visual_split_number=4)
    except ValueError as e:
        e = str(e)
        e = e.split("No coordinate is specified for ")[1]#获取不支持的城市名
        for i in range(0,len(data_map)):
            if e in data_map[i]:
                data_map.pop[i]
                break

    else:
        break
geo.render('爱情公墓.html')

#折线+柱图分析
city_main = city_com.sort_values('count',ascending=False)[0:20]
#print(city_main)
attr = city_main['city']
v1 = city_main['count']
v2 = city_main['mean']
#print(attr,v1,v2)
line = Line("主要城市评分")
line.add("城市",attr,v2,is_stack=True,xaxis_rotate=30,yaxix_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("主要城市评论数")
bar.add("城市",attr,v1,is_stack=True,xaxis_rotate=30,yaxix_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('主要城市评论数_平均分.html')


#词云分析
#分词
comment = jieba.cut(str(data['comment']),cut_all=False)
wl_space_split = " ".join(comment)

#导入背景图
backgroud_Image = plt.imread('lan.jpg') 
stopwords = STOPWORDS.copy()
#print("STOPWORDS.copy()",help(STOPWORDS.copy()))


wc = WordCloud(width=1024,height=768,background_color='white',
    mask=backgroud_Image,font_path="C:simhei.ttf",
    stopwords=stopwords,max_font_size=400,
    random_state=50)

wc.generate_from_text(wl_space_split)
plt.imshow(wc)
plt.axis('off')#不显示坐标轴  
plt.show()
wc.to_file(r'laji.jpg')