# 导入包
import pandas as pd
import time
import requests
import json
from fake_useragent import UserAgentdef get_qq_comment(page_num):# 存储数据df_all = pd.DataFrame()for i in range(page_num):# 打印进度print('我正在获取第{}页的信息'.format(i))# 获取URLurl = 'https://c.y.qq.com/base/fcgi-bin/fcg_global_comment_h5.fcg?biztype=2&topid=12924001&cmd=8pagenum={}&pagesize=25'.format(i)# 添加headersheaders = {'user-agent': UserAgent().random}# 发起请求try:r = requests.get(url, headers=headers)except Exception as e:print(e)continue# 解析网页json_data = json.loads(r.text)# 获取数据comment_list = json_data['comment']['commentlist']# 昵称nick_name = [i.get('nick') for i in comment_list]# 评论内容content = [i.get('rootcommentcontent') for i in comment_list]# 评论时间comment_time = [i.get('time') for i in comment_list]# 点赞数praise_num = [i.get('praisenum') for i in comment_list]# 存储数据df = pd.DataFrame({'nick_name': nick_name,'content': content,'comment_time': comment_time,'praise_num': praise_num})# 追加数据df_all = df_all.append(df, ignore_index=True)# 休眠一秒time.sleep(1)return df_all# 运行函数
df = get_qq_comment(page_num=912) 

df.head()

# 导入所需包
import jieba
import stylecloud
from pyecharts.charts import Pie, Bar, Map, Line, WordCloud, Page
from pyecharts import options as opts
from pyecharts.globals import SymbolType, WarningType
WarningType.ShowWarning = False# 读入数据
df = pd.read_excel('../data/QQ音乐评论数据6.13.xlsx')# 查看重复值和空值
print(df.duplicated().sum())
print(df.isnull().sum()) 

# 转换函数
def transform_time(time_second):time_array = time.localtime(time_second)otherStyleTime = time.strftime('%Y-%m-%d %H:%M:%S', time_array) return otherStyleTime# 时间数据处理
df['comment_time'] = df['comment_time'].apply(lambda x: transform_time(x))# content初步处理
pattern = re.compile(r'[em](.*?)[/em]')
df['content'] = df.content.str.replace(pattern, '')
df.head() 

# 日期数量
comment_num = df.comment_time.str.split(':').str[0].value_counts().sort_index()
comment_num[:5]
2020-06-12 00    12673
2020-06-12 01     1185
2020-06-12 02      364
2020-06-12 03      146
2020-06-12 04       80
Name: comment_time, dtype: int64

# 产生数据
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='1350px', height='750px'))
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('Mojito评论人数走势图'), 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=False), linestyle_opts=opts.LineStyleOpts(width=3))
line1.render() 

def get_cut_words(content_series):# 读入停用词表stop_words = [] with open(r"stop_words.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 = ['周杰伦', '一首歌', '好好听', '方文山', '30多岁']    for i in my_words:jieba.add_word(i) #     自定义停用词my_stop_words = ['歌有', '真的', '这首', '一首', '一点', '反正', '一段', '一句', '首歌', '啊啊啊', '哈哈哈', '转发', '微博', '那段', '他会']   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.content)
text1[:5]
['致敬', '久石', '人生', '旋转', '木马']

# 绘制词云图
stylecloud.gen_stylecloud(text=' '.join(text1), max_words=1000,collocations=False,font_path=r'‪C:WindowsFontsmsyh.ttc',icon_name='fas fa-music',size=624,output_name='./词云图/QQ音乐评论词云图.png')