import re

import requests     # 發(fā)送網(wǎng)絡(luò)請求
import pandas as pd # 保存數(shù)據(jù)

headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36'
}
# 構(gòu)建一個列表儲存數(shù)據(jù)
data_list = []
for page in range(15, 1500, 30):
    url = f'https://mfm.video.qq.com/danmu?otype=json&target_id=7626435152%26vid%3Dp0041oidttf&session_key=0%2C174%2C1642248894&timestamp={page}'
    esponse = requests.get(url=url, headers=headers)

json_data = response.json()

comments = json_data['comments']
print(comments)
for comment in comments:
    data_dict = {}
    data_dict['commentid'] = comment['commentid']
    content = comment['content']
    content = re.sub(r'[\x0e\xa0]', '', content)

    data_dict['content'] = content
    data_dict['opername'] = comment['opername']
    print(data_dict)
    data_list.append(data_dict)

df = pd.DataFrame(data_list)
# 亂碼, 指定編碼 為 utf-8 或者是 gbk 或者 utf-8-sig
df.to_csv('data.csv', encoding='utf-8-sig')

import jieba
from pyecharts.charts import WordCloud
import pandas as pd
from pyecharts import options as opts

wordlist = []
data = pd.read_csv('data.csv')['content']
data

a = [list(z) for z in zip(word, count)]
c = (
    WordCloud()
    .add('', a, word_size_range=[10, 50], shape='circle')
    .set_global_opts(title_opts=opts.TitleOpts(title="詞云圖"))
)
c.render_notebook()