Python采集电视剧《开端》弹幕做成词云图

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

import requests

import pandas as pd

# 构建一个列表存储数据

data_set = []

for page in range(15, 600, 30):

    try:

        # 1. 发送请求

        url = f'https://mfm.video.qq.com/danmu?otype=json&target_id=7626117232%26vid%3Dn0041aa087e&session_key=0%2C0%2C0&timestamp={page}&_=1641804763748'

        response = requests.get(url=url)

        # 2. 获取数据

        json_data = response.json()

        # 3. 解析数据

        comments = json_data['comments']

        for comment in comments:

            data_dict = {}

            data_dict['commentid'] = comment['commentid']

            data_dict['content'] = comment['content']

            data_dict['opername'] = comment['opername']

            print(data_dict)

            data_set.append(data_dict)

    except:

        pass

# 4. 保存数据

df = pd.DataFrame(data_set)

df.to_csv('data.csv', index=False)

1

2

3

4

5

6

7

8

9

word = dfword3['word'].tolist()

count = dfword3['count'].tolist()

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="词云图"))

)

c.render_notebook()