Python获取高分热播剧弹幕数据，制作词云分析

前言

环境介绍

• python 3.8
• pycharm
• requests >>> pip install requests
• pandas >>> pip install pandas
• jieba
• stylecloud

获取弹幕代码

请求数据

# 伪装
headers = {
    # 浏览器基本信息
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36'
}
url = f'https://dm.video.qq.com/barrage/segment/u00445z1gcx/t/v1/0/30000'
response = requests.get(url, headers=headers)

获取数据

# .text: 字符串
# .json(): 字典, {"":"", "":""} 包裹起来的内容
json_data = response.json()
barrage_list = json_data['barrage_list']

解析数据

# 遍历 循环
for i in range(0, len(barrage_list)):
    content = json_data['barrage_list'][i]['content']
    nick = json_data['barrage_list'][i]['nick']
    id = json_data['barrage_list'][i]['id']
    print(id, nick, content)

保存弹幕

with open('弹幕.csv', mode='a', encoding='utf-8-sig', newline='') as f:
    csv_writer = csv.writer(f)
    csv_writer.writerow([id, nick, content])

运行代码，得到结果

词云

import pandas as pd  # 第三方模块
import jieba
import stylecloud

# 两年权限以外
# 冻结学时
# 被动重修以外, 也可以自行选择重修
# 1. 导入数据
df = pd.read_csv('弹幕.csv')
def get_cut_words(content_):
    # 定义停用词的表
    stop_words = []
    with open('stop_words.txt', 'r', encoding='utf-8-sig') as f:
        lines = f.readlines()
        for line in lines:
            stop_words.append(line.strip())
    # 添加关键词
    my_words = ['666', '鬼吹灯']
    for i in my_words:
        jieba.add_word(i)
    word_num = jieba.lcut(content_.str.cat(sep='。'), cut_all=False)
    word_num_selected = [i for i in word_num if i not in stop_words and len(i) >= 2]
    return word_num_selected
text = get_cut_words(df['content'])

stylecloud.gen_stylecloud(
    text=' '.join(text),
    collocations=False,
    font_path=r'C:\Windows\Fonts\msyh.ttc',
    icon_name='fab fa-youtube',
    size=768,
    output_name='video.png'
)

👇问题解答 · 源码获取 · 技术交流 · 抱团学习请联系👇