B站视频弹幕分析

采集弹幕数据

用Python爬取B站视频弹幕

导入数据并进行处理

jieba分词

设置词云参数

生成词云并保存到本地

最终效果

完整代码

# ！/usr/bin/env python
# —*— coding: utf-8 —*—
# @Time:    2020/1/1 15:53
# @Author:  Martin
# @File:    Barrage_Analysis.py
# @Software:PyCharm

import pandas as pd
import jieba
import matplotlib.pyplot as plt
from random import randint
from wordcloud import WordCloud
# 弹幕数据读入
csv_data = pd.read_csv('./result/Barrage.csv')
# 数据处理
barrage_str = ""
for row in csv_data.itertuples():
    barrage_str += getattr(row, '弹幕内容')
# jieba分词
words_list = jieba.lcut(barrage_str)
words_str = "".join(words_list)


# 设置词云参数
def random_color_func(word=None, font_size=None, position=None, orientation=None, font_path=None, random_state=None):
    h = randint(120, 250)
    s = int(100.0 * 255.0 / 255.0)
    l = int(100.0 * float(randint(60, 120)) / 255.0)
    return "hsl({}, {}%, {}%)".format(h, s, l)


background_Image = plt.imread('./res/xin.jpg')
wc = WordCloud(
    background_color='white',
    mask=background_Image,
    font_path='./res/黑体.ttf',
    max_words=2000,
    max_font_size=100,
    min_font_size=5,
    color_func=random_color_func,
    random_state=50
)
# 产生词云
word_cloud = wc.generate(words_str)
# 保存到本地
word_cloud.to_file('./result/barrage.jpg')