Python爬虫自动化爬取b站实时弹幕实例方法

import jieba # 分词
from wordcloud import WordCloud # 词云
from PIL import Image # 图片处理
import numpy as np # 图片处理
import matplotlib.pyplot as plt # 画图

# 读取停用词库,注意编码应为‘utf8'
f = open('小夜斗的停用词表.txt', encoding='utf8')
stopwords = f.read().split('\n')
print(stopwords) # 打印停用词
f.close() # 关闭停用词文件

with open("冰冰vlog2.txt", "r", encoding='utf8') as fp:
text = fp.read()

segs = jieba.cut(text) # 进行jieba分词
mytext_list = [] # 构建一个容纳过滤掉停用词的冰冰弹幕数据文件
# 文本清洗
for seg in segs: # 循环遍历每一个分词文本
  # 如果该词不属于停用词表 并且非空 长度不为1
  if seg not in stopwords and seg != "" and len(seg) != 1:
    # 将该词语添加到mytext_list列表中
    mytext_list.append(seg.replace(" ", ""))
print(mytext_list) # 打印过滤后的冰冰弹幕数据

cloud_text = ",".join(mytext_list) # 连接列表里面的词语
print(cloud_text)