有关爬虫的应用，哔哩哔哩弹幕

爬虫的一个小实例

使用工具：

jieba分词；

Wordcloud词云

requests

• 源程序

  import requests#爬虫的请求包
  import pandas as pd#pandas数据分析包
  from bs4 import BeautifulSoup
  import datetime
  import re
  import jieba
  from wordcloud import WordCloud
  from imageio import imread
  import matplotlib.pyplot as plt
  
  header = {
      'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
  }
  url = 'http://comment.bilibili.com/125511694.xml'
  response = requests.get(url=url, headers=header)#向对方服务器发送请求
  response.encoding = response.apparent_encoding#设置字符编码
  data = response.text#获取文本
  soup = BeautifulSoup(data, 'lxml')#解析
  d_list = soup.find_all('d')#获取所有的d标签
  dlst = []
  for d in d_list:
      danmu = {}
      danmu['弹幕'] = d.text#获取文本信息
      dlst.append(danmu)
  df = pd.DataFrame(dlst)#转换成二位数组，类似于execl表格
  f = open('sign.txt', 'w', encoding='utf-8')#打开文件
  for i in df['弹幕'].values:#循环所有的文本信息
      pat = re.compile(r'[1-龥]+')# 定义过滤数据的规则，所有的汉字
      filter_data = re.findall(pattern=pat, string=i)#执行过滤操作
      f.write("".join(filter_data))#写入文本
  f.close()
  

  改进版的弹幕源代码

  import requests#爬虫的请求包
  import pandas as pd#pandas数据分析包
  from bs4 import BeautifulSoup
  import datetime
  import re
  import jieba
  from wordcloud import WordCloud
  from imageio import imread
  import matplotlib.pyplot as plt
  
  f = open('sign.txt', 'r', encoding='utf-8')
  data = f.read()
  result = " ".join(jieba.lcut(data))
  f.close()
  color_mask = imread('小猪佩奇.jpg')
  wc = WordCloud(
      font_path=r'C:\Windows\Fonts\simkai.ttf',
      width=1000,
      height=800,
      mask=color_mask,
      background_color='pink'
  )
  wc.generate(result)
  wc.to_file('bili.jpg')
  plt.imshow(wc)
  plt.show()