Python爬虫分析微博热搜关键词的实现代码

import requests
import wordcloud
import jieba
from bs4 import BeautifulSoup
from matplotlib import pyplot as plt
from pylab import mpl

#设置字体
mpl.rcParams['font.sans-serif'] = ['SimHei']
mpl.rcParams['axes.unicode_minus'] = False

url = 'https://s.weibo.com/top/summary?Refer=top_hot&topnav=1&wvr=6'

try:
  #获取数据
  r = requests.get(url)
  r.raise_for_status()
  r.encoding = r.apparent_encoding
  soup = BeautifulSoup(r.text,'html.parser')
  data = soup.find_all('a')
  d_list = []
  for item in data:
    d_list.append(item.text)
  words = d_list[4:-11:]
  #中文分词
  result = list(jieba.cut(words[0]))
  for word in words[1::]:
    result.extend(jieba.cut(word))
  redata = []
  for it in result:
    if len(it) <= 1:
      continue
    else:
      redata.append(it)
  result_str = ' '.join(redata)
  #输出词云图
  font = r'C:\Windows\Fonts\simhei.ttf'
  w = wordcloud.WordCloud(font_path=font,width=600,height=400)
  w.generate(result_str)
  w.to_file('微博热搜关键词词云.png')
  key = list(set(redata))
  x,y = [],[]
  #筛选数据
  for st in key:
    count = redata.count(st)
    if count <= 1:
      continue
    else:
      x.append(st)
      y.append(count)
  x.sort()
  y.sort()
  #绘制结果图
  plt.plot(x,y)
  plt.show()
except Exception as e:
  print(e)