python爬虫微博关键字,Python爬虫分析微博热搜关键词的实现代码

1，使用到的第三方库

requests

BeautifulSoup 美味汤

worldcloud 词云

jieba 中文分词

matplotlib 绘图

2，代码实现部分

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