利用python爬取网页做词云分析——2019年政府工作报告

直接上代码

#!/usr/bin/python
# -*- coding:utf-8 -*-


import matplotlib.pyplot as plt
from PIL import Image
import numpy as np
from wordcloud import WordCloud
from bs4 import BeautifulSoup
import jieba
import requests


# 获取网页中的正文文本
def extract_text(url):
    page_source = requests.get(url).content
    bs_source = BeautifulSoup