Python词云

import requests
from bs4 import BeautifulSoup

url='https:'
rep = requests.get(url=url)
rep.encoding = 'utf-8'
print(rep.status_code)
html=rep.text

htmllist=BeautifulSoup(html,'html.parser')
soup=htmllist.select('div.con>p')

with open('文件.txt','w+',encoding='utf-8') as fw:
    for t in soup:
        text = t.text + '\n'
        fw.write(text)

import jieba
text = ''
with open('文件.txt','r',encoding='utf-8') as fo:
    text = fo.read()

list = jieba.lcut(text)

counts = {}

for word in list:
    if len(word) == 1:
        continue
    counts[word] = counts.get(word,0) + 1


items = counts.items()
counts["请党放心"]=29
items = sorted(items,key=lambda x:x[1],reverse=True)
print(items)

for i in range(10):
    print("关键字:{},出现频次:{}".format(items[i][0],items[i][1]))

import wordcloud
import imageio
mask = imageio.imread('map.jpg')
font = 'D:/AAAAAA我的桌面/华文彩云.TTF'
wc = wordcloud.WordCloud(font_path=font,width=1600,height=900,mask=mask,background_color='white')

s = ''

for t in range(len(items)):
    if i == 28:
        s = s + '轻钢放心 '
    else:
        s = s + str(items[t][0]) + ' '

print(s)

wc.generate(s)
wc.to_file('li.jpg')