爬虫大作业

# -*- coding: utf-8 -*-
import requests
from bs4 import BeautifulSoup as bs

def getreq(url):
    header = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36'}
    html = requests.get(url,headers=header).content.decode('utf-8')
    return html
def gettext(html):
    soup = bs(html,'html.parser')
    info = soup.select('.post_item_summary')
    return info
if __name__=='__main__':
    url = "https://www.cnblogs.com/"
    html = getreq(url)
    info = gettext(html)
    for i in info:
        f = open('i.txt', 'a+', encoding='utf-8')
        f.write(i.get_text())
        f.close()

　　

import jieba
import PIL
from wordcloud import WordCloud
import matplotlib.pyplot as p
import os


info = open('i.txt','r',encoding='utf-8').read()
text = ''
text += ' '.join(jieba.lcut(info))
wc = WordCloud(font_path='C:WindowsFontsSTZHONGS.TTF',background_color='White',max_words=50)
wc.generate_from_text(text)
p.imshow(wc)
# p.imshow(wc.recolor(color_func=00ff00))
p.axis("off")
p.show()
# wc.to_file('dream.png')