Python 新浪实时新闻词云

'''
Python 新浪实时新闻词云 by 郑瑞国
'''
from wordcloud import WordCloud
import re
import urllib.request
import time

def get_wordcloud(text):    
    image=WordCloud(font_path="c:/Windows/Fonts/simfang.ttf",width=1200,height=600,max_words=50).generate(text).to_image()
    image.show()
 
def get_wordcloud_fromfile():
    newtext=[]
    text=[]
    #try:
    with open(r'd:\test.txt','rt') as f:
        text = f.readlines()
    #except:
        #pass
    for i in range(len(text),0,-1):
        if len(text)-i<8:
            newtext.append(text[i-1])
    image=WordCloud(font_path="c:/Windows/Fonts/simfang.ttf",width=1200,height=600,max_words=50).generate(str(newtext)).to_image()
    image.show()

def open_url(url):
    return urllib.request.urlopen(url).read().decode("utf-8","ignore")
 
def find_url(url):
    return re.findall('href="(http://.*?)"',open_url(url))
 
def find_text(url):
    return re.findall('<a.*>(.*?)</a>',open_url(url))
 
def save_text(text):
    t=[]
    try:
        with open(r'd:\test.txt','r') as pre_f:
            t = pre_f.readlines()
    except:
        pass
    with open(r'd:\test.txt','a') as f:
        for i in range(0,len(text)):
            if len(text[i])>8:
                if text[i]+'\n' not in t:                     
                    try:
                        f.write(text[i]+"\n")
                        print(text[i])
                    except:
                        pass
    #print('*',end=' ')
 
if __name__ == "__main__":
    url = 'http://news.sina.com.cn/'
    url_list = find_url(url)
    newtext=[]
    while True:
        for c_url in url_list:
            #urllib.request.urlretrieve(c_url,filename=r'd:\tmp\abc.html')
            text = find_text(c_url)
            save_text(text)
            newtext.append(text)
            #get_wordcloud_fromfile()
            try:
                #get_wordcloud(str(newtext))
                get_wordcloud_fromfile()
                time.sleep(20)
            except:
                pass