利用简书首页文章标题数据生成词云1.词云图2.推荐几个不错的词云图工具3.爬取数据，制作词云图

#安装词云
pip install wordcloud

#安装jieba分词
pip install jieba

from wordcloud import WordCloud
import matplotlib.pyplot as plt

wc = WordCloud()

text = open(r"222.txt",encoding='utf-8').read()

wc.generate(text)

plt.imshow(wc)

#导入python画图的库，词云生成库和jieba的分词库
import matplotlib.pyplot as plt
from wordcloud import WordCloud
import jieba

#读取txt格式的文本内容
text_from_file_with_apath = open('JsIndex.txt').read()

#使用jieba进行分词，并对分词的结果以空格隔开
wordlist_after_jieba = jieba.cut(text_from_file_with_apath, cut_all = True)
wl_space_split = " ".join(wordlist_after_jieba)

#对分词后的文本生成词云
my_wordcloud = WordCloud().generate(wl_space_split)

#用pyplot展示词云图。
plt.imshow(my_wordcloud)
plt.axis("off")
plt.show()

#-*- coding:utf-8 -*-

#creater 简书-_知几 2017.8.26

import urllib,urllib2,re
from lxml import etree

class CrawlJs:
    #定义函数，爬取对应的数据
    def getArticle(self,url):
        print '█████████████◣开始爬取数据'
        my_headers = {
            'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.104 Safari/537.36',
        }
        request = urllib2.Request(url,headers=my_headers)
        content = urllib2.urlopen(request).read()
        return content

    #定义函数，筛选和保存爬取到的数据
    def save(self,content):
        xml = etree.HTML(content)
        datas = xml.xpath('//div[@class="content"]/a/text()')
        print datas
        for data in datas:
            print data
            with open('JsIndex.txt','a+') as f:
                f.write(data.encode('utf-8')+ '\n')
        print '█████████████◣爬取完成！'

#定义主程序接口
if __name__ == '__main__':
    url = 'http://www.jianshu.com/'
    js = CrawlJs()
    content = js.getArticle(url)
    js.save(content)