def get_urls(self):while(self.page<4):#得到当前页面的urlurl = self.cur_url.format(page = self.page*25)#获取当前页面所有内容text = self.Downloader.download(url)#将下载页面进行解析得到需要的urlurls = self.Parser.get_urls(text)#将当前获取的url加入url管理器中
            self.URL_manager.add_urls(urls)#继续下一页的url添加self.page += 1

def craw(self):print("开始搜集导演信息")datas = list()titles = list()#data = list()num = 0while self.URL_manager.has_new_url():try:#获取一个电影详情页面的urlurl = self.URL_manager.get_url()#将这个页面下载text = self.Downloader.download(url)#对这个页面进行解析，获得需要的内容data= self.Parser.get_datas(text)for item in data:datas.append(item)#titles.append(title)print("top %d:%s"%(num,item))num += 1except:print("craw failed!")#将数据存入本地
        self.Outputer.save(datas)print("done")

import wordcloud
from PIL import Image
import numpy as np
import jieba
import jieba.analyse
from matplotlib import pyplot as pltclass WC_dires(object):"""docstring for WC_dirs"""def __init__(self):self.path = r"F:/Python_Program/douban/director/spider/directors.txt"def Read_text(self):lyric = ''try:f = open(self.path,'r')lyric = f.read()return lyricexcept:print("open file error!")return Nonefinally:f.close()def Analyse(self,text):results = jieba.analyse.extract_tags(text,topK = 100)return resultsdef Draw(self,results):image = np.array(Image.open(r'F:/Python_Program/douban/director/dires.png'))wc = wordcloud.WordCloud(background_color = 'white',max_words = 100,mask = image,stopwords = wordcloud.STOPWORDS,font_path = 'C:\Windows\Fonts\STZHONGS.TTF')cut_results = " ".join(results)wc.generate(cut_results)plt.figure()plt.imshow(wc)plt.axis("off")plt.show()def main():we = WC_dires()text = we.Read_text()data = we.Analyse(text)#for item in data:#    print(item)
    we.Draw(data)if __name__ == "__main__":main()