#coding:utf-8
#Author:LSA
#Description:wordcloud for wooyun
#Date:20170904

import urllib
import urllib2
import re
import threading
import Queue

q0 = Queue.Queue()

threads = 20

threadList = []

def gettitle():
 while not q0.empty():

 i = q0.get()
 url = 'http://wy.hxsec.com/bugs.php?page=' + str(i)
 html = urllib.urlopen(url).read()
 reg = re.compile(r'<li style="width:60%;height:25px;background-color:#FFFFFF;float:left" ><a href=".*?" rel="external nofollow" >(.*?)</a>')
 titleList = re.findall(reg,html)
 fwy = open("wooyunBugTitle.txt","a")
 for title in titleList:
 fwy.write(title+'\n')
 fwy.flush()
 fwy.close()
 print 'Page ' + str(i) + ' over!'

def main():
 for page in range(1,2962):
 q0.put(page)
 for thread in range(threads):
 t = threading.Thread(target=gettitle)
 t.start()
 threadList.append(t)
 for th in threadList:
 th.join()

 print '***********************All pages over!**********************'

if __name__ == '__main__':
 main()

# coding: utf-8

import jieba
from wordcloud import WordCloud
import matplotlib.pyplot as plt

data = open("wooyunBugTitle.txt","r").read()
cutData = jieba.cut(data, cut_all=True)
word = " ".join(cutData)

cloud = WordCloud(
 #設(shè)置字體，不指定可能會(huì)出現(xiàn)中文亂碼
 font_path="msyh.ttf",
 #font_path=path.join(e,'xxx.ttc'),
 #設(shè)置背景色
 background_color='white',
 #詞云形狀
 #mask=color_mask,
 #允許最大詞匯
 max_words=2000,
 #最大號(hào)字體
 max_font_size=40
 )

wc = cloud.generate(word)
wc.to_file("wooyunwordcloud.jpg") 
plt.imshow(wc)
plt.axis("off")
plt.show()