2014-12-22

来源:互联网 发布:oracle 数据搜索引擎 编辑:程序博客网 时间:2024/06/06 03:23

1 http://www.gamefromscratch.com/

  game from scratch

2 http://www.ccs.neu.edu/home/matthias/HtDP2e/part_prologue.html

  racket lang 

3 http://www.csdn.net/article/2014-12-17/2823183

  sina post system 

4  https://gitcafe.com/gdgeek/UnityGame

   a unity3D game 

5 http://pdos.csail.mit.edu/6.828/2011/schedule.html

a mit os course

import urllibimport reimport timeimport threadingdef getHtml(url):html = urllib.urlopen(url).read().decode('utf-8')return htmldef gettopic(html):reg = r'http://www.douban.com/group/topic/\d+'topiclist = re.findall(reg,html)x = 0for topicurl in topiclist:x+=1return topicurldef download(topic_page):reg2 = r'http://img3.douban.com/view/group_topic/large/public/.+\.jpg'imglist = re.findall(reg2,topic_page)i = 1print(imglist)download_img = Nonefor imgurl in imglist:img_numlist = re.findall(r'p\d{7}',imgurl)print(img_numlist)for img_num in img_numlist:download_img = urllib.urlretrieve(imgurl,'/home/space/hua.song/mycode/girl/%s.jpg'%img_num)time.sleep(1)i+=1print(imgurl)return download_imgdef main_loop(num,num_end,pagenum):while num <= num_end:html=getHtml('http://www.douban.com/group/kaopulove/discussion?start=%d'%num)#print(html)topicurl = gettopic(html)#print(topicurl)topic_page = getHtml(topicurl)#print(topic_page)download_img = download(topic_page)num = page_num*25page_num+=1else:print('over')page_end = int(input('input eng pagenum:'))num_end = page_end*25num = 0page_num = 1threadnum = 5while num <= num_end:num_start = numnum_stop = num + page_end / threadnum * 25pagenum = num / 25 + 1t = threading.Thread(target=main_loop,args=(num_start,num_stop,pagenum,))t.start()t.join()num = num_stop#while num <= num_end:#html=getHtml('http://www.douban.com/group/kaopulove/discussion?start=%d'%num)#print(html)#topicurl = gettopic(html)#print(topicurl)#topic_page = getHtml(topicurl)#print(topic_page)#download_img = download(topic_page)#num = page_num*25#page_num+=1#else:#print('over')


0 0
原创粉丝点击