├── .idea ├── .name ├── Douban.iml ├── encodings.xml ├── misc.xml ├── modules.xml ├── scopes │ └── scope_settings.xml ├── vcs.xml └── workspace.xml ├── README.md ├── Win_Client.7z ├── Win_Client ├── dou2_win.exe └── 必读.txt ├── dou2.py ├── dou2_win.py ├── html ├── air.png ├── center.css ├── index.html └── shadow_light.png ├── stup.py └── test.py /.idea/.name: -------------------------------------------------------------------------------- 1 | Douban -------------------------------------------------------------------------------- /.idea/Douban.iml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | -------------------------------------------------------------------------------- /.idea/encodings.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | -------------------------------------------------------------------------------- /.idea/misc.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | -------------------------------------------------------------------------------- /.idea/modules.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | -------------------------------------------------------------------------------- /.idea/scopes/scope_settings.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 5 | -------------------------------------------------------------------------------- /.idea/vcs.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | -------------------------------------------------------------------------------- /.idea/workspace.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 16 | 17 | 18 | 20 | 21 | 22 | 23 | 24 | 25 | 26 | 27 | 28 | 29 | 30 | 31 | 32 | 33 | 34 | 35 | 36 | 37 | 38 | 39 | 40 | 41 | 42 | 43 | 44 | 45 | 46 | 47 | 48 | 49 | 50 | 51 | 52 | 53 | 54 | 55 | 56 | 57 | 58 | 59 | 60 | 61 | 62 | 63 | 64 | 65 | 66 | 67 | 68 | 69 | 70 | 71 | 72 | 73 | 74 | 75 | 76 | 77 | 78 | 79 | 80 | 81 | 82 | 83 | 84 | 85 | 86 | 87 | 88 | 89 | 90 | 91 | 92 | 93 | 94 | 96 | 97 | 113 | 114 | 115 | 120 | 121 | 122 | 123 | 124 | 125 | 126 | 127 | 128 | 129 | 130 | 131 | 133 | 134 | 135 | 136 | 137 | 138 | 139 | 140 | 141 | 142 | 143 | 144 | 145 | 146 | 147 | 148 | 149 | 150 | 153 | 154 | 155 | 156 | 157 | 158 | 159 | 160 | 161 | 162 | 163 | 164 | 167 | 168 | 169 | 170 | 189 | 190 | 209 | 210 | 227 | 228 | 247 | 248 | 273 | 274 | 297 | 298 | 318 | 319 | 334 | 335 | 356 | 357 | 375 | 376 | 394 | 395 | 396 | 397 | 398 | 399 | 400 | 401 | 402 | 403 | 404 | 405 | 406 | 407 | 408 | 409 | 410 | 411 | 412 | 413 | 414 | 415 | 1405394782054 416 | 1405394782054 417 | 418 | 419 | 1405401436680 420 | 1405401436680 421 | 422 | 423 | 1405420255362 424 | 1405420255362 425 | 426 | 427 | 1405432782746 428 | 1405432782746 429 | 430 | 431 | 1405452937498 432 | 1405452937498 433 | 434 | 435 | 1405453700235 436 | 1405453700235 437 | 438 | 439 | 1405453751309 440 | 1405453751309 441 | 442 | 443 | 1405458742066 444 | 1405458742066 445 | 446 | 447 | 1405458937852 448 | 1405458937852 449 | 450 | 451 | 1405460428859 452 | 1405460428859 453 | 454 | 455 | 1405500594569 456 | 1405500594569 457 | 458 | 459 | 1405503584832 460 | 1405503584832 461 | 462 | 463 | 1405504215762 464 | 1405504215762 465 | 466 | 467 | 1405514518777 468 | 1405514518777 469 | 470 | 471 | 1405514560387 472 | 1405514560387 473 | 474 | 475 | 1405514589111 476 | 1405514589111 477 | 478 | 479 | 1405587097350 480 | 1405587097350 481 | 482 | 483 | 1405587687903 484 | 1405587687903 485 | 486 | 489 | 490 | 491 | 492 | 493 | 494 | 495 | 496 | 497 | 498 | 499 | 500 | 501 | 502 | 503 | 504 | 505 | 506 | 507 | 508 | 509 | 510 | 511 | 512 | 513 | 514 | 515 | 516 | 517 | 518 | 519 | 520 | 521 | 522 | 523 | 524 | 525 | 526 | 527 | 528 | 529 | 530 | 531 | 532 | 533 | 534 | 536 | 537 | 540 | 543 | 544 | 545 | 547 | 548 | 551 | 552 | 553 | 554 | 555 | 556 | 557 | 558 | 559 | 560 | 561 | 562 | 563 | 564 | 565 | 567 | 568 | 569 | 570 | 571 | 572 | 574 | 575 | 576 | 577 | 578 | 579 | 580 | 581 | 582 | 583 | 584 | 585 | 586 | 587 | 588 | 589 | 590 | 591 | 592 | 593 | 594 | 595 | 596 | 597 | 598 | 599 | 600 | 601 | 602 | 603 | 604 | 605 | 606 | 607 | 608 | 609 | 610 | 611 | 612 | 613 | 614 | 615 | 616 | 617 | 618 | 619 | 620 | 621 | 622 | 623 | 624 | 625 | 626 | 627 | 628 | 629 | 630 | 631 | 632 | 633 | 634 | 635 | 636 | 637 | 638 | 639 | 640 | 641 | 642 | 643 | 644 | 645 | 646 | 647 | 648 | 649 | 650 | 651 | 652 | 653 | 654 | 655 | 656 | 657 | 658 | 659 | 660 | 661 | 662 | 663 | 664 | 665 | 666 | 667 | 668 | 669 | 670 | 671 | 672 | 673 | 674 | 675 | 676 | 677 | 678 | 679 | 680 | 681 | 682 | 683 | 684 | 685 | 686 | 687 | 688 | 689 | 690 | 691 | 692 | 693 | 694 | 695 | 696 | 697 | 698 | 699 | 700 | 701 | 702 | 703 | 704 | 705 | 706 | 707 | 708 | 709 | 710 | 711 | 712 | 713 | 714 | 715 | 716 | 717 | 718 | 719 | 720 | 721 | 722 | 723 | 724 | 725 | 726 | 727 | 728 | 729 | 730 | 731 | 732 | 733 | 734 | 735 | 736 | 737 | 738 | 739 | 740 | 741 | 742 | 743 | 744 | 745 | 746 | 747 | 748 | 749 | 750 | 751 | 752 | 753 | 754 | 755 | 756 | 757 | 758 | 759 | 760 | 761 | 762 | 763 | 764 | 765 | 766 | 767 | 768 | 769 | 770 | 771 | 772 | 773 | 774 | 775 | 776 | 777 | 778 | 779 | 780 | 781 | 782 | 783 | 784 | 785 | 786 | 787 | 788 | 789 | 790 | 791 | 792 | 793 | 794 | 795 | 796 | 797 | 798 | 799 | 800 | 801 | 802 | 803 | 804 | 805 | 806 | 807 | 808 | 809 | 810 | 811 | 812 | 813 | 814 | 815 | 816 | 817 | 818 | 819 | 820 | 821 | 822 | 823 | 824 | 825 | 826 | 827 | 828 | 829 | 830 | 831 | 832 | 833 | 834 | 835 | 836 | 837 | 838 | 839 | 840 | 841 | 842 | 843 | 844 | 845 | 846 | 847 | 848 | 849 | 850 | 851 | 852 | 853 | 854 | 855 | 856 | 857 | 858 | 859 | 860 | 861 | 862 | 863 | 864 | 865 | 866 | 867 | 868 | 869 | 870 | 871 | 872 | 873 | 874 | 875 | 876 | 877 | 878 | 879 | 880 | 881 | 882 | 883 | 884 | 885 | 886 | 887 | 888 | 889 | 890 | 891 | 892 | 893 | 894 | 895 | 896 | 897 | 898 | 899 | 900 | 901 | 902 | 903 | 904 | 905 | 906 | 907 | 908 | 909 | 910 | 911 | 912 | 913 | 914 | 915 | 916 | 917 | 918 | 919 | 920 | 921 | 922 | 923 | 924 | 925 | 926 | 927 | 928 | 929 | 930 | 931 | 932 | 933 | 934 | 935 | 936 | 937 | 938 | 939 | 940 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | ###豆瓣小组图片采集程序 2 | #####By 肾虚公子 3 | 4 | 官网: http://Douban.miaowu.asia 5 | 6 | 主程序:dou2.py 7 | 8 | 9 | 10 | Mac/Liunx 运行程序(python dou2.py)即可。 11 | 12 | Windows用户请下载压缩包: [下载](https://raw.githubusercontent.com/ShenXuGongZi/DouBanGroupPic/master/Win_Client.7z) 13 | 14 | 15 | #### 程序基本功能 16 | * 用户可以自由选择用户组下载图片支持豆瓣所有小组 17 | * 本程序自动采集代理 18 | * 采集代理后随机选择 19 | * 自动下载图片并保存 20 | 21 | 22 | 获取用户组ID方法 23 | http://www.douban.com/group/264964/ #只需要输入人group/后面的字符 不包括斜杠 24 | 25 | ##### 2015-6-3 更新 26 | * 无需用户手动创建文件夹 27 | * 更新可用性去掉代理采集 28 | * 优化Windows客户端大小以及文件数量 29 | 30 | ##### 2014-7-17 更新 31 | * 修改程序Bug 32 | * 增加错误输出 33 | * 加快程序执行效率 34 | * 尝试启用多线程失败! 35 | 36 | ##### 2014-7-16 更新 37 | * 用户可以自由选择用户组下载图片支持豆瓣所有小组 38 | * 增加默认功能 39 | * 模拟UA 40 | * 更换代理源 41 | * Win版支持 42 | * 优化程序 43 | * 美化程序 -------------------------------------------------------------------------------- /Win_Client.7z: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenXuGongZi/DouBanGroupPic/4839aef33e06ababbbc201589ac41a857b588e93/Win_Client.7z -------------------------------------------------------------------------------- /Win_Client/dou2_win.exe: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenXuGongZi/DouBanGroupPic/4839aef33e06ababbbc201589ac41a857b588e93/Win_Client/dou2_win.exe -------------------------------------------------------------------------------- /Win_Client/必读.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenXuGongZi/DouBanGroupPic/4839aef33e06ababbbc201589ac41a857b588e93/Win_Client/必读.txt -------------------------------------------------------------------------------- /dou2.py: -------------------------------------------------------------------------------- 1 | #-*- coding: utf-8 -* 2 | import urllib 3 | import urllib2 4 | import re 5 | import time 6 | import sys 7 | import os 8 | import random 9 | 10 | print '#'*50 11 | print '#'*2 + '\t\t\t\t豆瓣小组采集器\t\t\t\t\t'+'#'*2 12 | print '#'*50 13 | 14 | import os 15 | type = sys.getfilesystemencoding() 16 | 17 | mkmulu = os.path.exists('Doubanimg') 18 | 19 | if not mkmulu: 20 | print '#'*50 21 | print '目录创建成功!图片将下载到DOubanimg目录'.decode('UTF-8').encode('GBK') 22 | print '#'*50 23 | os.mkdir('Doubanimg') 24 | # return True 25 | else: 26 | print '#'*50 27 | print '目录存在,图片下载到Doubanimg目录'.decode('UTF-8').encode('GBK') 28 | print '#'*50 29 | # return False 30 | 31 | # print '*'*20+'开始采集代理'+'*'*20 32 | # #采集代理信息 33 | # f = open('proxy_list.txt','w') 34 | # exp1 = re.compile("(?isu)]*>(.*?)") 35 | # exp2 = re.compile("(?isu)]*>(.*?)") 36 | # #加入UA模拟浏览器 37 | # proxy_ua = {'User-Agent':'Mozilla/5.0 (X11; Linux i686) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36'} 38 | # proxyHtml = urllib2.Request(url="http://www.site-digger.com/html/articles/20110516/proxieslist.html",headers=proxy_ua) 39 | # try: #检查代理是否写入成功 40 | # proxySocket = urllib2.urlopen(proxyHtml) 41 | # htmlSource = proxySocket.read() 42 | # #print htmlSource 43 | # except Exception: #如果错误 44 | # print '-'*50 45 | # print '代理程序采集出错！请确认您的网络正常!' 46 | # print '-'*50 47 | # raw_input('按回车结束程序:') 48 | # else: #成功继续执行 49 | # for row in exp1.findall(htmlSource): 50 | # for col in exp2.findall(row)[:1]: 51 | # #写入代理信息 52 | # f.write(col+'\n') 53 | # #print col 54 | # f.close() 55 | 56 | 57 | #针对http://cn-proxy.com/网站所写的一些采集后文件内操作 58 | #删除指定字符 59 | # with open('proxy_list.txt', 'r') as f: 60 | # with open('proxy_list.txt.new', 'w') as g: 61 | # for line in f.readlines(): 62 | # if '服务器地址' not in line: 63 | # g.write(line) 64 | # shutil.move('proxy_list.txt.new', 'proxy_list.txt') 65 | # #删除指定字符 66 | # with open('proxy_list.txt', 'r') as f: 67 | # with open('proxy_list.txt.new', 'w') as g: 68 | # for line in f.readlines(): 69 | # if '端口' not in line: 70 | # g.write(line) 71 | # shutil.move('proxy_list.txt.new', 'proxy_list.txt') 72 | # 73 | # #读取文件合并行 74 | # file = open("proxy_list.txt",'r') 75 | # lines = file.readlines() #列出文件所有行 76 | # newlines = [] #新行 77 | # j = 1 78 | # for i in range(len(lines)): 79 | # if(j!=len(lines)-2): 80 | # string = lines[j].replace('\n','')+':'+lines[j+1].replace('\n','') 81 | # newlines.append(string) 82 | # j=j+2 83 | 84 | #print(newlines) 85 | 86 | # open("proxy_list.txt","w").write('%s' % '\n'.join(newlines)) 87 | # file.close() 88 | 89 | # print '*'*20+'代理采集完成'+'*'*20 90 | ##########################################################################################3 91 | ### 代理模块(全局代理) 92 | print '#'*50 93 | print '#'*2 + '\t\t\t\t肾虚公子 亲情制作\t\t\t\t\t'+'#'*2 94 | print '#'*2 + '\t\t\t\t主页: Douban.miaowu.asia\t\t\t'+'#'*2 95 | print '#'*50 96 | print '说明:本程序可以采集豆瓣任何小组的图片.' 97 | print '说明:采集的图片在文件夹Doubanimg内.' 98 | # print '注意:代理没有验证，如果不成功请重新运行.' 99 | print '#'*50 100 | 101 | #读取代理文件的每一行 102 | # f0=open('proxy_list.txt','r') 103 | # dat0=f0.readlines() 104 | # f0.close() 105 | # #随即选取代理文件的一行 106 | # proxy_SJ = random.choice(dat0) 107 | # #代理 108 | # #proxy_input = raw_input('请输入采集代理服务器:') 109 | # proxy_handler = urllib2.ProxyHandler({'http':'%s'%proxy_SJ}) 110 | # opener = urllib2.build_opener(proxy_handler) 111 | # urllib2.install_opener(opener) 112 | 113 | #采集本地路径全局变量 114 | #img_LuJ = raw_input("图片下载路径:".decode('utf-8')) 115 | #img_LuJ2 = os.path.abspath(img_LuJ) 116 | print '请输入小组代码,默认采集豆瓣害羞组[ID=haixiuzu]' 117 | print '小组ID就是(http://www.douban.com/group/这里的字符/)' 118 | Douban_group = raw_input('请输入小组ID(默认按回车继续):')or 'haixiuzu' 119 | Douban_group_url = 'http://www.douban.com/group/' 120 | 121 | #模块化输出 122 | #获取帖子单页html 123 | def gethtml2(url2): 124 | Douban_ua = {'User-Agent':'Mozilla/5.0 (X11; Linux i686) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36'} 125 | Douban_Html = urllib2.Request(url=(url2),headers=Douban_ua) 126 | Douban_Socket = urllib2.urlopen(Douban_Html) 127 | html2 = Douban_Socket.read().decode('utf-8') 128 | return html2 129 | 130 | #打开帖子列表 131 | def gettoimg(html2): 132 | #添加正则 匹配url路径数字 d+代表获取0-9无限循环\转义符号 133 | reg2 = r'http://www.douban.com/group/topic/\d+' 134 | toplist = re.findall(reg2,html2) 135 | x = 0 136 | #限制下载图片数量 137 | #输出topicurl 每次输出一个 的循环 138 | for topicurl in toplist: 139 | x+=1 140 | return topicurl 141 | 142 | #下载图片到本地 143 | def download(topic_page): 144 | #获取贴内图片 正则 ".+\" .匹配任意字符 + 匹配前一个字符或无限次 \ 转移符号 也就是 匹配所有字符 145 | reg3 = r'http://img3.douban.com/view/group_topic/large/public/.+\.jpg' 146 | imglist = re.findall(reg3,topic_page) 147 | i = 1 148 | download_img = None 149 | for imgurl in imglist: 150 | #取图片id为文件名 151 | img_numlist = re.findall(r'p\d{7}',imgurl) 152 | for img_num in img_numlist: 153 | #获取用户输入路径 154 | #download_img = urllib.urlretrieve(imgurl,img_LuJ2 + '/%s.jpg'%img_num) 155 | #固定程序路径 156 | download_img = urllib.urlretrieve(imgurl,'Doubanimg/%s.jpg'%img_num) 157 | time.sleep(0.5) 158 | i+=1 159 | print (imgurl) 160 | return download_img 161 | 162 | 163 | print '-'*50 164 | print '请输入采集帖子数,默认采集10个帖子' 165 | page_end = int(raw_input('输入数字即可(默认按回车继续):')or 10) 166 | print '-'*50 167 | print '正在采集图片中，程序可能用较长时间,此时您可以干点别的，比如喝杯咖啡？' 168 | print '-'*50 169 | 170 | num_end = page_end*25 171 | num = 0 172 | page_num = 1 173 | try: #判断输出错误 174 | while num<=num_end: 175 | #获取帖子列表,从0页开始 176 | html2 = gethtml2(Douban_group_url+Douban_group+"/discussion?start=%d"%num) 177 | #抽取下载图片 178 | topicurl = gettoimg(html2) 179 | topic_page = gethtml2(topicurl) 180 | download_img=download(topic_page) 181 | num = page_num*25 182 | page_num+=1 183 | #print('程序采集完成') 184 | except Exception: 185 | print '错误：图片下载失败！请检查小组名称是否正确!!请重新运行本程序' 186 | print '-'*50 187 | raw_input('按回车结束程序:') 188 | else: 189 | print '#'*20 + '下载完成' + '#'*20 190 | print '程序采集已经结束感谢您的使用!'+'网站:http://Douban.miaowu.asia' 191 | print '#'*20 + '程序结束' + '#'*20 192 | JS = raw_input('按回车结束程序:') 193 | print JS 194 | 195 | -------------------------------------------------------------------------------- /dou2_win.py: -------------------------------------------------------------------------------- 1 | #-*- coding: utf-8 -* 2 | # coding=cp936 3 | import urllib 4 | import urllib2 5 | import re 6 | import time 7 | import random 8 | import sys 9 | import os 10 | type = sys.getfilesystemencoding() 11 | 12 | print '#'*50 13 | print '#'*2 + '\t\t\t\t豆瓣小组采集器\t\t\t\t\t'.decode('UTF-8').encode('GBK')+'#'*2 14 | print '#'*50 15 | 16 | mkmulu = os.path.exists('Doubanimg') 17 | 18 | if not mkmulu: 19 | print '#'*50 20 | print '目录创建成功!图片将下载到Doubanimg目录'.decode('UTF-8').encode('GBK') 21 | print '#'*50 22 | os.mkdir('Doubanimg') 23 | # return True 24 | else: 25 | print '#'*50 26 | print '目录存在,图片下载到Doubanimg目录'.decode('UTF-8').encode('GBK') 27 | print '#'*50 28 | # return False 29 | 30 | print '#'*50 31 | print '#'*2 + '\t肾虚公子 亲情制作'.decode('UTF-8').encode('GBK') 32 | print '#'*2 + '\t主页: Douban.miaowu.asia'.decode('UTF-8').encode('GBK') 33 | print '#'*50 34 | print '说明:本程序可以采集豆瓣任何小组的图片.'.decode('UTF-8').encode('GBK') 35 | print '说明:采集的图片在文件夹Doubanimg内.'.decode('UTF-8').encode('GBK') 36 | print '注意:代理没有验证，如果不成功请重新运行.'.decode('UTF-8').encode('GBK') 37 | print '#'*50 38 | 39 | 40 | print '请输入小组代码,默认采集豆瓣害羞组[ID=haixiuzu]'.decode('UTF-8').encode('GBK') 41 | print '小组ID就是(http://www.douban.com/group/这里的字符/)'.decode('UTF-8').encode('GBK') 42 | Douban_group = raw_input('请输入小组ID(默认按回车继续):'.decode('UTF-8').encode('GBK') )or 'haixiuzu' 43 | Douban_group_url = 'http://www.douban.com/group/' 44 | 45 | def gethtml2(url2): 46 | Douban_ua = {'User-Agent':'Mozilla/5.0 (X11; Linux i686) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36'} 47 | Douban_Html = urllib2.Request(url=(url2),headers=Douban_ua) 48 | Douban_Socket = urllib2.urlopen(Douban_Html) 49 | html2 = Douban_Socket.read().decode('utf-8') 50 | return html2 51 | 52 | def gettoimg(html2): 53 | reg2 = r'http://www.douban.com/group/topic/\d+' 54 | toplist = re.findall(reg2,html2) 55 | x = 0 56 | for topicurl in toplist: 57 | x+=1 58 | return topicurl 59 | 60 | def download(topic_page): 61 | reg3 = r'http://img3.douban.com/view/group_topic/large/public/.+\.jpg' 62 | imglist = re.findall(reg3,topic_page) 63 | i = 1 64 | download_img = None 65 | for imgurl in imglist: 66 | img_numlist = re.findall(r'p\d{7}',imgurl) 67 | for img_num in img_numlist: 68 | download_img = urllib.urlretrieve(imgurl,'Doubanimg/%s.jpg'%img_num) 69 | time.sleep(0.5) 70 | i+=1 71 | print (imgurl) 72 | return download_img 73 | 74 | 75 | print '-'*50 76 | print '请输入采集帖子数,默认采集10个帖子'.decode('UTF-8').encode('GBK') 77 | page_end = int(raw_input('输入数字即可(默认按回车继续):'.decode('UTF-8').encode('GBK'))or 10) 78 | print '-'*50 79 | print '正在采集图片中，程序可能用较长时间,此时您可以干点别的，比如喝杯咖啡？'.decode('UTF-8').encode('GBK') 80 | print '-'*50 81 | 82 | num_end = page_end*25 83 | num = 0 84 | page_num = 1 85 | try: 86 | while num<=num_end: 87 | html2 = gethtml2(Douban_group_url+Douban_group+"/discussion?start=%d"%num) 88 | topicurl = gettoimg(html2) 89 | topic_page = gethtml2(topicurl) 90 | download_img=download(topic_page) 91 | num = page_num*25 92 | page_num+=1 93 | except Exception: 94 | print '错误：图片下载失败！请检查小组名称是否正确!!请重新运行本程序'.decode('UTF-8').encode('GBK') 95 | print '-'*50 96 | raw_input('按回车结束程序:'.decode('UTF-8').encode('GBK') ) 97 | else: 98 | print '#'*20 + '下载完成'.decode('UTF-8').encode('GBK') + '#'*20 99 | print '程序采集已经结束感谢您的使用!'+'网站:http://Douban.miaowu.asia'.decode('UTF-8').encode('GBK') 100 | print '#'*20 + '程序结束'.decode('UTF-8').encode('GBK') + '#'*20 101 | JS = raw_input('按回车结束程序:'.decode('UTF-8').encode('GBK') ) 102 | print JS -------------------------------------------------------------------------------- /html/air.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenXuGongZi/DouBanGroupPic/4839aef33e06ababbbc201589ac41a857b588e93/html/air.png -------------------------------------------------------------------------------- /html/center.css: -------------------------------------------------------------------------------- 1 | /* Space out content a bit */ 2 | body { 3 | padding-top: 20px; 4 | padding-bottom: 20px; 5 | /* background-color: #333; */ 6 | background-image: url("shadow_light.png"), url("air.png"); background-repeat: repeat-x, repeat; }; 7 | } 8 | 9 | /* Everything but the jumbotron gets side spacing for mobile first views */ 10 | .header, 11 | .marketing, 12 | .footer { 13 | padding-right: 15px; 14 | padding-left: 15px; 15 | } 16 | 17 | /* Custom page header */ 18 | .header { 19 | border-bottom: 1px solid #e5e5e5; 20 | } 21 | /* Make the masthead heading the same height as the navigation */ 22 | .header h3 { 23 | padding-bottom: 19px; 24 | margin-top: 0; 25 | margin-bottom: 0; 26 | line-height: 40px; 27 | } 28 | 29 | /* Custom page footer */ 30 | .footer { 31 | padding-top: 19px; 32 | color: #777; 33 | border-top: 1px solid #e5e5e5; 34 | } 35 | 36 | /* Customize container */ 37 | @media (min-width: 768px) { 38 | .container { 39 | max-width: 730px; 40 | 41 | background-color: #FCFCFC; 42 | padding-top: 20px; 43 | } 44 | } 45 | .container-narrow > hr { 46 | margin: 30px 0; 47 | } 48 | 49 | /* Main marketing message and sign up button */ 50 | .jumbotron { 51 | text-align: center; 52 | border-bottom: 1px solid #e5e5e5; 53 | } 54 | .jumbotron .btn { 55 | padding: 14px 24px; 56 | font-size: 21px; 57 | } 58 | 59 | /* Supporting marketing content */ 60 | .marketing { 61 | margin: 40px 0; 62 | } 63 | .marketing p + h4 { 64 | margin-top: 28px; 65 | } 66 | 67 | /* Responsive: Portrait tablets and up */ 68 | @media screen and (min-width: 768px) { 69 | /* Remove the padding we set earlier */ 70 | .header, 71 | .marketing, 72 | .footer { 73 | padding-right: 0; 74 | padding-left: 0; 75 | } 76 | /* Space out the masthead */ 77 | .header { 78 | margin-bottom: 30px; 79 | } 80 | /* Remove the bottom border on the jumbotron for visual effect */ 81 | .jumbotron { 82 | border-bottom: 0; 83 | } 84 | } -------------------------------------------------------------------------------- /html/index.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 豆瓣小组图片采集器 15 | 16 | 17 | 18 | 19 | 20 | 21 | 22 |
23 |
24 | 30 |

豆瓣小组图片采集器

31 |
32 | 33 |
34 |

豆瓣小组图片采集器

35 |

用户可以自由选择用户组下载图片支持豆瓣所有小组.

36 |

37 | GitHub主页 38 |

39 |
40 |
41 |
42 |
43 |

Mac/Linux用户

44 |

请下载dou2.py程序运行 并且在同文件夹下创建Doubanimg文件

45 |

具体流程如下

46 | 
mkdir Doubanimg
47 | 
wget http://douban.miaowu.asia/dou2.py&&python dou2.py
48 |
49 |

50 |

Windows用户

51 |

Windows用户直接下载文件运行即可.

52 | 下载Windows版本 53 |

54 |
55 |

演示

56 | 57 |
58 |
59 | 60 |
61 |

© Company 肾虚公子 2014

62 |
63 | 64 |
65 | 66 | 67 | 69 | 70 | 71 | 74 | -------------------------------------------------------------------------------- /html/shadow_light.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShenXuGongZi/DouBanGroupPic/4839aef33e06ababbbc201589ac41a857b588e93/html/shadow_light.png -------------------------------------------------------------------------------- /stup.py: -------------------------------------------------------------------------------- 1 | from distutils.core import setup 2 | 3 | import py2exe 4 | 5 | 6 | 7 | includes = ["encodings", "encodings.*"] 8 | 9 | options = {"py2exe": 10 | 11 | { "compressed": 1, 12 | 13 | "optimize": 2, 14 | 15 | "includes": includes, 16 | 17 | "bundle_files": 1 18 | 19 | } 20 | 21 | } 22 | 23 | setup( 24 | 25 | version = "3.0.0", 26 | 27 | description = "Data Convert Tools(For MM-Bukepa.org only)", 28 | 29 | name = "Data Convert Tools", 30 | 31 | options = options, 32 | 33 | zipfile=None, 34 | 35 | console = ["dou2_win.py"], 36 | ) -------------------------------------------------------------------------------- /test.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | from threading import Thread 3 | def run_thread(n): 4 | for i in range(n): 5 | print i 6 | 7 | t1 = Thread(target=run_thread,args=(500000,))#指定目标函数，传入参数，这里参数也是元组 8 | t1.start() #启动线程 --------------------------------------------------------------------------------