1 import re, os, time
 2 import urllib.request
 3
 4 def getHtml(url):#取得网页的html纯文本
 5     return urllib.request.urlopen(url).read().decode('utf-8')
 6
 7 def download(url, filename):#将文件下载到本地
 8     urllib.request.urlretrieve(url, filename)
 9
10 if __name__ == '__main__':
11     print('---豆瓣妹子抓图机---')
12     dic = {1:'性感', 2:'有沟', 3:'美腿', 4:'小露点',
13            6:'所有男', 7:'肌肉男', 8:'清新男', 9:'有意思' ,
14            10:'所有', 11:'小清新', 12:'文艺', 13:'文艺男', 14:'美臀'}
15     for i in dic.keys():
16         print('{:<15}'.format(str(i)+'--'+dic[i]), end='')
17         if i%4==0: print()
18     category = int(input('\n请输入抓取类别:'))
19     pageNo1 = int(input('请输入抓取页面起始编号(0-476):'))#2014.5.5正好476页
20     pageNo2 = int(input('请输入抓取页面终止编号(0-476):'))
21     for no in range(pageNo1, pageNo2+1):
22         url = 'http://dbmeizi.com/category/{}?p={}'.format(category, no)
23         html = getHtml(url)
24         reMeizi = r'(?<=bigimg=").+jpg'
25         pics = re.findall(reMeizi, html)
26         folder = 'D:/DBMeizi/{}/{}/'.format(dic[category], no)
27         if not os.path.exists(folder):
28             os.makedirs(folder)
29         logfile = open(folder+'log.txt', 'wt')
30         logfile.write('图片来源：'+ url +'\n图片链接：\n')
31         for pic in pics:
32             print('正在下载', pic)
33             try:
34                 download(pic, folder+pic[-13:])
35             except:
36                 print('下载出错')
37                 logfile.write(pic + ' 下载出错！\n')
38                 continue
39             logfile.write(pic+'\n')
40         logfile.close()
41         print('下载' + dic[category] +'['+ str(no) +']结束。')
42         time.sleep(1)
43     print('全部任务结束。')
44