python练习：从番号到封面-CSDN博客

我不知道为什么会选择python去学习，可能和前阵子有在v2ex看到有同学用python抓磁力的有关，今天12点起床闲来无事，继续学习吧。

本来也想找个磁力站练练手抓抓magnet的，打开收藏夹的几个站点才发现URL全都加密了。一个个找，终于发现一个可以联手的网站。嘻嘻。

 1 #!/usr/bin/env python
 2 
 3 #coding :UTF-8
 4 __auther__ = 'mashaz'
 5 import urllib,urllib2
 6 import sys
 7 import re
 8 print 'Thank ****** a lot'
 9 url = 'http://www.******.xyz/en/search/'
10 key = sys.argv[1]
11 key_len=len(key)
12 unicode(key,'utf-8')
13 url = url + key
14 req = urllib2.Request(url)
15 req.add_header('User-Agent','Mozilla 5.10')
16 fo = urllib2.urlopen(req)
17 html = str(fo.read())
18 #print html
19 
20 wait = re.compile(r'http://d8c5bb17\.ds\.******\.xyz/digital/video/[a-z0-9]+/[a-z0-9]+\.jpg')
21 image1 =re.findall(wait,html)
22 #print image1[0]
23 
24 r_detail = re.compile(r'http://www\.******\.xyz/en/movie/[a-zA-Z0-9]+')
25 image_detail = re.findall(r_detail,html)
26 s = image_detail[0]
27 #print s
28 #s detail_web
29 
30 req2 = urllib2.Request(s)
31 req.add_header('User-Agent','Mozilla 5.10')
32 fod = urllib2.urlopen(req2)
33 html2 = str(fod.read())
34 if(key_len==7):
35  wait2 = re.compile(r'http://d8c5bb17\.ds\.******\.xyz/digital/video/[a-zA-Z0-9]+/[a-zA-Z0-9]{8}pl\.jpg')
36 if(key_len==8):
37  wait2 = re.compile(r'http://d8c5bb17\.ds\.******\.xyz/digital/video/[a-zA-Z0-9]+/[a-zA-Z0-9]{9}pl\.jpg')
38 big_image = re.findall(wait2,html2)
39 #print big_image[0]
40 #print html2
41 
42 def getImage(addr):
43     u = urllib.urlopen(addr)
44     data=u.read()
45     splitPath = addr.split('/')
46     fName = splitPath.pop()
47     print fName
48 
49     f= open(fName,'wb')
50     f.write(data)
51     f.close()
52 
53 addr = big_image[0]
54 getImage(addr)