python爬虫之获取 wtfx.tk 上的 ss 二维码

 1 #coding:utf-8
 2 __Author__ = ‘liuqi‘
 3 import os
 4 import re
 5 import sys
 6 import copy
 7 import shutil
 8 import urllib
 9 import chardet
10 
11 def getHtml(url):
12     page = urllib.urlopen(url)
13     html = page.read()
14     return html
15 
16 def getPngAddr(html):
17     png = r"pic/\w+[-]?\w+[-]?\w*\.png"
18     tmp = re.compile(png)
19     png = re.findall(tmp, html)
20     # print png
21     for i in range(len(png)):
22         png[i] = url + png[i]
23     
24     return png
25 
26 def getPngName(pngAddr):
27     pngName = copy.deepcopy(pngAddr)
28     
29     pngT = r‘pic/(\w+[-]?\w+[-]?\w*)\.‘
30     t = re.compile(pngT)
31     for i in range(len(pngAddr)):
32         pngName[i] = re.findall(t, pngAddr[i])[0]
33     
34     return pngName
35     
36 def getPng(Addr, Name):
37     urllib.urlretrieve(Addr, "pic\\%s.png" % Name)
38 
39     
40 if __name__ == "__main__":
41     url = ‘http://wtfx.tk/‘
42 
43     html = getHtml(url)
44 
45     pngAddr = getPngAddr(html)
46     # print pngAddr
47     pngName = getPngName(pngAddr)
48 
49     # os.rmdir(‘pic‘)
50     try:
51         shutil.rmtree(‘pic‘)
52     except WindowsError, e:
53         print "couldn‘t rm folder: no such folder!"
54         raw_input("please press Enter to continue > ")
55     
56     os.mkdir(‘pic‘)
57 
58     for i in range(len(pngAddr)):
59         getPng(pngAddr[i], pngName[i])
60 
61 # html_code = chardet.detect(html)[‘encoding‘]
62 # sys_code = sys.getfilesystemencoding()
63 # print "html is encoding by: ", html_code
64 # print "system is encoding by: ", sys_code
65 # 正常输出网页
66 # print html.decode(html_code).encode(sys_code)