├── .gitignore
├── README.md
└── ooxx.py


/.gitignore:
--------------------------------------------------------------------------------
 1 | # Byte-compiled / optimized / DLL files
 2 | __pycache__/
 3 | *.py[cod]
 4 | 
 5 | # C extensions
 6 | *.so
 7 | 
 8 | # Distribution / packaging
 9 | .Python
10 | env/
11 | build/
12 | develop-eggs/
13 | dist/
14 | downloads/
15 | eggs/
16 | .eggs/
17 | lib/
18 | lib64/
19 | parts/
20 | sdist/
21 | var/
22 | *.egg-info/
23 | .installed.cfg
24 | *.egg
25 | 
26 | # PyInstaller
27 | #  Usually these files are written by a python script from a template
28 | #  before PyInstaller builds the exe, so as to inject date/other infos into it.
29 | *.manifest
30 | *.spec
31 | 
32 | # Installer logs
33 | pip-log.txt
34 | pip-delete-this-directory.txt
35 | 
36 | # Unit test / coverage reports
37 | htmlcov/
38 | .tox/
39 | .coverage
40 | .coverage.*
41 | .cache
42 | nosetests.xml
43 | coverage.xml
44 | *,cover
45 | 
46 | # Translations
47 | *.mo
48 | *.pot
49 | 
50 | # Django stuff:
51 | *.log
52 | 
53 | # Sphinx documentation
54 | docs/_build/
55 | 
56 | # PyBuilder
57 | target/
58 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # ooxx
 2 | 
 3 | ## Warning
 4 | 
 5 | Just for studying. Please don't consume `Jandan` too much network traffic.
 6 | 
 7 | ## Run
 8 | 
 9 | Make sure you have installed python, then you can run the code below:
10 | 
11 | ```
12 | python ooxx.py
13 | ```
14 | 
15 | ## About
16 | 
17 | author: **Haipz**
18 | 
19 | site: **http://haipz.com**
20 | 
21 | e-mail: **haipzm@gmail.com**
22 | 
23 | 


--------------------------------------------------------------------------------
/ooxx.py:
--------------------------------------------------------------------------------
 1 | '''
 2 | 
 3 |     author  : haipz
 4 |     site    : haipz.com
 5 |     email   : i@haipz.com
 6 | 
 7 | modified by TC
 8 | oo xx indexes are included.
 9 | 
10 | '''
11 | 
12 | import urllib2, os, re, thread, time
13 | 
14 | def getHtml(url) :
15 |     hdr = {'User-Agent':'Mozilla/5.0'}
16 |     req = urllib2.Request(url, headers=hdr)
17 |     page = urllib2.urlopen(req)
18 |     html = page.read()
19 |     return html
20 | 
21 | def filterComment(source) :
22 |     pattern = ur'begin comments([\s\S]*?)end comments'
23 |     matchs = re.search(pattern, source)
24 |     return matchs.group()
25 | 
26 | def filterThumbnail(source) :
27 |     pattern = ur'<img src="([\s\S]*?)\.gif"'
28 |     reobj = re.compile(pattern)
29 |     result, number = reobj.subn('', source)
30 |     return result
31 | 
32 | def downloadPicture(picurl, picpath, picname) :
33 |     pic = urllib2.urlopen(picurl)
34 |     f = open(picpath + picname, 'wb')
35 |     f.write(pic.read()) 
36 |     f.close()
37 |     print 'System: ' + picname + ' saved\n'
38 | 
39 | choice = int(input("0. ooxx 1. pic : "))
40 | pagestart = int(input("page start: "))
41 | pageend = int(input("page end: "))
42 | ooover = int(input("at least how many oo: "))
43 | xxbelow = int(input("at most how many xx: "))
44 | 
45 | if choice == 0 :
46 |     dirname = "ooxx"
47 | else :
48 |     dirname = "pic"
49 | 
50 | path = os.getcwd() + "/" + dirname
51 | isExists = os.path.exists(path)
52 | if not isExists :
53 |     print 'System: ' + path + " created"
54 |     os.makedirs(path)
55 | else :
56 |     print 'System: ' + path + " exists"
57 | 
58 | initurl = "http://jandan.net/" + dirname + "/"
59 | 
60 | for pagenum in range(pagestart, pageend) :
61 |     cururl = initurl + "page-" + str(pagenum)
62 |     print 'Current url: ' + cururl
63 |     inithtml = getHtml(cururl)
64 |     curhtml = filterComment(inithtml)
65 | 
66 |     pattern = ur'<li id="comment-([\s\S]*?)</li>'
67 |     reobj = re.compile(pattern)
68 |     matchs = reobj.findall(curhtml)
69 |     count0 = 0
70 |     for match in matchs :
71 |         count0 = count0 + 1
72 |         match = filterThumbnail(match)
73 | 
74 |         oopattern = ur'(?:<span id="cos_support-)(?:\d*?)(?:">)(\d*?)(?:</span>)'
75 |         xxpattern = ur'(?:<span id="cos_unsupport-)(?:\d*?)(?:">)(\d*?)(?:</span>)'
76 |         oo = re.search(oopattern, match).group(1)
77 |         xx = re.search(xxpattern, match).group(1)
78 | 
79 |         picpattern = ur'(?:href=")(http\:\/\/w[\s\S]*?)(.jpg|.png|.gif)'
80 |         picobj = re.compile(picpattern)
81 |         result = picobj.findall(match)
82 | 
83 |         count1 = 0
84 |         for pic in result :
85 |             if int(oo) > ooover and int(xx) < xxbelow:
86 |                 count1 = count1 + 1
87 |                 picurl = pic[0] + pic[1]
88 |                 picpath = path + '/'
89 |                 picname = str(pagenum) + '_oo' + oo + '_xx' + xx + '_' + str(count0) + '_' + str(count1) + pic[1]
90 | 
91 |                 print 'Infomation:'
92 |                 print 'Picture url: ' + picurl
93 |                 print 'Picture path: ' + picpath
94 |                 print 'Picture name: ' + picname
95 |                 try :
96 |                     downloadPicture(picurl, picpath, picname)
97 |                 except Exception as e :
98 |                     print(e)
99 | 


--------------------------------------------------------------------------------