MiniScripts/miss-bone.py

   1 #!/usr/bin/env python
   2
   3 '''
   4 This program is free software; you can redistribute it and/or modify
   5 it under the terms of the Revised BSD License.
   6
   7 This program is distributed in the hope that it will be useful,
   8 but WITHOUT ANY WARRANTY; without even the implied warranty of
   9 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  10 Revised BSD License for more details.
  11
  12 Copyright 2014 Cool Dude 2k - http://idb.berlios.de/
  13 Copyright 2014 Game Maker 2k - http://intdb.sourceforge.net/
  14 Copyright 2014 Kazuki Przyborowski - https://github.com/KazukiPrzyborowski
  15
  16 $FileInfo: miss-bone.py - Last Update: 6/12/2014 Ver. 1.0.0 RC 2 - Author: cooldude2k $
  17 '''
  18
  19 import argparse
  20 import datetime
  21 import gzip
  22 import os
  23 import re
  24 import sys
  25 import time
  26 import urllib
  27
  28 import cookielib
  29 import StringIO
  30 import urllib2
  31 import urlparse
  32
  33 fakeua = "Mozilla/5.0 (Windows NT 6.1; rv:24.0) Gecko/20100101 Firefox/24.0"
  34 geturls_cj = cookielib.CookieJar()
  35 geturls_opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(geturls_cj))
  36 geturls_opener.addheaders = [
  37     ("Referer",
  38      "http://www.emoticonplus.com/miss-bone/"),
  39     ("User-Agent",
  40      fakeua),
  41     ("Accept-Encoding",
  42      "gzip, deflate"),
  43     ("Accept-Language",
  44      "en-US,en-CA,en-GB,en-UK,en-AU,en-NZ,en-ZA,en;q=0.5"),
  45     ("Accept-Charset",
  46      "ISO-8859-1,ISO-8859-15,utf-8;q=0.7,*;q=0.7"),
  47     ("Accept",
  48      "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"),
  49     ("Connection",
  50      "close")]
  51 sfcountsub = 0
  52 sfcountfull = 0
  53 i = 1
  54 il = 15
  55 while (i < il):
  56     print(
  57         str(i) +
  58         " Reading URL: http://www.emoticonplus.com/miss-bone/page/" +
  59         str(i))
  60     geturls_text = geturls_opener.open(
  61         "http://www.emoticonplus.com/miss-bone/page/" + str(i))
  62     if (geturls_text.info().get("Content-Encoding") ==
  63             "gzip" or geturls_text.info().get("Content-Encoding") == "deflate"):
  64         strbuf = StringIO.StringIO(geturls_text.read())
  65         gzstrbuf = gzip.GzipFile(fileobj=strbuf)
  66         out_text = gzstrbuf.read()[:]
  67     if (geturls_text.info().get("Content-Encoding") !=
  68             "gzip" and geturls_text.info().get("Content-Encoding") != "deflate"):
  69         out_text = geturls_text.read()[:]
  70     regex_text = re.escape("<a class=\"emoticon-list\" href=\"#\" data=\"") + "(.*?)" + \
  71         re.escape("\" im=\"") + "([0-9]+)" + \
  72         re.escape("\" category=\"miss-bone\">")
  73     post_text = re.findall(regex_text, out_text)
  74     isub = 0
  75     ilsub = len(post_text)
  76     print(str(i) + " Found " + str(ilsub) + " GIF Images.")
  77     while (isub < ilsub):
  78         getsub2xurls_cj = geturls_cj
  79         getsub2xurls_opener = urllib2.build_opener(
  80             urllib2.HTTPCookieProcessor(getsub2xurls_cj))
  81         getsub2xurls_opener.addheaders = [
  82             ("Referer",
  83              "http://www.emoticonplus.com/miss-bone/page/" +
  84              str(i)),
  85             ("User-Agent",
  86              fakeua),
  87             ("Accept-Encoding",
  88              "gzip, deflate"),
  89             ("Accept-Language",
  90              "en-US,en-CA,en-GB,en-UK,en-AU,en-NZ,en-ZA,en;q=0.5"),
  91             ("Accept-Charset",
  92              "ISO-8859-1,ISO-8859-15,utf-8;q=0.7,*;q=0.7"),
  93             ("Accept",
  94              "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"),
  95             ("Connection",
  96              "close")]
  97         print(str(i) + "," + str(isub + 1) + " Start Downloading Image File: " +
  98               str(isub + 1) + " of " + str(ilsub))
  99         print(str(i) + "," + str(isub + 1) +
 100               " Downloading Image: " + post_text[isub][0])
 101         getsub2xurls_text = getsub2xurls_opener.open(post_text[isub][0])
 102         gif_file_name = os.path.basename(
 103             urlparse.urlparse(post_text[isub][0]).path)
 104         print(str(i) + "," + str(isub + 1) +
 105               " Finished Downloading Image: " + post_text[isub][0])
 106         print(str(i) + "," + str(isub + 1) +
 107               " Saving File: ./" + gif_file_name)
 108         gifsf = open("./" + gif_file_name, "wb")
 109         gifsf.write(getsub2xurls_text.read())
 110         gifsf.close()
 111         isub = isub + 1
 112         sfcountsub = sfcountsub + 1
 113     print(str(i) + " Downloaded " + str(sfcountsub) + " GIF Images")
 114     sfcountfull = sfcountfull + sfcountsub
 115     sfcountsub = 0
 116     i = i + 1
 117 print("Downloaded " + str(sfcountfull) + " GIF Images")
 118 sfcountfull = 0