hoster plugin fixes; new plugins: mediafire, sendspace

4 files changed, 260 insertions, 8 deletions

diff --git a/module/plugins/hoster/MediafireCom.py b/module/plugins/hoster/MediafireCom.py
new file mode 100644
index 000000000..f7c122f40
--- /dev/null
+++ b/module/plugins/hoster/MediafireCom.py
@@ -0,0 +1,130 @@
+# -*- coding: utf-8 -*-
+"""
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 3 of the License,
+    or (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+    See the GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, see <http://www.gnu.org/licenses/>.
+
+    @author: zoidberg
+"""
+
+import re
+from module.common.JsEngine import JsEngine
+from module.plugins.Hoster import Hoster
+from module.network.RequestFactory import getURL
+
+def getInfo(urls):
+    result = []
+
+    for url in urls:
+        html = getURL(url, decode=True)
+        if re.search(MediafireCom.FILE_OFFLINE_PATTERN, html):
+            # File offline
+            result.append((url, 0, 1, url))
+        else:
+            # Get file info
+            name, size = url, 0
+
+            found = re.search(MediafireCom.FILE_SIZE_PATTERN, html)
+            if found is not None:
+                size, units = found.groups()
+                size = float(size) * 1024 ** {'kB': 1, 'MB': 2, 'GB': 3}[units]
+
+            found = re.search(MediafireCom.FILE_NAME_PATTERN, html)
+            if found is not None:
+                name = found.group(1)
+
+            if found or size > 0:
+                result.append((name, size, 2, url))
+    yield result
+
+class MediafireCom(Hoster):
+    __name__ = "MediafireCom"
+    __type__ = "hoster"
+    __pattern__ = r"http://(?:\w*\.)*mediafire\.com/.*"
+    __version__ = "0.2"
+    __description__ = """Mediafire.com plugin - free only"""
+    __author_name__ = ("zoidberg")
+    
+    PAGE1_FUNCTION_PATTERN = r"function %s\(qk,pk1\)\{if[^']*'loadingicon'\);[^;]*; (.*?)eval"
+    PAGE1_KEY_PATTERN = ";break;}\s*(\w+='';\w+=unescape.*?)eval\("
+    PAGE1_RESULT_PATTERN = r"(\w+)\('(?P<qk>[^']+)','(?P<pk1>[^']+)'\)"
+    PAGE1_DIV_PATTERN = r'getElementById\("(\w{32})"\)'
+    PAGE1_PKR_PATTERN = r"pKr='([^']+)';"
+    
+    PAGE2_VARS_PATTERN = r'<script language="Javascript"><!--\s*(var.*?unescape.*?)eval\('
+    PAGE2_DZ_PATTERN = r'break;case 15:(.*)</script>'
+    PAGE2_LINK_PATTERN = r"(?:if.*</a>\')?(?:eval\(\")?(.*?)eval\("
+    FINAL_LINK_PATTERN = r'parent.document.getElementById\(\'(\w{32})\'\)\).*?"(http://download[^"]+)" \+(\w+)\+ "([^"]+)">'
+    
+    FILE_NAME_PATTERN = r'<META NAME="description" CONTENT="([^"]+)"/>'
+    FILE_SIZE_PATTERN = r'<div style="font-size:14px;padding-top:12px;color:#777;">\(([0-9.]+) (kB|MB|GB)\)</div>'
+    FILE_OFFLINE_PATTERN = r'class="error_msg_title"> Invalid or Deleted File. </div>'
+    
+    def process(self, pyfile):
+        self.html = self.load(pyfile.url, decode = True, cookies = True)
+        
+        try:
+            pyfile.name = re.search(self.FILE_NAME_PATTERN, self.html).group(1)
+            found = re.search(self.FILE_SIZE_PATTERN, self.html)
+            pyfile.size = float(found.group(1)) * 1024 ** {'kB': 1, 'MB': 2, 'GB': 3}[found.group(2)]
+        except Exception, e:
+            self.logError(e)
+            self.retry(3, 0, "Parse error - file info")
+    
+        self.handleFree(pyfile)
+    
+    def handleFree(self, pyfile):
+        js = JsEngine()
+                   
+        found = re.search(self.PAGE1_KEY_PATTERN, self.html)
+        if found:
+            result = js.eval(found.group(1))
+            found = re.search(self.PAGE1_RESULT_PATTERN, result)   
+        else:
+            self.fail("Parse error - javascript")
+        
+        param_dict = found.groupdict()            
+        param_dict['r'] = re.search(self.PAGE1_PKR_PATTERN, self.html).group(1)
+        self.logDebug(param_dict)
+        key_func = found.group(1)
+        self.logDebug("KEY_FUNC: %s" % key_func)
+        
+        found = re.search(self.PAGE1_FUNCTION_PATTERN % key_func, self.html)
+        result = js.eval(found.group(1))
+        key_div = found = re.search(self.PAGE1_DIV_PATTERN, result).group(1)
+        self.logDebug("KEY_DIV: %s" % key_div)
+        
+        self.html = self.load("http://www.mediafire.com/dynamic/download.php", get = param_dict, cookies = True)
+        result = js.eval(re.search(self.PAGE2_VARS_PATTERN, self.html).group(1))
+        var_list = dict(re.findall("([^=]+)='([^']+)';", result))
+        
+        page2_dz = re.search(self.PAGE2_DZ_PATTERN, self.html, re.DOTALL).group(1)
+        
+        final_link = None
+        for link_enc in re.finditer(self.PAGE2_LINK_PATTERN, page2_dz):
+            #self.logDebug("LINK_ENC: %s..." % link_enc.group(1)[:20])
+            try:
+                link_dec = js.eval(link_enc.group(1).replace(r"\'",r"'"))                
+            except:
+                self.logError("Unable to decrypt link %s" % link_enc.group(1)[:20])
+                self.logDebug(link_enc.group(1).replace(r"\'",r"'"))
+                continue
+                    
+            found = re.search(self.FINAL_LINK_PATTERN, link_dec)
+            if found and found.group(1) == key_div:
+                final_link = found.group(2) + var_list[found.group(3)] + found.group(4)
+                break;           
+        else:
+            self.fail("Final link not found")
+            
+        self.logDebug("FINAL LINK: %s" % final_link)
+        self.download(final_link, cookies=True)
\ No newline at end of file
diff --git a/module/plugins/hoster/MultishareCz.py b/module/plugins/hoster/MultishareCz.py
index 488fdcbc4..d8dfeaed9 100644
--- a/module/plugins/hoster/MultishareCz.py
+++ b/module/plugins/hoster/MultishareCz.py
@@ -51,13 +51,13 @@ class MultishareCz(Hoster):
     __name__ = "MultishareCz"
     __type__ = "hoster"
     __pattern__ = r"http://(\w*\.)?multishare.cz/stahnout/.*"
-    __version__ = "0.2"
+    __version__ = "0.3"
     __description__ = """MultiShare.cz"""
     __author_name__ = ("zoidberg")
 
     FILE_ID_PATTERN = r'/stahnout/(\d+)/'
-    FILE_INFO_PATTERN = r'<ul class="no-padding"><li>N�zev: <strong>([^<]+)</strong></li><li>Velikost: <strong>([^&]+)&nbsp;([^<]+)</strong>'
-    OFFLINE_PATTERN = r'<h1>St�hnout soubor</h1><p><strong>Po.adovan� soubor neexistuje.</strong></p>'
+    FILE_INFO_PATTERN = ur'<ul class="no-padding"><li>Název: <strong>([^<]+)</strong></li><li>Velikost: <strong>([^&]+)&nbsp;([^<]+)</strong>'
+    OFFLINE_PATTERN = ur'<h1>Stáhnout soubor</h1><p><strong>Požadovaný soubor neexistuje.</strong></p>'
 
     def setup(self):
         self.multiDL = False
@@ -80,4 +80,4 @@ class MultishareCz(Hoster):
 
         self.download("http://www.multishare.cz/html/download_free.php", get={
             "ID": file_id
-        })
+        })
\ No newline at end of file
diff --git a/module/plugins/hoster/SendspaceCom.py b/module/plugins/hoster/SendspaceCom.py
new file mode 100644
index 000000000..1d65945c7
--- /dev/null
+++ b/module/plugins/hoster/SendspaceCom.py
@@ -0,0 +1,108 @@
+# -*- coding: utf-8 -*-
+"""
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 3 of the License,
+    or (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+    See the GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, see <http://www.gnu.org/licenses/>.
+
+    @author: zoidberg
+"""
+
+import re
+from module.plugins.Hoster import Hoster
+from module.network.RequestFactory import getURL
+
+def getInfo(urls):
+    result = []
+
+    for url in urls:
+        html = getURL(url, decode=True)
+        if re.search(SendspaceCom.FILE_OFFLINE_PATTERN, html):
+            # File offline
+            result.append((url, 0, 1, url))
+        else:
+            # Get file info
+            name, size = url, 0
+
+            found = re.search(SendspaceCom.FILE_SIZE_PATTERN, html)
+            if found is not None:
+                size, units = found.groups()
+                size = float(size) * 1024 ** {'KB': 1, 'MB': 2, 'GB': 3}[units]
+
+            found = re.search(SendspaceCom.FILE_NAME_PATTERN, html)
+            if found is not None:
+                name = found.group(1)
+
+            if found or size > 0:
+                result.append((name, size, 2, url))
+    yield result
+
+
+class SendspaceCom(Hoster):
+    __name__ = "SendspaceCom"
+    __type__ = "hoster"
+    __pattern__ = r"http://(www\.)?sendspace.com/file/.*"
+    __version__ = "0.1"
+    __description__ = """sendspace.com plugin - free only"""
+    __author_name__ = ("zoidberg")
+
+    DOWNLOAD_URL_PATTERN = r'<a id="download_button" href="([^"]+)"'
+    FILE_NAME_PATTERN = r'<h2 class="bgray">\s*<(?:b|strong)>([^<]+)</'
+    FILE_SIZE_PATTERN = r'<div class="file_description reverse margin_center">\s*<b>File Size:</b>\s*([0-9.]+)(KB|MB|GB)\s*</div>'
+    FILE_OFFLINE_PATTERN = r'<div class="msg error" style="cursor: default">Sorry, the file you requested is not available.</div>'
+    CAPTCHA_PATTERN = r'<td><img src="(/captchas/captcha.php?captcha=([^"]+))"></td>'
+    USER_CAPTCHA_PATTERN = r'<td><img src="/captchas/captcha.php?user=([^"]+))"></td>'
+
+    def setup(self):
+        self.multiDL = False
+
+    def process(self, pyfile):
+        self.html = self.load(pyfile.url, decode=True)
+
+        if re.search(self.FILE_OFFLINE_PATTERN, self.html) is not None:
+            self.offline()
+
+        found = re.search(self.FILE_NAME_PATTERN, self.html)
+        if found is None: self.fail("Parse error (file name)")
+        pyfile.name = found.group(1)
+
+        found = re.search(self.FILE_SIZE_PATTERN, self.html)
+        if found is None: self.fail("Parse error (file size)")
+        pyfile.size = float(found.group(1)) * 1024 ** {'KB': 1, 'MB': 2, 'GB': 3}[found.group(2)]
+
+        params = {}
+        for i in range(3):
+            found = re.search(self.DOWNLOAD_URL_PATTERN, self.html)
+            if found:
+                if params.has_key('captcha_hash'): self.correctCaptcha()
+                download_url = found.group(1)
+                break
+
+            found = re.search(self.CAPTCHA_PATTERN, self.html)
+            if found:
+                if params.has_key('captcha_hash'): self.invalidCaptcha()
+                captcha_url1 = "http://www.sendspace.com/" + found.group(1)
+                found = re.search(self.USER_CAPTCHA_PATTERN, self.html)
+                captcha_url2 = "http://www.sendspace.com/" + found.group(1)
+                params = {'captcha_hash' : found.group(2),
+                          'captcha_submit': 'Verify',
+                          'captcha_answer': self.decryptCaptcha(captcha_url1) + " " + self.decryptCaptcha(captcha_url2)
+                         }
+            else:
+                params = {'download': "Regular Download"}
+
+            self.logDebug(params)
+            self.html = self.load(pyfile.url, post = params)
+        else:
+            self.fail("Download link not found")
+
+        self.logDebug("Download URL: %s" % download_url)
+        self.download(download_url)
diff --git a/module/plugins/hoster/UloziskoSk.py b/module/plugins/hoster/UloziskoSk.py
index b8ec0df55..e439a0f87 100644
--- a/module/plugins/hoster/UloziskoSk.py
+++ b/module/plugins/hoster/UloziskoSk.py
@@ -30,10 +30,19 @@ def getInfo(urls):
             result.append((url, 0, 1, url))
         else:
             # Get file info
+            name, size = url, 0
+
+            found = re.search(UloziskoSk.FILE_SIZE_PATTERN, html)
+            if found is not None:
+                size, units = found.groups()
+                size = float(size) * 1024 ** {'KB': 1, 'MB': 2, 'GB': 3}[units]
+
             found = re.search(UloziskoSk.FILE_NAME_PATTERN, html)
             if found is not None:
                 name = found.group(1)
-                result.append((name, 0, 2, url))
+
+            if found or size > 0:
+                result.append((name, size, 2, url))
     yield result
 
 
@@ -41,15 +50,16 @@ class UloziskoSk(Hoster):
     __name__ = "UloziskoSk"
     __type__ = "hoster"
     __pattern__ = r"http://(\w*\.)?ulozisko.sk/.*"
-    __version__ = "0.1"
+    __version__ = "0.2"
     __description__ = """Ulozisko.sk"""
     __author_name__ = ("zoidberg")
 
     URL_PATTERN = r'<form name = "formular" action = "([^"]+)" method = "post">'
     ID_PATTERN = r'<input type = "hidden" name = "id" value = "([^"]+)" />'
     FILE_NAME_PATTERN = r'<input type = "hidden" name = "name" value = "([^"]+)" />'
+    FILE_SIZE_PATTERN = ur'Veľkosť súboru: <strong>([0-9.]+) (KB|MB|GB)</strong><br />'
     CAPTCHA_PATTERN = r'<img src="(/obrazky/obrazky.php\?fid=[^"]+)" alt="" />'
-    FILE_OFFLINE_PATTERN = r'<span class = "red">Zadan� s�bor neexistuje z jedn�ho z nasleduj�cich d�vodov:</span>'
+    FILE_OFFLINE_PATTERN = ur'<span class = "red">Zadaný súbor neexistuje z jedného z nasledujúcich dôvodov:</span>'
 
     def setup(self):
         self.multiDL = False
@@ -69,6 +79,11 @@ class UloziskoSk(Hoster):
         if found is None:
             self.fail("Parse error (FILENAME)")
         pyfile.name = found.group(1)
+        
+        found = re.search(self.FILE_SIZE_PATTERN, self.html)
+        if found is not None:
+            size, units = found.groups()
+            pyfile.size = float(size) * 1024 ** {'KB': 1, 'MB': 2, 'GB': 3}[units]
 
         found = re.search(self.ID_PATTERN, self.html)
         if found is None:
@@ -92,4 +107,3 @@ class UloziskoSk(Hoster):
             "name": pyfile.name,
             "but": "++++STIAHNI+S%DABOR++++"
         })
-        
\ No newline at end of file