update filefactory, add datei.to, jumbofiles.com

4 files changed, 141 insertions, 40 deletions

diff --git a/module/plugins/hoster/DateiTo.py b/module/plugins/hoster/DateiTo.py
new file mode 100644
index 000000000..529a5a06f
--- /dev/null
+++ b/module/plugins/hoster/DateiTo.py
@@ -0,0 +1,92 @@
+# -*- 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.internal.SimpleHoster import SimpleHoster, create_getInfo
+from module.plugins.ReCaptcha import ReCaptcha
+
+class DateiTo(SimpleHoster):
+    __name__ = "DateiTo"
+    __type__ = "hoster"
+    __pattern__ = r"http://(?:www\.)?datei\.to/datei/(?P<ID>\w+)\.html"
+    __version__ = "0.01"
+    __description__ = """Datei.to plugin - free only"""
+    __author_name__ = ("zoidberg")
+    __author_mail__ = ("zoidberg@mujmail.cz")
+
+    FILE_NAME_PATTERN = r'Dateiname:</td>\s*<td colspan="2"><strong>(?P<N>.*?)</'
+    FILE_SIZE_PATTERN = r'Dateigr&ouml;&szlig;e:</td>\s*<td colspan="2">(?P<S>.*?)</'
+    FILE_OFFLINE_PATTERN = r'>Datei wurde nicht gefunden<|>Bitte wähle deine Datei aus... <'
+    PARALELL_PATTERN = r'>Du lädst bereits eine Datei herunter<'
+    
+    WAIT_PATTERN = r'countdown\({seconds: (\d+)'
+    DATA_PATTERN = r'url: "(.*?)", data: "(.*?)",'
+    RECAPTCHA_KEY_PATTERN = r'Recaptcha.create\("(.*?)"'
+        
+    def handleFree(self):
+        url = 'http://datei.to/ajax/download.php'
+        data = {'P': 'I', 'ID': self.file_info['ID']}
+        
+        recaptcha = ReCaptcha(self)   
+        
+        for i in range(10):
+            self.logDebug("URL", url, "POST", data)        
+            self.html = self.load(url, post = data)
+            self.checkErrors()
+            
+            if url.endswith('download.php') and 'P' in data:
+                if data['P'] == 'I':
+                    self.doWait()
+                    
+                elif data['P'] == 'IV':
+                    break   
+            
+            found = re.search(self.DATA_PATTERN, self.html)
+            if not found: self.parseError('data')
+            url = 'http://datei.to/' + found.group(1)
+            data = dict(x.split('=') for x in found.group(2).split('&'))
+            
+            if url.endswith('recaptcha.php'):
+                found = re.search(self.RECAPTCHA_KEY_PATTERN, self.html)
+                recaptcha_key = found.group(1) if found else "6LdBbL8SAAAAAI0vKUo58XRwDd5Tu_Ze1DA7qTao"
+                
+                data['recaptcha_challenge_field'], data['recaptcha_response_field'] = recaptcha.challenge(recaptcha_key) 
+        
+        else:
+            self.fail('Too bad...')  
+              
+        download_url = self.html
+        self.logDebug('Download URL', download_url)
+        self.download(download_url)
+    
+    def checkErrors(self):
+        found = re.search(self.PARALELL_PATTERN, self.html)
+        if found:
+            self.setWait(wait_time + 1, False)
+            self.wait(300)
+            self.retry()
+    
+    def doWait(self):                              
+        found = re.search(self.WAIT_PATTERN, self.html)
+        wait_time = int(found.group(1)) if found else 30
+        self.setWait(wait_time + 1, False)
+  
+        self.load('http://datei.to/ajax/download.php', post = {'P': 'Ads'})
+        self.wait()      
+        
+getInfo = create_getInfo(DateiTo)
diff --git a/module/plugins/hoster/FilefactoryCom.py b/module/plugins/hoster/FilefactoryCom.py
index 4f6666675..135dd90a1 100644
--- a/module/plugins/hoster/FilefactoryCom.py
+++ b/module/plugins/hoster/FilefactoryCom.py
@@ -4,6 +4,7 @@ from module.plugins.Hoster import Hoster
 from module.plugins.ReCaptcha import ReCaptcha
 from module.utils import parseFileSize
 from module.plugins.Plugin import chunks
+from module.common.json_layer import json_loads
 
 import re
 
@@ -16,7 +17,7 @@ def checkFile(plugin, urls):
     url_ids = url_dict.keys()
     urls = map(lambda url_id: 'http://www.filefactory.com/file/' + url_id, url_ids)
 
-    html = getURL("http://filefactory.com/tool/links.php", post = {"func": "links", "links": "\n".join(urls)}, decode=True)   
+    html = getURL("http://www.filefactory.com/tool/links.php", post = {"func": "links", "links": "\n".join(urls)}, decode=True)   
         
     for m in re.finditer(plugin.LC_INFO_PATTERN, html):
         if m.group('id') in url_ids:
@@ -34,29 +35,28 @@ class FilefactoryCom(Hoster):
     __name__ = "FilefactoryCom"
     __type__ = "hoster"
     __pattern__ = r"http://(?:www\.)?filefactory\.com/file/(?P<id>[a-zA-Z0-9]+).*" # URLs given out are often longer but this is the requirement
-    __version__ = "0.33"
+    __version__ = "0.34"
     __description__ = """Filefactory.Com File Download Hoster"""
     __author_name__ = ("paulking", "zoidberg")
     
-    LC_INFO_PATTERN = r'<tr class="(even|odd)">\s*<td>\s*<a href="http://www.filefactory.com/file/(?P<id>\w+)[^"]*">(?P<name>[^<]+)</a>\s*.*\s*</td>\s*<td>(?P<size>[0-9.]+ \w+)</td>'
-    LC_OFFLINE_PATTERN = r'<li class="(even|odd)">\s*<div class="metadata">http://www.filefactory.com/file/(?P<id>\w+)/</div>'
-    
+    LC_INFO_PATTERN = r'<h1 class="name">(?P<name>[^<]+) \((?P<size>[0-9.]+ \w+)\)</h1>\s*<p>http://www.filefactory.com/file/(?P<id>\w+)/'
+    LC_OFFLINE_PATTERN = r'<p>http://www.filefactory.com/file/(?P<id>\w+)/</p>\s*<p class="errorResponse">'
+ 
     FILE_OFFLINE_PATTERN = r'<title>File Not Found'
     FILE_NAME_PATTERN = r'<span class="last">(?P<name>.*?)</span>'
     FILE_INFO_PATTERN = r'<span>(?P<size>\d(\d|\.)*) (?P<units>..) file uploaded'
     
-    FILE_CHECK_PATTERN = r'check:\'(?P<check>.*?)\''
-    CAPTCHA_KEY_PATTERN = r'Recaptcha.create\("(?P<recaptchakey>.*?)",' 
-    WAIT_PATH_PATTERN = r'path:"(?P<path>.*?)"'
+    FILE_CHECK_PATTERN = r'check:\s*\'(?P<check>.*?)\''
+    CAPTCHA_KEY_PATTERN = r'Recaptcha.create\(\s*"(.*?)",' 
     WAIT_PATTERN = r'id="startWait" value="(?P<wait>\d+)"'
-    FILE_URL_PATTERN = r'<a href="(?P<url>.*?)" id="downloadLinkTarget">'
+    FILE_URL_PATTERN = r'<p[^>]*?id="downloadLinkTarget"[^>]*>\s*<a href="(?P<url>.*?)"' 
             
     def setup(self):
         self.multiDL = self.resumeDownloads = self.premium
 
     def process(self, pyfile):
         # Check file
-        pyfile.name, pyfile.size, status, self.url = checkFile(self, [pyfile.url])[0]        
+        pyfile.name, pyfile.size, status, self.url = checkFile(self, [pyfile.url])[0]     
         if status != 2: self.offline()
         self.logDebug("File Name: %s Size: %d" % (pyfile.name, pyfile.size)) 
         
@@ -93,42 +93,41 @@ class FilefactoryCom(Hoster):
              
         # Check Id
         self.check = re.search(self.FILE_CHECK_PATTERN, self.html).group('check')
-        self.log.debug("%s: File check code is [%s]" % (self.__name__, self.check))
+        self.logDebug("File check code is [%s]" % self.check)
         
         # Resolve captcha
-        self.log.debug("%s: File is captcha protected" % self.__name__)
-        id = re.search(self.CAPTCHA_KEY_PATTERN, self.html).group('recaptchakey')
+        found = re.search(self.CAPTCHA_KEY_PATTERN, self.html)
+        recaptcha_key = found.group(1) if found else "6LeN8roSAAAAAPdC1zy399Qei4b1BwmSBSsBN8zm"
+        recaptcha = ReCaptcha(self)
+        
         # Try up to 5 times
-        for i in range(5):
-            self.log.debug("%s: Resolving ReCaptcha with key [%s], round %d" % (self.__name__, id, i+1))
-            recaptcha = ReCaptcha(self)
-            challenge, code = recaptcha.challenge(id)
-            response = self.load("http://www.filefactory.com/file/checkCaptcha.php",
-                            post={"check" : self.check, "recaptcha_challenge_field" : challenge, "recaptcha_response_field" : code})
-            captchavalid = self.handleCaptchaErrors(response)
-            if captchavalid:
+        for i in range(5):           
+            challenge, code = recaptcha.challenge(recaptcha_key)
+            response = json_loads(self.load("http://www.filefactory.com/file/checkCaptcha.php",
+                            post={"check" : self.check, "recaptcha_challenge_field" : challenge, "recaptcha_response_field" : code}))
+            if response['status'] == 'ok':
+                self.correctCaptcha()
                 break
-        if not captchavalid:
+            else:
+                self.invalidCaptcha()                            
+        else:
             self.fail("No valid captcha after 5 attempts")
-
-        # Get wait URL
-        waitpath = re.search(self.WAIT_PATH_PATTERN, response).group('path')
-        waiturl = "http://www.filefactory.com" + waitpath
         
         # This will take us to a wait screen
-        self.log.debug("%s: fetching wait with url [%s]" % (self.__name__, waiturl))
+        waiturl = "http://www.filefactory.com" + response['path']
+        self.logDebug("Fetching wait with url [%s]" % waiturl)
         waithtml = self.load(waiturl, decode=True)
 
         # Find the wait value and wait     
         wait = int(re.search(self.WAIT_PATTERN, waithtml).group('wait'))
-        self.log.debug("%s: Waiting %d seconds." % (self.__name__, wait))
+        self.logDebug("Waiting %d seconds." % wait)
         self.setWait(wait, True)
         self.wait()
 
         # Now get the real download url and retrieve the file
         url = re.search(self.FILE_URL_PATTERN,waithtml).group('url')
         # this may either download our file or forward us to an error page
-        self.log.debug("%s: download url %s" % (self.__name__, url))
+        self.logDebug("Download URL: %s" % url)
         dl = self.download(url)
         
         check = self.checkDownload({"multiple": "You are currently downloading too many files at once.",
@@ -136,20 +135,11 @@ class FilefactoryCom(Hoster):
 
         if check == "multiple":
             self.setWait(15*60)
-            self.log.debug("%s: Parallel downloads detected waiting 15 minutes" % self.__name__)
+            self.logDebug("Parallel downloads detected; waiting 15 minutes")
             self.wait()
             self.retry()
         elif check == "error":
             self.fail("Unknown error")
-
-    def handleCaptchaErrors(self, response):
-        self.log.debug("%s: Result of captcha resolving [%s]" % (self.__name__, response))
-        if 'status:"ok"' in response:
-            self.correctCaptcha()
-            return True
-        
-        self.log.debug("%s: Wrong captcha" % self.__name__)
-        self.invalidCaptcha()
     
     def handlePremium(self):
         self.fail('Please enable direct downloads')
diff --git a/module/plugins/hoster/JumbofilesCom.py b/module/plugins/hoster/JumbofilesCom.py
new file mode 100644
index 000000000..a338b31cc
--- /dev/null
+++ b/module/plugins/hoster/JumbofilesCom.py
@@ -0,0 +1,19 @@
+# -*- coding: utf-8 -*-
+import re
+from module.plugins.hoster.XFileSharingPro import XFileSharingPro, create_getInfo
+from module.utils import html_unescape
+
+class JumbofilesCom(XFileSharingPro):
+    __name__ = "JumbofilesCom"
+    __type__ = "hoster"
+    __pattern__ = r"http://(?:\w*\.)*(jumbofiles.com)/\w{12}"
+    __version__ = "0.01"
+    __description__ = """JumboFiles.com hoster plugin"""
+    __author_name__ = ("zoidberg")
+    __author_mail__ = ("zoidberg@mujmail.cz")
+    
+    FILE_INFO_PATTERN = '<TR><TD>(?P<N>[^<]+?)\s*<small>\((?P<S>[\d.]+)\s*(?P<U>[KMG][bB])\)</small></TD></TR>'
+    FILE_OFFLINE_PATTERN = 'Not Found or Deleted / Disabled due to inactivity or DMCA'
+    DIRECT_LINK_PATTERN = '<FORM METHOD="LINK" ACTION="(.*?)"'
+
+getInfo = create_getInfo(JumbofilesCom)
\ No newline at end of file
diff --git a/module/plugins/hoster/XFileSharingPro.py b/module/plugins/hoster/XFileSharingPro.py
index b7b7803f5..6b98b4d08 100644
--- a/module/plugins/hoster/XFileSharingPro.py
+++ b/module/plugins/hoster/XFileSharingPro.py
@@ -154,7 +154,7 @@ class XFileSharingPro(SimpleHoster):
                 self.wait()
             elif 'captcha' in self.errmsg:
                 self.invalidCaptcha()
-            elif 'countdown' in self.errmsg:
+            elif 'countdown' or 'Expired session' in self.errmsg:
                 self.retry(3)
             elif 'maintenance' in self.errmsg:
                 self.tempOffline()