filefactory premium, uloz.to new url pattern

2 files changed, 107 insertions, 90 deletions

diff --git a/module/plugins/hoster/FilefactoryCom.py b/module/plugins/hoster/FilefactoryCom.py
index 37b2bb7ce..17520a6c3 100644
--- a/module/plugins/hoster/FilefactoryCom.py
+++ b/module/plugins/hoster/FilefactoryCom.py
@@ -1,88 +1,95 @@
 # -*- coding: utf-8 -*-
-from __future__ import with_statement
-
 from module.network.RequestFactory import getURL
 from module.plugins.Hoster import Hoster
 from module.plugins.ReCaptcha import ReCaptcha
+from module.utils import parseFileSize
+from module.plugins.Plugin import chunks
 
 import re
 
-def getInfo(urls):
-    result = []
+def checkFile(plugin, urls):
+    file_info = []
+    url_dict = {}
     
     for url in urls:
-        
-        # Get file info html
-        # @TODO: Force responses in english language so current patterns will be right
-        html = getURL(url)
-        if re.search(FilefactoryCom.FILE_OFFLINE_PATTERN, html):
-            result.append((url, 0, 1, url))
+        url_dict[re.search(plugin.__pattern__, url).group('id')] = (url, 0, 0, url)
+    url_ids = url_dict.keys()
+    urls = map(lambda url_id: 'http://www.filefactory.com/file/' + url_id, url_ids)
 
-        # Name
-        name = re.search(FilefactoryCom.FILE_NAME_PATTERN, html).group('name')
-        m = re.search(FilefactoryCom.FILE_INFO_PATTERN, html)
+    html = getURL("http://filefactory.com/tool/links.php", post = {"func": "links", "links": "\n".join(urls)}, decode=True)   
         
-        # Size
-        value = float(m.group('size'))
-        units = m.group('units')
-        pow = {'KB' : 1, 'MB' : 2, 'GB' : 3}[units] 
-        size = int(value*1024**pow)
+    for m in re.finditer(plugin.LC_INFO_PATTERN, html):
+        if m.group('id') in url_ids:
+            url_dict[m.group('id')] = (m.group('name'), parseFileSize(m.group('size')), 2, url_dict[m.group('id')][3])
+            
+    for m in re.finditer(plugin.LC_OFFLINE_PATTERN, html):
+        if m.group('id') in url_ids:
+            url_dict[m.group('id')] = (url_dict[m.group('id')][0], 0, 1, url_dict[m.group('id')][3])
     
-        # Return info
-        result.append((name, size, 2, url))
-        
-    yield result
+    file_info = url_dict.values()
     
+    return file_info
+   
 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__ = "0.3"
+    __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__ = "0.31"
     __description__ = """Filefactory.Com File Download Hoster"""
-    __author_name__ = ("paulking")
+    __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>'
     
     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>.*?)"'
     WAIT_PATTERN = r'id="startWait" value="(?P<wait>\d+)"'
     FILE_URL_PATTERN = r'<a href="(?P<url>.*?)" id="downloadLinkTarget">'
-        
+            
     def setup(self):
-        self.multiDL = False
+        self.multiDL = self.resumeDownloads = self.premium
 
     def process(self, pyfile):
-    
-        self.pyfile = pyfile
+        # Check file
+        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)) 
         
-        # Force responses language to US English
-        self.req.cj.setCookie("filefactory.com", "ff_locale","")
-
-        # Load main page
-        self.html = self.load(self.pyfile.url, ref=False, decode=True)
-
-        # Check offline
-        if re.search(self.FILE_OFFLINE_PATTERN, self.html) is not None:
-            self.offline()
+        # Handle downloading
+        url = self.checkDirectDownload(pyfile.url)
+        if url:
+            self.download(url)
+        else:                
+            self.html = self.load(pyfile.url, decode = True)
+                      
+            if self.premium:
+                self.handlePremium()
+            else:
+                self.handleFree()
+              
+    def checkDirectDownload(self, url):
+        for i in range(5):
+            header = self.load(url, just_header = True)           
+            if 'location' in header:
+                url = header['location'].strip() 
+                if not url.startswith("http://"):
+                    url = "http://www.filefactory.com" + url
+                self.logDebug('URL: ' + url)
+            elif 'content-disposition' in header:
+                return url
         
-        # File id
-        self.file_id = re.match(self.__pattern__, self.pyfile.url).group('id')
-        self.log.debug("%s: File id is [%s]" % (self.__name__, self.file_id))
-           
-        # File name
-        self.pyfile.name = re.search(self.FILE_NAME_PATTERN, self.html).group('name')
-
+        return False                                
+    
+    def handleFree(self):        
         # 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))
-
-        # Handle free downloading
-        self.handleFree()
-    
-    def handleFree(self):
-    
+        
         # Resolve captcha
         self.log.debug("%s: File is captcha protected" % self.__name__)
         id = re.search(self.CAPTCHA_KEY_PATTERN, self.html).group('recaptchakey')
@@ -138,3 +145,9 @@ class FilefactoryCom(Hoster):
         
         self.log.debug("%s: Wrong captcha" % self.__name__)
         self.invalidCaptcha()
+    
+    def handlePremium(self):
+        self.fail('Please enable direct downloads')
+        
+def getInfo(urls):
+    for chunk in chunks(urls, 100): yield checkFile(FilefactoryCom, chunk)
diff --git a/module/plugins/hoster/UlozTo.py b/module/plugins/hoster/UlozTo.py
index 5f482e189..a67e52d4d 100644
--- a/module/plugins/hoster/UlozTo.py
+++ b/module/plugins/hoster/UlozTo.py
@@ -21,54 +21,57 @@ from module.plugins.internal.SimpleHoster import SimpleHoster, create_getInfo
 
 def convertDecimalPrefix(m):
     # decimal prefixes used in filesize and traffic
-    return ("%%.%df" % {'k':3,'M':6,'G':9}[m.group(2)] % float(m.group(1))).replace('.','')     
+    return ("%%.%df" % {'k':3,'M':6,'G':9}[m.group(2)] % float(m.group(1))).replace('.','')
 
 class UlozTo(SimpleHoster):
     __name__ = "UlozTo"
     __type__ = "hoster"
-    __pattern__ = r"http://(\w*\.)?(uloz\.to|ulozto\.(cz|sk|net)|bagruj.cz|zachowajto.pl)/(?:live/)?(?P<id>\d+/[^/?]*)"
-    __version__ = "0.83"
+    __pattern__ = r"http://(\w*\.)?(uloz\.to|ulozto\.(cz|sk|net)|bagruj.cz|zachowajto.pl)/(?:live/)?(?P<id>\w+/[^/?]*)"
+    __version__ = "0.84"
     __description__ = """uloz.to"""
     __author_name__ = ("zoidberg")
 
-    FILE_NAME_PATTERN = r'<a href="#download" class="jsShowDownload">(?P<N>[^<]+)</a>' 
-    FILE_SIZE_PATTERN = r'<span id="fileSize">(?P<S>[^<]+)</span>'   
-    FILE_SIZE_REPLACEMENTS = [('([0-9.]+)\s([kMG])B', convertDecimalPrefix)]       
-    FILE_OFFLINE_PATTERN = ur'<title>(404 - Page not found|Stránka nenalezena|Nie można wyświetlić strony)</title>'
-    
-    PASSWD_PATTERN = r'<input type="password" class="text" name="file_password" id="frmfilepasswordForm-file_password" />'
-    VIPLINK_PATTERN = r'<a href="[^"]*\?disclaimer=1" class="linkVip">'    
+    FILE_NAME_PATTERN = r'<a href="#download" class="jsShowDownload">(?P<N>[^<]+)</a>'
+    FILE_SIZE_PATTERN = r'<span id="fileSize">(?P<S>[^<]+)</span>'
+    FILE_INFO_PATTERN = r'<p>File <strong>(?P<N>[^<]+)</strong> is password protected</p>'
+    FILE_OFFLINE_PATTERN = r'<title>404 - Page not found</title>|<h1 class="h1">File was banned</h1>'
+    FILE_SIZE_REPLACEMENTS = [('([0-9.]+)\s([kMG])B', convertDecimalPrefix)]
+    FILE_URL_REPLACEMENTS = [(r"(?<=http://)([^/]+)", "www.ulozto.net")]
+
+    PASSWD_PATTERN = r'<div class="passwordProtectedFile">'
+    VIPLINK_PATTERN = r'<a href="[^"]*\?disclaimer=1" class="linkVip">'
     FREE_URL_PATTERN = r'<div class="freeDownloadForm"><form action="([^"]+)"'
     PREMIUM_URL_PATTERN = r'<div class="downloadForm"><form action="([^"]+)"'
     CAPTCHA_PATTERN = r'<img class="captcha" src="(.*?(\d+).png)" alt="" />'
-    
-    def process(self, pyfile):        
-        self.url = "http://www.ulozto.net/" + re.match(self.__pattern__, pyfile.url).group('id')   
-        
-        self.html = self.load(self.url, decode=True)
-        
-        # password protected links
-        passwords = self.getPassword().splitlines()       
+
+    def setup(self):
+        self.multiDL = self.resumeDownload = True
+
+    def process(self, pyfile):
+        pyfile.url = re.sub(r"(?<=http://)([^/]+)", "www.ulozto.net", pyfile.url)
+        self.html = self.load(pyfile.url, decode = True, cookies = False)
+
+        passwords = self.getPassword().splitlines()
         while self.PASSWD_PATTERN in self.html:
             if passwords:
                 password = passwords.pop(0)
                 self.logInfo("Password protected link, trying " + password)
-                self.html = self.load(self.url, get = {"do": "filepasswordForm-submit"}, post={"file_password": password, "fpwdsend": 'Odeslat'}, cookies=True)
+                self.html = self.load(pyfile.url, get = {"do": "passwordProtectedForm-submit"},
+                    post={"password": password, "password_send": 'Send'}, cookies=True)
             else:
                 self.fail("No or incorrect password")
-        
-        self.file_info = self.getFileInfo()
-                
-        # adult content    
+
         if re.search(self.VIPLINK_PATTERN, self.html):
-            self.html = self.load(self.url, get={"disclaimer": "1"})
-        
+            self.html = self.load(pyfile.url, get={"disclaimer": "1"})
+
+        self.file_info = self.getFileInfo()
+
         if self.premium and self.checkTrafficLeft():
             self.handlePremium()
-        else: 
+        else:
             self.handleFree()
-            
-    def handleFree(self):    
+
+    def handleFree(self):
         parsed_url = self.findDownloadURL(premium=False)
 
         # get and decrypt captcha
@@ -82,21 +85,21 @@ class UlozTo(SimpleHoster):
             captcha_url, captcha_id = found.groups()
 
             captcha_text = self.decryptCaptcha(captcha_url)
-        
+
         self.log.debug('CAPTCHA_URL:' + captcha_url + ' CAPTCHA ID:' + captcha_id + ' CAPTCHA TEXT:' + captcha_text)
 
-        # download and check        
+        # download and check
         self.download(parsed_url, post={"captcha[id]": captcha_id, "captcha[text]": captcha_text, "freeDownload": "Download"}, cookies=True)
-        self.doCheckDownload()   
-        
+        self.doCheckDownload()
+
         self.setStorage("captcha_id", captcha_id)
         self.setStorage("captcha_text", captcha_text)
-    
+
     def handlePremium(self):
         parsed_url = self.findDownloadURL(premium=True)
         self.download(parsed_url, post={"download": "Download"})
         self.doCheckDownload()
-        
+
     def findDownloadURL(self, premium=False):
         msg = "%s link" % ("Premium" if premium else "Free")
         found = re.search(self.PREMIUM_URL_PATTERN if premium else self.FREE_URL_PATTERN, self.html)
@@ -104,13 +107,13 @@ class UlozTo(SimpleHoster):
         parsed_url = "http://www.ulozto.net" + found.group(1)
         self.logDebug("%s: %s" % (msg, parsed_url))
         return parsed_url
-    
+
     def doCheckDownload(self):
         check = self.checkDownload({
             "wrong_captcha": re.compile(self.CAPTCHA_PATTERN),
             "offline": re.compile(self.FILE_OFFLINE_PATTERN),
             "passwd": self.PASSWD_PATTERN,
-            "paralell_dl": u'<h2 class="center">Z Vašeho počítače se již stahuje</h2>'
+            "paralell_dl": re.compile(r'<title>Uloz.to - Ji. stahuje.</title>')
         })
 
         if check == "wrong_captcha":
@@ -123,8 +126,9 @@ class UlozTo(SimpleHoster):
         elif check == "passwd":
             self.fail("Wrong password")
         elif check == "paralell_dl":
-            self.setWait(600, True)
+            self.multiDL = False
+            self.setWait(300, True)
             self.wait()
-            self.retry()    
+            self.retry()
 
-getInfo = create_getInfo(UlozTo)        
\ No newline at end of file
+getInfo = create_getInfo(UlozTo)
\ No newline at end of file