fix uloz.to premium, add turbobit.net free

3 files changed, 120 insertions, 19 deletions

diff --git a/module/plugins/hoster/TurbobitNet.py b/module/plugins/hoster/TurbobitNet.py
new file mode 100644
index 000000000..ee55d257b
--- /dev/null
+++ b/module/plugins/hoster/TurbobitNet.py
@@ -0,0 +1,87 @@
+# -*- 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
+
+from pycurl import HTTPHEADER
+
+class TurbobitNet(SimpleHoster):
+    __name__ = "TurbobitNet"
+    __type__ = "hoster"
+    __pattern__ = r"http://(?:\w*\.)?turbobit.net/(?P<ID>\w+).*"
+    __version__ = "0.01"
+    __description__ = """Turbobit.net plugin"""
+    __author_name__ = ("zoidberg")
+    __author_mail__ = ("zoidberg@mujmail.cz")
+    
+    FILE_SIZE_PATTERN = r"<span class='file-icon1 document'>[^<]*</span>\s*\((?P<S>[^\)]+)\)"
+    FILE_NAME_PATTERN = r'<meta name="keywords" content="(?P<N>[^,]+)'
+    FILE_OFFLINE_PATTERN = r'<h2>File Not Found</h2>'
+    FILE_URL_REPLACEMENTS = [(r'(?<=http://)(.*?)(?=turbobit.net/)', '')]
+    SH_COOKIES = [("turbobit.net", "user_lang", "en")]
+    
+    CAPTCHA_KEY_PATTERN = r'src="http://api\.recaptcha\.net/challenge\?k=([^"]+)"'
+    DOWNLOAD_URL_PATTERN = r'(?P<url>/download/redirect/[^"\']+)'
+    LIMIT_WAIT_PATTERN = r'<div id="time-limit-text">\s*.*?<span id=\'timeout\'>(\d+)</span> seconds'      
+
+    def handleFree(self):         
+        self.url = "http://turbobit.net/download/free/%s" % self.file_info['ID']
+        self.html = self.load(self.url)
+        
+        found = re.search(self.CAPTCHA_KEY_PATTERN, self.html)
+        captcha_key = found.group(1) if found else '6LcTGLoSAAAAAHCWY9TTIrQfjUlxu6kZlTYP50_c'
+        recaptcha = ReCaptcha(self)                                    
+
+        for i in range(5):
+            found = re.search(self.LIMIT_WAIT_PATTERN, self.html)
+            if found:
+                self.setWait(int(found.group(1)), True)
+                self.wait()
+                self.retry()
+        
+            action, inputs = self.parseHtmlForm("action='#'")            
+            inputs['recaptcha_challenge_field'], inputs['recaptcha_response_field'] = recaptcha.challenge(captcha_key)
+            if not inputs: self.parseError("inputs")
+            self.logDebug(inputs)
+
+            self.html = self.load(self.url, post = inputs)
+            
+            if not "<div class='download-timer-header'>" in self.html:
+                self.invalidCaptcha()
+            else:
+                self.correctCaptcha()
+                break
+        else: self.fail("Invalid captcha")
+        
+        self.req.http.lastURL = self.url
+        self.req.http.c.setopt(HTTPHEADER, ["X-Requested-With: XMLHttpRequest"])
+        
+        self.setWait(60, False)
+        self.wait()
+        
+        self.html = self.load("http://turbobit.net/download/getLinkAfterTimeout/" + self.file_info['ID'])
+        found = re.search(self.DOWNLOAD_URL_PATTERN, self.html)
+        if not found: self.parseError("free download link")        
+        self.url = "http://turbobit.net" + found.group('url')
+        self.logDebug(self.url)
+        self.download(self.url)
+
+getInfo = create_getInfo(TurbobitNet)
\ No newline at end of file
diff --git a/module/plugins/hoster/UlozTo.py b/module/plugins/hoster/UlozTo.py
index a67e52d4d..54138e7e5 100644
--- a/module/plugins/hoster/UlozTo.py
+++ b/module/plugins/hoster/UlozTo.py
@@ -27,7 +27,7 @@ class UlozTo(SimpleHoster):
     __name__ = "UlozTo"
     __type__ = "hoster"
     __pattern__ = r"http://(\w*\.)?(uloz\.to|ulozto\.(cz|sk|net)|bagruj.cz|zachowajto.pl)/(?:live/)?(?P<id>\w+/[^/?]*)"
-    __version__ = "0.84"
+    __version__ = "0.85"
     __description__ = """uloz.to"""
     __author_name__ = ("zoidberg")
 
@@ -45,11 +45,12 @@ class UlozTo(SimpleHoster):
     CAPTCHA_PATTERN = r'<img class="captcha" src="(.*?(\d+).png)" alt="" />'
 
     def setup(self):
-        self.multiDL = self.resumeDownload = True
+        self.multiDL = self.premium 
+        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)
+        self.html = self.load(pyfile.url, decode = True, cookies = True)
 
         passwords = self.getPassword().splitlines()
         while self.PASSWD_PATTERN in self.html:
@@ -70,6 +71,8 @@ class UlozTo(SimpleHoster):
             self.handlePremium()
         else:
             self.handleFree()
+            
+        self.doCheckDownload()
 
     def handleFree(self):
         parsed_url = self.findDownloadURL(premium=False)
@@ -87,18 +90,16 @@ class UlozTo(SimpleHoster):
             captcha_text = self.decryptCaptcha(captcha_url)
 
         self.log.debug('CAPTCHA_URL:' + captcha_url + ' CAPTCHA ID:' + captcha_id + ' CAPTCHA TEXT:' + captcha_text)
-
-        # download and check
-        self.download(parsed_url, post={"captcha[id]": captcha_id, "captcha[text]": captcha_text, "freeDownload": "Download"}, cookies=True)
-        self.doCheckDownload()
-
+        
         self.setStorage("captcha_id", captcha_id)
         self.setStorage("captcha_text", captcha_text)
+        self.multiDL = True
+
+        self.download(parsed_url, post={"captcha[id]": captcha_id, "captcha[text]": captcha_text, "freeDownload": "Download"}, cookies=True)
 
     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")
@@ -113,7 +114,8 @@ class UlozTo(SimpleHoster):
             "wrong_captcha": re.compile(self.CAPTCHA_PATTERN),
             "offline": re.compile(self.FILE_OFFLINE_PATTERN),
             "passwd": self.PASSWD_PATTERN,
-            "paralell_dl": re.compile(r'<title>Uloz.to - Ji. stahuje.</title>')
+            "paralell_dl": "<title>Uloz.to - Již stahuješ</title>",
+            "not_found": "<title>Ulož.to</title>"
         })
 
         if check == "wrong_captcha":
@@ -130,5 +132,7 @@ class UlozTo(SimpleHoster):
             self.setWait(300, True)
             self.wait()
             self.retry()
+        elif check == "not_found":
+            self.fail("Server error - file not downloadable")
 
 getInfo = create_getInfo(UlozTo)
\ No newline at end of file
diff --git a/module/plugins/internal/SimpleHoster.py b/module/plugins/internal/SimpleHoster.py
index 0aab2334c..555eefee3 100644
--- a/module/plugins/internal/SimpleHoster.py
+++ b/module/plugins/internal/SimpleHoster.py
@@ -23,14 +23,21 @@ from time import time
 from module.plugins.Hoster import Hoster
 from module.utils import html_unescape, fixup, parseFileSize
 from module.network.RequestFactory import getURL
+from module.network.CookieJar import CookieJar
 
-def reSub(string, ruleslist):
+def replace_patterns(string, ruleslist):
     for r in ruleslist:
         rf, rt = r
         string = re.sub(rf, rt, string)
         #self.logDebug(rf, rt, string)
     return string
     
+def set_cookies(cj, cookies):
+    for cookie in cookies:
+        if isinstance(cookie, tuple) and len(cookie) == 3:
+            domain, name, value = cookie
+            cj.setCookie(domain, name, value)
+    
 def parseHtmlTagAttrValue(attr_name, tag):
         m = re.search(r"%s\s*=\s*([\"']?)((?<=\")[^\"]+|(?<=')[^']+|[^\s\"'][^>\s]+)\1" % attr_name, tag)   
         return m.group(2) if m else ''
@@ -62,9 +69,9 @@ def parseFileInfo(self, url = '', html = '', infomode = False):
                 # File online, return name and size
                 info['status'] = 2
                 if 'N' in info:
-                    info['name'] = reSub(info['N'], self.FILE_NAME_REPLACEMENTS)
+                    info['name'] = replace_patterns(info['N'], self.FILE_NAME_REPLACEMENTS)
                 if 'S' in info:
-                    size = reSub(info['S'] + info['U'] if 'U' in info else info['S'], self.FILE_SIZE_REPLACEMENTS)
+                    size = replace_patterns(info['S'] + info['U'] if 'U' in info else info['S'], self.FILE_SIZE_REPLACEMENTS)
                     info['size'] = parseFileSize(size)
                 elif isinstance(info['size'], (str, unicode)):
                     if 'units' in info: info['size'] += info['units']
@@ -80,8 +87,10 @@ def parseFileInfo(self, url = '', html = '', infomode = False):
 def create_getInfo(plugin):
     def getInfo(urls):
         for url in urls:
-            file_info = parseFileInfo(plugin, url, getURL(reSub(url, plugin.FILE_URL_REPLACEMENTS), \
-                decode = not plugin.SH_BROKEN_ENCODING))
+            cj = CookieJar(plugin.__name__)
+            if isinstance(plugin.SH_COOKIES, list): set_cookies(cj, plugin.SH_COOKIES)
+            file_info = parseFileInfo(plugin, url, getURL(replace_patterns(url, plugin.FILE_URL_REPLACEMENTS), \
+                decode = not plugin.SH_BROKEN_ENCODING, cookies = cj))
             yield file_info
     return getInfo
 
@@ -97,7 +106,7 @@ class PluginParseError(Exception):
 
 class SimpleHoster(Hoster):
     __name__ = "SimpleHoster"
-    __version__ = "0.18"
+    __version__ = "0.20"
     __pattern__ = None
     __type__ = "hoster"
     __description__ = """Base hoster plugin"""
@@ -117,14 +126,15 @@ class SimpleHoster(Hoster):
     FILE_URL_REPLACEMENTS = []
     
     SH_BROKEN_ENCODING = False # Set to True or encoding name if encoding in http header is not correct
-    SH_COOKIES = True
-    SH_CHECK_TRAFFIC = False
+    SH_COOKIES = True # or False or list of tuples [(domain, name, value)]
+    SH_CHECK_TRAFFIC = False # True = force check traffic left for a premium account 
 
     def setup(self):
         self.resumeDownload = self.multiDL = True if self.premium else False
+        if isinstance(self.SH_COOKIES, list): set_cookies(self.req.cj, self.SH_COOKIES)
 
     def process(self, pyfile):
-        pyfile.url = reSub(pyfile.url, self.FILE_URL_REPLACEMENTS)
+        pyfile.url = replace_patterns(pyfile.url, self.FILE_URL_REPLACEMENTS)
         self.html = self.load(pyfile.url, decode = not self.SH_BROKEN_ENCODING, cookies = self.SH_COOKIES)
         self.file_info = self.getFileInfo()
         if self.premium and (not self.SH_CHECK_TRAFFIC or self.checkTrafficLeft()):