Merge pull request #2128 from thadrien/pull-request-dlprotect

Pull request dlprotect

5 files changed, 81 insertions, 17 deletions

diff --git a/module/plugins/PluginManager.py b/module/plugins/PluginManager.py
index f3f5f47bc..6c1d22359 100644
--- a/module/plugins/PluginManager.py
+++ b/module/plugins/PluginManager.py
@@ -272,6 +272,9 @@ class PluginManager:
                 self.log.error(_("Error importing %(name)s: %(msg)s") % {"name": name, "msg": str(e)})
                 if self.core.debug:
                     print_exc()
+        else:
+            self.log.debug("Plugin %s not found" % name)
+            self.log.debug("Available plugins : %s" % str(plugins))
 
     def loadClass(self, type, name):
         """Returns the class of a plugin with the same name"""
diff --git a/module/plugins/crypter/DlProtectCom.py b/module/plugins/crypter/DlProtectCom.py
index 3377d4a8a..874815eee 100644
--- a/module/plugins/crypter/DlProtectCom.py
+++ b/module/plugins/crypter/DlProtectCom.py
@@ -3,6 +3,7 @@
 import re
 import time
 
+import base64
 from base64 import urlsafe_b64encode
 
 from module.plugins.internal.SimpleCrypter import SimpleCrypter, create_getInfo
@@ -11,7 +12,7 @@ from module.plugins.internal.SimpleCrypter import SimpleCrypter, create_getInfo
 class DlProtectCom(SimpleCrypter):
     __name__    = "DlProtectCom"
     __type__    = "crypter"
-    __version__ = "0.07"
+    __version__ = "0.08"
     __status__  = "testing"
 
     __pattern__ = r'https?://(?:www\.)?dl-protect\.com/((en|fr)/)?\w+'
@@ -30,6 +31,56 @@ class DlProtectCom(SimpleCrypter):
 
     OFFLINE_PATTERN = r'Unfortunately, the link you are looking for is not found'
 
+    # Information decoding
+    # For test purposes
+    def info_decode(self, i):
+        # Remove end string
+        assert i.endswith("_%3D")
+        i = i[0:-4]
+        # Invert string
+        i = i[::-1]
+        # Base 64 decode
+        i = base64.b64decode(i)
+        # Split information
+        infos = i.split('|')
+        assert(len(infos) == 4)
+        res = infos[0]
+        user_agent = infos[1]
+        plugins = [x.split(';') for x in infos[2].split('&')]
+        java = {"ENABLE": True, "DISABLE":False}[infos[3]]
+        # Return information
+        return {'res':res,
+                'user_agent':user_agent,
+                'plugins':plugins,
+                'java':java}
+
+    # Information encoding
+    def info_encode(self, info):
+        # Pack information
+        res = info['res']
+        user_agent = info['user_agent']
+        plugins = '&'.join(';'.join(x) for x in info['plugins'])
+        java = {True:"ENABLE", False:"DISABLE"}[info['java']]
+        i = '|'.join([res, user_agent, plugins, java])
+        # Base 64 encode
+        i = base64.b64encode(i)
+        # Invert string
+        i = i[::-1]
+        # Add end string and return
+        i = i + "_%3D"
+        return i
+
+    # Sample configuration
+    def conf(self):
+        useragent = self.get_config('useragent', plugin="UserAgentSwitcher")
+        conf = {'res': '1280x611x24',
+                'java': True,
+                'user_agent': useragent,
+                'plugins': [['Adobe Acrobat', 'nppdf32.dll', 'Adobe PDF Plug-In For Firefox and Netscape 11.0.13', '11.0.13.17'],
+                            ['Adobe Acrobat', 'nppdf32.dll', 'Adobe PDF Plug-In For Firefox and Netscape 11.0.13', '11.0.13.17'],
+                            ['Java(TM) Platform SE 8 U51', 'npjp2.dll', 'Next Generation Java Plug-in 11.51.2 for Mozilla browsers', '11.51.2.16'],
+                            ['Shockwave Flash', 'NPSWF32_19_0_0_226.dll', 'Shockwave Flash 19.0 r0', '19.0.0.226']]}
+        return conf
 
     def get_links(self):
         #: Direct link with redirect
@@ -38,9 +89,11 @@ class DlProtectCom(SimpleCrypter):
 
         post_req = {'key'       : re.search(r'name="key" value="(.+?)"', self.data).group(1),
                     'submitform': ""}
+        self.log_debug("Key: %s" % post_req['key'])
 
         if "Please click on continue to see the links" in self.data:
             post_req['submitform'] = "Continue"
+            post_req['i'] = self.info_encode(self.conf())
             self.wait(2)
 
         else:
@@ -57,15 +110,20 @@ class DlProtectCom(SimpleCrypter):
                 m = re.search(r'/captcha\.php\?key=(.+?)"', self.data)
                 if m is not None:
                     captcha_code = self.captcha.decrypt("http://www.dl-protect.com/captcha.php?key=" + m.group(1), input_type="gif")
+                    self.log_debug("Captcha code: %s" % captcha_code)
                     post_req['secure'] = captcha_code
+                else:
+                    self.log_debug("Captcha code requested but captcha not found")
 
         self.data = self.load(self.pyfile.url, post=post_req)
 
+        # Check error messages in pages
         for errmsg in ("The password is incorrect", "The security code is incorrect"):
             if errmsg in self.data:
                 self.fail(_(errmsg[1:]))
 
-        return re.findall(r'<a href="([^/].+?)" target="_blank">', self.data)
+        # Filters interesting urls from ads
+        return re.findall(r'<a href="(?P<id>[^/].+?)" target="_blank">(?P=id)</a>', self.data)
 
 
 getInfo = create_getInfo(DlProtectCom)
diff --git a/module/plugins/internal/Captcha.py b/module/plugins/internal/Captcha.py
index 333602e29..d30271dd4 100644
--- a/module/plugins/internal/Captcha.py
+++ b/module/plugins/internal/Captcha.py
@@ -38,6 +38,7 @@ class Captcha(Plugin):
         """
         Extend to build your custom anti-captcha ocr
         """
+        self.log_debug("This function does nothing")
         pass
 
 
diff --git a/module/plugins/internal/OCR.py b/module/plugins/internal/OCR.py
index 89eed1832..b4e28ca0f 100644
--- a/module/plugins/internal/OCR.py
+++ b/module/plugins/internal/OCR.py
@@ -65,7 +65,7 @@ class OCR(Plugin):
         output = popen.stdout.read() + " | " + popen.stderr.read()
         popen.stdout.close()
         popen.stderr.close()
-        self.pyload.log_debug("Tesseract ReturnCode " + popen.returncode, "Output: " + output)
+        self.log_debug("Tesseract ReturnCode %d" % popen.returncode, "Output: %s" % output)
 
 
     def run_tesser(self, subset=False, digits=True, lowercase=True, uppercase=True, pagesegmode=None):
@@ -82,7 +82,7 @@ class OCR(Plugin):
             self.log_error(e)
             return
 
-        self.pyload.log_debug("Saving tiff...")
+        self.log_debug("Saving tiff...")
         self.image.save(tmpTif.name, 'TIFF')
 
         if os.name is "nt":
@@ -111,9 +111,9 @@ class OCR(Plugin):
                 tessparams.append("nobatch")
                 tessparams.append(os.path.abspath(tmpSub.name))
 
-        self.pyload.log_debug("Running tesseract...")
+        self.log_debug("Running tesseract...")
         self.run(tessparams)
-        self.pyload.log_debug("Reading txt...")
+        self.log_debug("Reading txt...")
 
         try:
             with open(tmpTxt.name, 'r') as f:
@@ -122,7 +122,7 @@ class OCR(Plugin):
         except Exception:
             self.result_captcha = ""
 
-        self.pyload.log_info(_("OCR result: ") + self.result_captcha)
+        self.log_info(_("OCR result: ") + self.result_captcha)
         try:
             os.remove(tmpTif.name)
             os.remove(tmpTxt.name)
diff --git a/module/plugins/internal/SimpleCrypter.py b/module/plugins/internal/SimpleCrypter.py
index f37323f90..59b9acc31 100644
--- a/module/plugins/internal/SimpleCrypter.py
+++ b/module/plugins/internal/SimpleCrypter.py
@@ -11,7 +11,7 @@ from module.plugins.internal.utils import replace_patterns, set_cookie, set_cook
 class SimpleCrypter(Crypter):
     __name__    = "SimpleCrypter"
     __type__    = "crypter"
-    __version__ = "0.78"
+    __version__ = "0.79"
     __status__  = "testing"
 
     __pattern__ = r'^unmatchable$'
@@ -149,24 +149,26 @@ class SimpleCrypter(Crypter):
 
 
     def handle_direct(self, pyfile):
-        link      = None
+        redirect = None
         maxredirs = self.get_config("maxredirs", default=10, plugin="UserAgentSwitcher")
 
         for i in xrange(maxredirs):
-            url = link or pyfile.url
-            self.log_debug("Redirect #%d to: %s" % (i, url))
+            redirect = redirect or pyfile.url
+            self.log_debug("Redirect #%d to: %s" % (i, redirect))
 
-            header   = self.load(url, just_header=True)
+            data = self.load(redirect)
+            header = dict(re.findall(r"(?P<name>.+?): (?P<value>.+?)\r?\n", self.req.http.header))
+                #Ugly, but there is no direct way to fetch headers AND data
             location = header.get('location')
 
             if location:
-                link = location
-
-            elif link:
-                self.links.append(link)
+                redirect = location
+            else:
+                self.data = data
+                self.links.extend(self.get_links())
                 return
         else:
-            self.log_warning(_("Too many redirects"))
+            self.log_error(_("Too many redirects"))
 
 
     def preload(self):