Fixed Netload, no Premium

4 files changed, 81 insertions, 72 deletions

diff --git a/module/config/core.xml b/module/config/core.xml
index 6da85cf32..392309e1c 100644
--- a/module/config/core.xml
+++ b/module/config/core.xml
@@ -11,7 +11,7 @@
         <key>ssl.key</key>
     </ssl>
     <webinterface>
-        <activated>True</activated>
+        <activated>False</activated>
         <host>0.0.0.0</host>
         <port>8000</port>
         <template>default</template>
diff --git a/module/plugins/NetloadIn.py b/module/plugins/NetloadIn.py
index b9fb4cfed..e90124f10 100644
--- a/module/plugins/NetloadIn.py
+++ b/module/plugins/NetloadIn.py
@@ -37,46 +37,30 @@ class NetloadIn(Plugin):
 
     def prepare(self, thread):
         pyfile = self.parent
+        self.req.clear_cookies()
 
-        self.want_reconnect = False
-
-        tries = 0
-
-        while not pyfile.status.url:
-
-            self.req.clear_cookies()
-            self.download_html()
-
-            pyfile.status.exists = self.file_exists()
-
-            if not pyfile.status.exists:
-                raise Exception, "The file was not found on the server."
-                
-            self.download_api_data()
-
+        self.download_api_data()
+        if self.file_exists():
             pyfile.status.filename = self.get_file_name()
-            
+
             if self.config['premium']:
+                self.logger.info("Netload: Use Premium Account")
                 pyfile.status.url = self.parent.url
+                #@TODO: premium??
                 return True
-            
-            self.download_html2()
-
-            self.get_wait_time()
 
-            pyfile.status.waituntil = self.time_plus_wait
-            pyfile.status.want_reconnect = self.want_reconnect
-
-            thread.wait(self.parent)
-
-            pyfile.status.url = self.get_file_url()
-
-            tries += 1
-            if tries > 3:
-                raise Exception, "Error while preparing DL, HTML dump: %s %s" % (self.html[0], self.html[1])
+            self.download_html()
+            while not pyfile.status.url:
+                self.get_wait_time()
+                pyfile.status.waituntil = self.time_plus_wait
+                pyfile.status.want_reconnect = self.want_reconnect
+                thread.wait(self.parent)
+                
+                pyfile.status.url = self.get_file_url()
 
-        return True
-        
+        else:
+            raise Exception, "The file was not found on the server."
+            
     def download_api_data(self):
         url = self.parent.url
         id_regex = re.compile("http://netload.in/datei(.*?)(?:\.htm|/)")
@@ -85,20 +69,43 @@ class NetloadIn(Plugin):
             apiurl = "http://netload.in/share/fileinfos2.php"
             src = self.req.load(apiurl, cookies=False, get={"file_id": match.group(1)})
             self.api_data = {}
-            lines = src.split(";")
-            self.api_data["fileid"] = lines[0]
-            self.api_data["filename"] = lines[1]
-            self.api_data["size"] = lines[2] #@TODO formatting? (ex: '2.07 KB')
-            self.api_data["status"] = lines[3]
-            self.api_data["checksum"] = lines[4]
-
+            if src != "unknown file_data":
+                lines = src.split(";")
+                self.api_data["exists"] = True
+                self.api_data["fileid"] = lines[0]
+                self.api_data["filename"] = lines[1]
+                self.api_data["size"] = lines[2] #@TODO formatting? (ex: '2.07 KB')
+                self.api_data["status"] = lines[3]
+                self.api_data["checksum"] = lines[4].replace("\n", "")
+            else:
+                self.api_data["exists"] = False
 
     def download_html(self):
-        if self.config['premium']:
-            self.config['username'], self.config['password']
-            self.req.load("http://netload.in/index.php", None, { "txtuser" : self.config['username'], "txtpass" : self.config['password'], "txtcheck" : "login", "txtlogin" : ""})
-        url = self.parent.url
-        self.html[0] = self.req.load(url, cookies=True)
+        #~ if self.config['premium']:
+            #~ self.config['username'], self.config['password']
+            #~ self.req.load("http://netload.in/index.php", None, { "txtuser" : self.config['username'], "txtpass" : self.config['password'], "txtcheck" : "login", "txtlogin" : ""})
+        self.html[0] = self.req.load(self.parent.url, cookies=True)
+        url_captcha_html = "http://netload.in/" + re.search('(index.php\?id=10&amp;.*&amp;captcha=1)', self.html[0]).group(1).replace("amp;", "")
+        for i in range(6):
+            self.html[1] = self.req.load(url_captcha_html, cookies=True)
+            try:
+                captcha_url = "http://netload.in/" + re.search('(share/includes/captcha.php\?t=\d*)', self.html[1]).group(1)
+            except:
+                url_captcha_html = "http://netload.in/" + re.search('(index.php\?id=10&amp;.*&amp;captcha=1)', self.html[1]).group(1).replace("amp;", "")
+                self.html[1] = self.req.load(url_captcha_html, cookies=True)
+                captcha_url = "http://netload.in/" + re.search('(share/includes/captcha.php\?t=\d*)', self.html[1]).group(1)
+
+            file_id = re.search('<input name="file_id" type="hidden" value="(.*)" />', self.html[1]).group(1)
+            captcha_image = tempfile.NamedTemporaryFile(suffix=".png").name
+            self.req.download(captcha_url, captcha_image, cookies=True)
+            captcha = self.ocr.get_captcha(captcha_image)
+            os.remove(captcha_image)
+            self.logger.debug("Captcha %s: %s" % (i, captcha))
+            sleep(5)
+            self.html[2] = self.req.load("http://netload.in/index.php?id=10", post={"file_id": file_id, "captcha_check": captcha}, cookies=True)
+
+            if re.search(r"(We will prepare your download..|We had a reqeust with the IP)", self.html[2]) != None:
+                break
 
     def download_html2(self):
         
@@ -141,42 +148,43 @@ class NetloadIn(Plugin):
             return None
 
     def get_wait_time(self):
-        wait = int(re.search(r"countdown\((.+),'change\(\)'\)", self.html[2]).group(1))
-        self.time_plus_wait = time() + wait / 100
-
         if re.search(r"We had a reqeust with the IP", self.html[2]):
-            self.want_reconnect = True
+            self.time_plus_wait = time() + 10 * 30
+            return
+            
+        wait_seconds = int(re.search(r"countdown\((.+),'change\(\)'\)", self.html[2]).group(1)) / 100
+        self.time_plus_wait = time() + wait_seconds
         
     def get_file_name(self):
-        try:
-            if self.api_data and self.api_data["filename"]:
-                return self.api_data["filename"]
+        if self.api_data["filename"]:
+            return self.api_data["filename"]
+        elif self.html[0]:
             file_name_pattern = '\t\t\t(.+)<span style="color: #8d8d8d;">'
-            return re.search(file_name_pattern, self.html[0]).group(1)
-        except:
-            return self.parent.url
+            file_name_search = re.search(file_name_pattern, self.html[0])
+            if file_name_search:
+                return file_name_search.group(1)
+        return self.parent.url
 
     def file_exists(self):
-        """ returns True or False
-        """
-        if re.search(r"The file has been deleted", self.html[0]) != None:
-            return False
-        else:
+        if self.api_data["exists"]:
+            return self.api_data["exists"]
+        elif self.html[0] and re.search(r"The file has been deleted", self.html[0]) == None:
             return True
+        return False
 
     def proceed(self, url, location):
-
         self.req.download(url, location, cookies=True)
 
     def check_file(self, local_file):
         if self.api_data and self.api_data["checksum"]:
             h = hashlib.md5()
-            with open(local_file, "rb") as f:
-                h.update(f.read())
+            f = open(local_file, "rb")
+            h.update(f.read())
+            f.close()
             hexd = h.hexdigest()
             if hexd == self.api_data["checksum"]:
                 return (True, 0)
             else:
                 return (False, 1)
         else:
-        	return (True, 5)
+            return (True, 5)
diff --git a/module/plugins/RapidshareCom.py b/module/plugins/RapidshareCom.py
index 615dda521..96d526d73 100644
--- a/module/plugins/RapidshareCom.py
+++ b/module/plugins/RapidshareCom.py
@@ -38,10 +38,12 @@ class RapidshareCom(Plugin):
 
     def prepare(self, thread):
         pyfile = self.parent
-        
+        self.req.clear_cookies()
+
         self.download_api_data()
         if self.api_data["status"] == "1":
             pyfile.status.filename = self.get_file_name()
+            
             if self.config["premium"]:
                 self.logger.info("Rapidshare: Use Premium Account (%sGB left)" % (self.props["premkbleft"]/1000000))
                 pyfile.status.url = self.parent.url
@@ -49,7 +51,7 @@ class RapidshareCom(Plugin):
 
             self.download_html()
             while self.no_slots:
-                self.download_serverhtml()
+                self.get_wait_time()
                 pyfile.status.waituntil = self.time_plus_wait
                 pyfile.status.want_reconnect = self.want_reconnect
                 thread.wait(pyfile)
@@ -122,7 +124,7 @@ class RapidshareCom(Plugin):
         self.html[0] = self.req.load(self.url, cookies=True)
         self.html_old = time()
 
-    def download_serverhtml(self):
+    def get_wait_time(self):
         """downloads html with the important informations
         """
         file_server_url = re.search(r"<form action=\"(.*?)\"", self.html[0]).group(1)
@@ -130,10 +132,10 @@ class RapidshareCom(Plugin):
         
         self.html_old = time()
 
-        if re.search(r"is already downloading", self.html[1]) != None:
+        if re.search(r"is already downloading", self.html[1]):
             self.logger.info("Rapidshare: Already downloading, wait 30 minutes")
             self.time_plus_wait = time() + 10 * 30
-            return False
+            return
         self.no_slots = False
         try:
             wait_minutes = re.search(r"Or try again in about (\d+) minute", self.html[1]).group(1)
@@ -160,7 +162,7 @@ class RapidshareCom(Plugin):
         return re.search(file_url_pattern, self.html[1]).group(1)
 
     def get_file_name(self):
-        if self.api_data and self.api_data["filename"]:
+        if self.api_data["filename"]:
             return self.api_data["filename"]
         elif self.html[0]:
             file_name_pattern = r"<p class=\"downloadlink\">.+/(.+) <font"
diff --git a/module/thread_list.py b/module/thread_list.py
index 6a42898be..d78a9b95c 100644
--- a/module/thread_list.py
+++ b/module/thread_list.py
@@ -110,7 +110,6 @@ class Thread_List(object):
                 newLinks = 0
                 if pyfile.plugin.links:
                     for link in pyfile.plugin.links:
-			print link
                         newFile = self.list.collector.addLink(link)
                         self.list.packager.addFileToPackage(pyfile.package.data["id"], self.list.collector.popFile(newFile))
                         newLinks += 1