mediafire.com plugin update (still not finished)

1 files changed, 59 insertions, 28 deletions

diff --git a/module/plugins/hoster/MediafireCom.py b/module/plugins/hoster/MediafireCom.py
index ae1c13613..9e18527cf 100644
--- a/module/plugins/hoster/MediafireCom.py
+++ b/module/plugins/hoster/MediafireCom.py
@@ -19,6 +19,7 @@
 import re
 from module.plugins.Hoster import Hoster
 from module.network.RequestFactory import getURL
+from module.plugins.ReCaptcha import ReCaptcha
 
 def getInfo(urls):
     result = []
@@ -45,12 +46,14 @@ def getInfo(urls):
                 result.append((name, size, 2, url))
     yield result
 
+def replace_eval(js_expr):
+    return js_expr.replace(r"\'", r"'").replace(r'eval("', '')
 
 class MediafireCom(Hoster):
     __name__ = "MediafireCom"
     __type__ = "hoster"
     __pattern__ = r"http://(?:\w*\.)*mediafire\.com/.*"
-    __version__ = "0.2"
+    __version__ = "0.3"
     __description__ = """Mediafire.com plugin - free only"""
     __author_name__ = ("zoidberg")
 
@@ -59,68 +62,96 @@ class MediafireCom(Hoster):
     PAGE1_RESULT_PATTERN = r"(\w+)\('(?P<qk>[^']+)','(?P<pk1>[^']+)'\)"
     PAGE1_DIV_PATTERN = r'getElementById\("(\w{32})"\)'
     PAGE1_PKR_PATTERN = r"pKr='([^']+)';"
+    RECAPTCHA_PATTERN = r'src="http://api.recaptcha.net/challenge?k=([^"]+)">'
+    PAGE1_ACTION_PATTERN = r'<link rel="canonical" href="([^"]+)"/>'
 
     PAGE2_VARS_PATTERN = r'<script language="Javascript"><!--\s*(var.*?unescape.*?)eval\('
     PAGE2_DZ_PATTERN = r'break;case 15:(.*)</script>'
-    PAGE2_LINK_PATTERN = r"(?:if.*</a>\')?(?:eval\(\")?(.*?)eval\("
-    FINAL_LINK_PATTERN = r'parent.document.getElementById\(\'(\w{32})\'\)\).*?"(http://download[^"]+)" \+(\w+)\+ "([^"]+)">'
+    PAGE2_LINK_PATTERN = r"(\w+='';\w+=unescape.*?)eval\(\w+\);(\\\" href=[^\>]*>)?"
+    FINAL_LINK_PATTERN = r'parent.document.getElementById\(\'(\w{32})\'\).*(http://[^"]+)" \+(\w+)\+ "([^"]+)">'
 
     FILE_NAME_PATTERN = r'<META NAME="description" CONTENT="([^"]+)"/>'
     FILE_SIZE_PATTERN = r'<div style="font-size:14px;padding-top:12px;color:#777;">\(([0-9.]+) (kB|MB|GB)\)</div>'
     FILE_OFFLINE_PATTERN = r'class="error_msg_title"> Invalid or Deleted File. </div>'
 
+    def setup(self):
+        self.multiDL = False
+
     def process(self, pyfile):
-        self.html = self.load(pyfile.url, decode=True)
+        self.html = self.load(pyfile.url)
 
-        try:
-            pyfile.name = re.search(self.FILE_NAME_PATTERN, self.html).group(1)
-            found = re.search(self.FILE_SIZE_PATTERN, self.html)
+        found = re.search(self.FILE_NAME_PATTERN, self.html)
+        if not found: self.fail("Parse error (file name)")
+        pyfile.name = found.group(1)
+
+        found = re.search(self.FILE_SIZE_PATTERN, self.html)
+        if found:
             pyfile.size = float(found.group(1)) * 1024 ** {'kB': 1, 'MB': 2, 'GB': 3}[found.group(2)]
-        except Exception, e:
-            self.logError(e)
-            self.retry(3, 0, "Parse error - file info")
 
         self.handleFree()
 
     def handleFree(self):
+        found = re.search(self.RECAPTCHA_PATTERN, self.html)
+        if found:
+            captcha_action = re.search(self.PAGE1_ACTION_PATTERN, self.html).group(1)
+            captcha_key = found.group(1)
+            recaptcha = ReCaptcha(self)
+            captcha_challenge, captcha_response = recaptcha.challenge(captcha_key)
+            self.html = self.load(captcha_action, post = {
+                "recaptcha_challenge_field": captcha_challenge,
+                "recaptcha_response_field": captcha_response
+                })
+
         found = re.search(self.PAGE1_KEY_PATTERN, self.html)
         if found:
             result = self.js.eval(found.group(1))
             found = re.search(self.PAGE1_RESULT_PATTERN, result)
         else:
-            self.fail("Parse error - javascript")
+            self.retry(3, 0, "Parse error (KEY)")
 
-        param_dict = found.groupdict()
-        param_dict['r'] = re.search(self.PAGE1_PKR_PATTERN, self.html).group(1)
-        self.logDebug(param_dict)
-        key_func = found.group(1)
-        self.logDebug("KEY_FUNC: %s" % key_func)
+        try:
+            param_dict = found.groupdict()
+            param_dict['r'] = re.search(self.PAGE1_PKR_PATTERN, self.html).group(1)
+            self.logDebug(param_dict)
+            key_func = found.group(1)
+            self.logDebug("KEY_FUNC: %s" % key_func)
 
-        found = re.search(self.PAGE1_FUNCTION_PATTERN % key_func, self.html)
-        result = self.js.eval(found.group(1))
-        key_div = re.search(self.PAGE1_DIV_PATTERN, result).group(1)
-        self.logDebug("KEY_DIV: %s" % key_div)
+            found = re.search(self.PAGE1_FUNCTION_PATTERN % key_func, self.html)
+            result = self.js.eval(found.group(1))
+            key_div = re.search(self.PAGE1_DIV_PATTERN, result).group(1)
+            self.logDebug("KEY_DIV: %s" % key_div)
+        except Exception, e:
+            self.logError(e)
+            self.retry(3, 0, "Parse error (KEY DIV)")
 
         self.html = self.load("http://www.mediafire.com/dynamic/download.php", get=param_dict)
-        result = self.js.eval(re.search(self.PAGE2_VARS_PATTERN, self.html).group(1))
+        js_expr = replace_eval(re.search(self.PAGE2_VARS_PATTERN, self.html).group(1))
+        result = self.js.eval(js_expr)
         var_list = dict(re.findall("([^=]+)='([^']+)';", result))
 
-        page2_dz = re.search(self.PAGE2_DZ_PATTERN, self.html, re.DOTALL).group(1)
+        page2_dz = replace_eval(re.search(self.PAGE2_DZ_PATTERN, self.html, re.DOTALL).group(1))
 
         final_link = None
         for link_enc in re.finditer(self.PAGE2_LINK_PATTERN, page2_dz):
             #self.logDebug("LINK_ENC: %s..." % link_enc.group(1)[:20])
             try:
-                link_dec = self.js.eval(link_enc.group(1).replace(r"\'", r"'"))
-            except:
+                link_dec = self.js.eval(link_enc.group(1))
+            except Exception, e:
                 self.logError("Unable to decrypt link %s" % link_enc.group(1)[:20])
-                self.logDebug(link_enc.group(1).replace(r"\'", r"'"))
+                self.logError(e)
+                self.logDebug(link_enc.group(1))
                 continue
 
+            #self.logDebug("LINK_DEC: %s" % link_dec)
+            if link_enc.group(2): link_dec = link_dec + replace_eval(link_enc.group(2))
+
             found = re.search(self.FINAL_LINK_PATTERN, link_dec)
-            if found and found.group(1) == key_div:
-                final_link = found.group(2) + var_list[found.group(3)] + found.group(4)
-                break
+            if found:
+                if found.group(1) == key_div:
+                    final_link = found.group(2) + var_list[found.group(3)] + found.group(4)
+                    break
+            else:
+                self.logDebug("Link not found in %s..." % link_dec)
         else:
             self.fail("Final link not found")