Spare fixes

8 files changed, 99 insertions, 85 deletions

diff --git a/module/plugins/hoster/EuroshareEu.py b/module/plugins/hoster/EuroshareEu.py
index c4bd54667..deb138ec7 100644
--- a/module/plugins/hoster/EuroshareEu.py
+++ b/module/plugins/hoster/EuroshareEu.py
@@ -23,20 +23,20 @@ class EuroshareEu(SimpleHoster):
 
     LINK_FREE_PATTERN = r'<a href="(/file/\d+/[^/]*/download/)"><div class="downloadButton"'
 
-    ERR_PARDL_PATTERN         = r'<h2>Prebieha s.ahovanie</h2>|<p>Naraz je z jednej IP adresy mo.n. s.ahova. iba jeden s.bor'
-    ERR_NOT_LOGGED_IN_PATTERN = r'href="/customer-zone/login/"'
+    DL_LIMIT_PATTERN = r'<h2>Prebieha s.ahovanie</h2>|<p>Naraz je z jednej IP adresy mo.n. s.ahova. iba jeden s.bor'
+    ERROR_PATTERN    = r'href="/customer-zone/login/"'
 
     URL_REPLACEMENTS = [(r"(http://[^/]*\.)(sk|cz|hu|pl)/", r"\1eu/")]
 
 
     def handlePremium(self, pyfile):
-        if self.ERR_NOT_LOGGED_IN_PATTERN in self.html:
+        if self.ERROR_PATTERN in self.html:
             self.account.relogin(self.user)
             self.retry(reason=_("User not logged in"))
 
         self.link = pyfile.url.rstrip('/') + "/download/"
 
-        check = self.checkDownload({"login": re.compile(self.ERR_NOT_LOGGED_IN_PATTERN),
+        check = self.checkDownload({"login": re.compile(self.ERROR_PATTERN),
                                     "json" : re.compile(r'\{"status":"error".*?"message":"(.*?)"')})
 
         if check == "login" or (check == "json" and self.lastCheck.group(1) == "Access token expired"):
@@ -48,7 +48,7 @@ class EuroshareEu(SimpleHoster):
 
 
     def handleFree(self, pyfile):
-        if re.search(self.ERR_PARDL_PATTERN, self.html):
+        if re.search(self.DL_LIMIT_PATTERN, self.html):
             self.wait(5 * 60, 12, _("Download limit reached"))
 
         m = re.search(self.LINK_FREE_PATTERN, self.html)
@@ -58,11 +58,4 @@ class EuroshareEu(SimpleHoster):
         self.link = "http://euroshare.eu%s" % m.group(1)
 
 
-    def checkFile(self):
-        if self.checkDownload({"multi-dl": re.compile(self.ERR_PARDL_PATTERN)})
-            self.wait(5 * 60, 12, _("Download limit reached"))
-
-        return super(EuroshareEu, self).checkFile()
-
-
 getInfo = create_getInfo(EuroshareEu)
diff --git a/module/plugins/hoster/HighWayMe.py b/module/plugins/hoster/HighWayMe.py
index 9f39c21e8..dc7a9fc12 100644
--- a/module/plugins/hoster/HighWayMe.py
+++ b/module/plugins/hoster/HighWayMe.py
@@ -24,7 +24,7 @@ class HighWayMe(MultiHoster):
 
 
     def checkErrors(self):
-        if self.html.get('code') == 302:  #@NOTE: This is not working. It should by if 302 Moved Temporarily then ... But I don't now how to implement it.
+        if self.html.get('code') == 302:  #@NOTE: This is not working. It should by if 302 Moved Temporarily then... But I don't now how to implement it.
             self.account.relogin(self.user)
             self.retry()
 
diff --git a/module/plugins/hoster/OverLoadMe.py b/module/plugins/hoster/OverLoadMe.py
index bc3ca87c4..8ba310b52 100644
--- a/module/plugins/hoster/OverLoadMe.py
+++ b/module/plugins/hoster/OverLoadMe.py
@@ -40,12 +40,10 @@ class OverLoadMe(MultiHoster):
             self.logWarning(data['msg'])
             self.tempOffline()
         else:
+            self.link = data['downloadlink']
             if pyfile.name and pyfile.name.endswith('.tmp') and data['filename']:
                 pyfile.name = data['filename']
                 pyfile.size = parseFileSize(data['filesize'])
 
-            http_repl = ["http://", "https://"]
-            self.link = data['downloadlink'].replace(*http_repl if self.getConfig('ssl') else *http_repl[::-1])
-
 
 getInfo = create_getInfo(OverLoadMe)
diff --git a/module/plugins/hoster/YourfilesTo.py b/module/plugins/hoster/YourfilesTo.py
index 0f6ca49df..4d316eabf 100644
--- a/module/plugins/hoster/YourfilesTo.py
+++ b/module/plugins/hoster/YourfilesTo.py
@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 
-import reimport urllib
+import re
+import urllib
 
 from module.plugins.internal.Hoster import Hoster
 
diff --git a/module/plugins/internal/Captcha.py b/module/plugins/internal/Captcha.py
index 8dbc33da2..4629c9522 100644
--- a/module/plugins/internal/Captcha.py
+++ b/module/plugins/internal/Captcha.py
@@ -3,7 +3,6 @@
 from module.plugins.internal.Plugin import Plugin
 
 
-#@TODO: Extend (new) Plugin class; remove all `html` args
 class Captcha(Plugin):
     __name__    = "Captcha"
     __type__    = "captcha"
@@ -11,16 +10,15 @@ class Captcha(Plugin):
 
     __description__ = """Base captcha service plugin"""
     __license__     = "GPLv3"
-    __authors__     = [("pyLoad Team", "admin@pyload.org")]
-
-
-    key = None  #: last key detected
+    __authors__     = [("Walter Purcaro", "vuolter@gmail.com")]
 
 
     def __init__(self, plugin):
-        self.plugin = plugin
         super(Captcha, self).__init__(plugin.core)
 
+        self.plugin = plugin
+        self.key    = None  #: last key detected
+
 
     #@TODO: Recheck in 0.4.10
     def retrieve_key(self, html):
diff --git a/module/plugins/internal/Extractor.py b/module/plugins/internal/Extractor.py
index 1a98060d9..2aa26e64a 100644
--- a/module/plugins/internal/Extractor.py
+++ b/module/plugins/internal/Extractor.py
@@ -4,6 +4,7 @@ import os
 import re
 
 from module.PyFile import PyFile
+from module.plugins.internal.Plugin import Plugin
 
 
 class ArchiveError(Exception):
@@ -18,8 +19,9 @@ class PasswordError(Exception):
     pass
 
 
-class Extractor:
+class Extractor(Plugin):
     __name__    = "Extractor"
+    __type__    = "extractor"
     __version__ = "0.24"
 
     __description__ = """Base extractor plugin"""
@@ -46,7 +48,8 @@ class Extractor:
 
     @classmethod
     def isUsable(cls):
-        """ Check if system statisfy dependencies
+        """
+        Check if system statisfy dependencies
         :return: boolean
         """
         return None
@@ -54,7 +57,8 @@ class Extractor:
 
     @classmethod
     def getTargets(cls, files_ids):
-        """ Filter suited targets from list of filename id tuple list
+        """
+        Filter suited targets from list of filename id tuple list
         :param files_ids: List of filepathes
         :return: List of targets, id tuple list
         """
@@ -78,7 +82,7 @@ class Extractor:
                  delete='No',
                  keepbroken=False,
                  fid=None):
-        """ Initialize extractor for specific file """
+        """Initialize extractor for specific file"""
         self.manager      = manager
         self.filename     = filename
         self.out          = out
@@ -95,12 +99,13 @@ class Extractor:
 
 
     def init(self):
-        """ Initialize additional data structures """
+        """Initialize additional data structures"""
         pass
 
 
     def check(self):
-        """Quick Check by listing content of archive.
+        """
+        Quick Check by listing content of archive.
         Raises error if password is needed, integrity is questionable or else.
 
         :raises PasswordError
@@ -109,8 +114,10 @@ class Extractor:
         """
         raise NotImplementedError
 
+
     def verify(self):
-        """Testing with Extractors buildt-in method
+        """
+        Testing with Extractors buildt-in method
         Raises error if password is needed, integrity is questionable or else.
 
         :raises PasswordError
@@ -125,7 +132,8 @@ class Extractor:
 
 
     def extract(self, password=None):
-        """Extract the archive. Raise specific errors in case of failure.
+        """
+        Extract the archive. Raise specific errors in case of failure.
 
         :param progress: Progress function, call this to update status
         :param password password to use
@@ -138,7 +146,8 @@ class Extractor:
 
 
     def getDeleteFiles(self):
-        """Return list of files to delete, do *not* delete them here.
+        """
+        Return list of files to delete, do *not* delete them here.
 
         :return: List with paths of files to delete
         """
diff --git a/module/plugins/internal/Hoster.py b/module/plugins/internal/Hoster.py
index 834a200ac..40430c38d 100644
--- a/module/plugins/internal/Hoster.py
+++ b/module/plugins/internal/Hoster.py
@@ -178,11 +178,11 @@ class Hoster(Plugin):
         :param seconds: wait time in seconds
         :param reconnect: True if a reconnect would avoid wait time
         """
-        wait_time  = int(seconds) + 1
-        wait_until = time.time() + wait_time
+        wait_time  = max(int(seconds), 1)
+        wait_until = time.time() + wait_time + 1
 
         self.logDebug("Set waitUntil to: %f (previous: %f)" % (wait_until, self.pyfile.waitUntil),
-                      "Wait: %d seconds" % wait_time)
+                      "Wait: %d(+1) seconds" % wait_time)
 
         self.pyfile.waitUntil = wait_until
 
@@ -190,13 +190,13 @@ class Hoster(Plugin):
             self.setReconnect(reconnect)
 
 
-    def wait(self, seconds=None, reconnect=None):
+    def wait(self, seconds=0, reconnect=None):
         """
         Waits the time previously set
         """
         pyfile = self.pyfile
 
-        if seconds is not None:
+        if seconds > 0:
             self.setWait(seconds)
 
         if reconnect is not None:
@@ -284,7 +284,7 @@ class Hoster(Plugin):
             self.retries[id] = 0
 
         if 0 < max_tries <= self.retries[id]:
-            self.fail(reason or _("Max retries reached"), "retry")
+            self.fail(reason or _("Max retries reached"), _("retry"))
 
         self.wait(wait_time, False)
 
@@ -480,7 +480,7 @@ class Hoster(Plugin):
         return self.lastDownload
 
 
-    def checkDownload(self, rules, delete=True, file_size=None, size_tolerance=1000, read_size=100000):
+    def checkDownload(self, rules, delete=True, file_size=0, size_tolerance=1000, read_size=100000):
         """
         Checks the content of the last downloaded file, re match is saved to `lastCheck`
 
@@ -491,40 +491,52 @@ class Hoster(Plugin):
         :param read_size: amount of bytes to read from files
         :return: dictionary key of the first rule that matched
         """
+        do_delete = False
         lastDownload = fs_encode(self.lastDownload)
 
         if not self.lastDownload or not os.path.exists(lastDownload):
             self.lastDownload = ""
             self.fail(self.pyfile.error or _("No file downloaded"))
 
-        download_size = os.stat(lastDownload).st_size
+        try:
+            download_size = os.stat(lastDownload).st_size
+
+            if download_size < 1:
+                do_delete = True
+                self.fail(_("Empty file"))
+
+            elif file_size > 0:
+                diff = abs(file_size - download_size)
+
+                if diff > size_tolerance:
+                    do_delete = True
+                    self.fail(_("File size mismatch"))
+
+                elif diff != 0:
+                    self.logWarning(_("File size is not equal to expected size"))
 
-        if download_size < 1 or (file_size and abs(file_size - download_size) > size_tolerance):
-            if delete:
+            self.logDebug("Download Check triggered")
+
+            with open(lastDownload, "rb") as f:
+                content = f.read(read_size)
+
+            # produces encoding errors, better log to other file in the future?
+            # self.logDebug("Content: %s" % content)
+            for name, rule in rules.iteritems():
+                if isinstance(rule, basestring):
+                    if rule in content:
+                        do_delete = True
+                        return name
+
+                elif hasattr(rule, "search"):
+                    m = rule.search(content)
+                    if m:
+                        do_delete = True
+                        self.lastCheck = m
+                        return name
+        finally:
+            if delete and do_delete:
                 os.remove(lastDownload)
-            self.fail(_("Empty file"))
-
-        self.logDebug("Download Check triggered")
-
-        with open(lastDownload, "rb") as f:
-            content = f.read(read_size)
-
-        # produces encoding errors, better log to other file in the future?
-        # self.logDebug("Content: %s" % content)
-        for name, rule in rules.iteritems():
-            if isinstance(rule, basestring):
-                if rule in content:
-                    if delete:
-                        os.remove(lastDownload)
-                    return name
-
-            elif hasattr(rule, "search"):
-                m = rule.search(content)
-                if m:
-                    if delete:
-                        os.remove(lastDownload)
-                    self.lastCheck = m
-                    return name
 
 
     def directLink(self, url, follow_location=None):
diff --git a/module/plugins/internal/OCR.py b/module/plugins/internal/OCR.py
index 1782e17f0..2d41ab39e 100644
--- a/module/plugins/internal/OCR.py
+++ b/module/plugins/internal/OCR.py
@@ -11,12 +11,13 @@ except ImportError:
 import logging
 import os
 import subprocess
-#import tempfile
+# import tempfile
 
+from module.plugins.internal.Plugin import Plugin
 from module.utils import save_join as fs_join
 
 
-class OCR(object):
+class OCR(Plugin):
     __name__    = "OCR"
     __type__    = "ocr"
     __version__ = "0.11"
@@ -37,7 +38,7 @@ class OCR(object):
 
 
     def deactivate(self):
-        """delete all tmp images"""
+        """Delete all tmp images"""
         pass
 
 
@@ -48,21 +49,21 @@ class OCR(object):
     def run(self, command):
         """Run a command"""
 
-        popen = subprocess.Popen(command, bufsize = -1, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        popen = subprocess.Popen(command, bufsize=-1, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
         popen.wait()
-        output = popen.stdout.read() +" | "+ popen.stderr.read()
+        output = popen.stdout.read() + " | " + popen.stderr.read()
         popen.stdout.close()
         popen.stderr.close()
         self.logger.debug("Tesseract ReturnCode %s Output: %s" % (popen.returncode, output))
 
 
-    def run_tesser(self, subset=False, digits=True, lowercase=True, uppercase=True):
-        #tmpTif = tempfile.NamedTemporaryFile(suffix=".tif")
+    def run_tesser(self, subset=False, digits=True, lowercase=True, uppercase=True, pagesegmode=None):
+        # tmpTif = tempfile.NamedTemporaryFile(suffix=".tif")
         try:
             tmpTif = open(fs_join("tmp", "tmpTif_%s.tif" % self.__name__), "wb")
             tmpTif.close()
 
-            #tmpTxt = tempfile.NamedTemporaryFile(suffix=".txt")
+            # tmpTxt = tempfile.NamedTemporaryFile(suffix=".txt")
             tmpTxt = open(fs_join("tmp", "tmpTxt_%s.txt" % self.__name__), "wb")
             tmpTxt.close()
 
@@ -78,10 +79,13 @@ class OCR(object):
         else:
             tessparams = ["tesseract"]
 
-        tessparams.extend( [os.path.abspath(tmpTif.name), os.path.abspath(tmpTxt.name).replace(".txt", "")] )
+        tessparams.extend([os.path.abspath(tmpTif.name), os.path.abspath(tmpTxt.name).replace(".txt", "")])
+
+        if pagesegmode:
+            tessparams.extend(["-psm", str(pagesegmode)])
 
         if subset and (digits or lowercase or uppercase):
-            #tmpSub = tempfile.NamedTemporaryFile(suffix=".subset")
+            # tmpSub = tempfile.NamedTemporaryFile(suffix=".subset")
             with open(fs_join("tmp", "tmpSub_%s.subset" % self.__name__), "wb") as tmpSub:
                 tmpSub.write("tessedit_char_whitelist ")
 
@@ -151,11 +155,11 @@ class OCR(object):
                 count = 0
 
                 try:
-                    if pixels[x-1, y-1] != 255:
+                    if pixels[x - 1, y - 1] != 255:
                         count += 1
-                    if pixels[x-1, y] != 255:
+                    if pixels[x - 1, y] != 255:
                         count += 1
-                    if pixels[x-1, y + 1] != 255:
+                    if pixels[x - 1, y + 1] != 255:
                         count += 1
                     if pixels[x, y + 1] != 255:
                         count += 1
@@ -163,19 +167,19 @@ class OCR(object):
                         count += 1
                     if pixels[x + 1, y] != 255:
                         count += 1
-                    if pixels[x + 1, y-1] != 255:
+                    if pixels[x + 1, y - 1] != 255:
                         count += 1
-                    if pixels[x, y-1] != 255:
+                    if pixels[x, y - 1] != 255:
                         count += 1
                 except Exception:
                     pass
 
-        # not enough neighbors are dark pixels so mark this pixel
-            # to be changed to white
+                # not enough neighbors are dark pixels so mark this pixel
+                # to be changed to white
                 if count < allowed:
                     pixels[x, y] = 1
 
-            # second pass: this time set all 1's to 255 (white)
+        # second pass: this time set all 1's to 255 (white)
         for x in xrange(w):
             for y in xrange(h):
                 if pixels[x, y] == 1:
@@ -185,7 +189,7 @@ class OCR(object):
 
 
     def derotate_by_average(self):
-        """rotate by checking each angle and guess most suitable"""
+        """Rotate by checking each angle and guess most suitable"""
 
         w, h = self.image.size
         pixels = self.pixels
@@ -211,7 +215,6 @@ class OCR(object):
                     if pixels[x, y] == 0:
                         pixels[x, y] = 255
 
-
             count = {}
 
             for x in xrange(w):