untested WIP.

core: update pysubs2
providers: opensubtitles: actually use sessions (they're broken) for checking for token state

Contents/Code/support/config.py

@@ -15,7 +15,8 @@ import subliminal
 import subliminal_patch
 import subzero.constants
 import lib
-from subliminal.exceptions import ServiceUnavailable, DownloadLimitExceeded, AuthenticationError
+from subliminal.exceptions import ServiceUnavailable, DownloadLimitExceeded, AuthenticationError, \
+    DownloadLimitPerDayExceeded
 from subliminal_patch.core import is_windows_special_path
 from whichdb import whichdb
 
@@ -61,12 +62,14 @@ def int_or_default(s, default):
         return default
 
 
-VALID_THROTTLE_EXCEPTIONS = (TooManyRequests, DownloadLimitExceeded, ServiceUnavailable, APIThrottled)
+VALID_THROTTLE_EXCEPTIONS = (TooManyRequests, DownloadLimitExceeded, DownloadLimitPerDayExceeded,
+                             ServiceUnavailable, APIThrottled)
 
 PROVIDER_THROTTLE_MAP = {
     "default": {
         TooManyRequests: (datetime.timedelta(hours=1), "1 hour"),
         DownloadLimitExceeded: (datetime.timedelta(hours=3), "3 hours"),
+        DownloadLimitPerDayExceeded: (datetime.timedelta(hours=4), "4 hours"),
         ServiceUnavailable: (datetime.timedelta(minutes=20), "20 minutes"),
         APIThrottled: (datetime.timedelta(minutes=10), "10 minutes"),
         AuthenticationError: (datetime.timedelta(hours=2), "2 hours"),
@@ -873,6 +876,7 @@ class Config(object):
 
         provider_settings = {'addic7ed': {'username': Prefs['provider.addic7ed.username'],
                                           'password': Prefs['provider.addic7ed.password'],
+                                          'is_vip': cast_bool(Prefs['provider.addic7ed.is_vip']),
                                           },
                              'opensubtitles': {'username': Prefs['provider.opensubtitles.username'],
                                                'password': Prefs['provider.opensubtitles.password'],

Contents/Code/support/tasks.py

@@ -171,12 +171,15 @@ class SubtitleListingMixin(object):
                     else:
                         s.wrong_season_ep = True
 
+            orig_matches = matches.copy()
+            score, score_without_hash = compute_score(matches, s, video, hearing_impaired=use_hearing_impaired)
+
             unsorted_subtitles.append(
-                (s, compute_score(matches, s, video, hearing_impaired=use_hearing_impaired), matches))
-        scored_subtitles = sorted(unsorted_subtitles, key=operator.itemgetter(1), reverse=True)
+                (s, score, score_without_hash, matches, orig_matches))
+        scored_subtitles = sorted(unsorted_subtitles, key=operator.itemgetter(1, 2), reverse=True)
 
         subtitles = []
-        for subtitle, score, matches in scored_subtitles:
+        for subtitle, score, score_without_hash, matches, orig_matches in scored_subtitles:
             # check score
             if score < min_score and not subtitle.wrong_series:
                 Log.Info(u'%s: Score %d is below min_score (%d)', self.name, score, min_score)

Contents/DefaultPrefs.json

@@ -375,6 +375,12 @@
     "default": "",
     "secure": "true"
   },
+  {
+    "id": "provider.addic7ed.is_vip",
+    "label": "Addic7ed VIP? (80 vs 40 downloads per day)",
+    "type": "bool",
+    "default": "false"
+  },
   {
     "id": "provider.addic7ed.boost_by2",
     "label": "Addic7ed: boost score (if requirements met)",

Contents/Info.plist

@@ -13,7 +13,7 @@
         <key>CFBundleSignature</key>
         <string>????</string>
         <key>CFBundleVersion</key>
-        <string>2.6.5.3217</string>
+        <string>2.6.5.3237</string>
         <key>PlexFrameworkVersion</key>
         <string>2</string>
         <key>PlexPluginClass</key>
@@ -23,7 +23,7 @@
         <key>PlexPluginConsoleLogging</key>
         <string>0</string>
         <key>PlexPluginDevMode</key>
-        <string>0</string>
+        <string>1</string>
          <key>PlexPluginCodePolicy</key>
             <!-- this allows channels to access some python methods which are otherwise blocked, as well as import external code libraries, and interact with the PMS HTTP API -->
             <string>Elevated</string>
@@ -32,7 +32,7 @@
 
 &lt;h1&gt;Sub-Zero for Plex&lt;/h1&gt;&lt;i&gt;Subtitles done right&lt;/i&gt;
 
-Version 2.6.5.3217
+Version 2.6.5.3237 DEV
 
 Originally based on @bramwalet's awesome &lt;a href=&quot;https://github.com/bramwalet/Subliminal.bundle&quot;&gt;Subliminal.bundle&lt;/a&gt;
 

Contents/Libraries/Shared/backports/__init__.py

@@ -0,0 +1 @@
+__path__ = __import__('pkgutil').extend_path(__path__, __name__)

Contents/Libraries/Shared/backports/functools_lru_cache.py

@@ -0,0 +1,196 @@
+from __future__ import absolute_import
+
+import functools
+from collections import namedtuple
+from threading import RLock
+
+_CacheInfo = namedtuple("CacheInfo", ["hits", "misses", "maxsize", "currsize"])
+
+
+@functools.wraps(functools.update_wrapper)
+def update_wrapper(
+    wrapper,
+    wrapped,
+    assigned=functools.WRAPPER_ASSIGNMENTS,
+    updated=functools.WRAPPER_UPDATES,
+):
+    """
+    Patch two bugs in functools.update_wrapper.
+    """
+    # workaround for http://bugs.python.org/issue3445
+    assigned = tuple(attr for attr in assigned if hasattr(wrapped, attr))
+    wrapper = functools.update_wrapper(wrapper, wrapped, assigned, updated)
+    # workaround for https://bugs.python.org/issue17482
+    wrapper.__wrapped__ = wrapped
+    return wrapper
+
+
+class _HashedSeq(list):
+    __slots__ = 'hashvalue'
+
+    def __init__(self, tup, hash=hash):
+        self[:] = tup
+        self.hashvalue = hash(tup)
+
+    def __hash__(self):
+        return self.hashvalue
+
+
+def _make_key(
+    args,
+    kwds,
+    typed,
+    kwd_mark=(object(),),
+    fasttypes=set([int, str, frozenset, type(None)]),
+    sorted=sorted,
+    tuple=tuple,
+    type=type,
+    len=len,
+):
+    'Make a cache key from optionally typed positional and keyword arguments'
+    key = args
+    if kwds:
+        sorted_items = sorted(kwds.items())
+        key += kwd_mark
+        for item in sorted_items:
+            key += item
+    if typed:
+        key += tuple(type(v) for v in args)
+        if kwds:
+            key += tuple(type(v) for k, v in sorted_items)
+    elif len(key) == 1 and type(key[0]) in fasttypes:
+        return key[0]
+    return _HashedSeq(key)
+
+
+def lru_cache(maxsize=100, typed=False):
+    """Least-recently-used cache decorator.
+
+    If *maxsize* is set to None, the LRU features are disabled and the cache
+    can grow without bound.
+
+    If *typed* is True, arguments of different types will be cached separately.
+    For example, f(3.0) and f(3) will be treated as distinct calls with
+    distinct results.
+
+    Arguments to the cached function must be hashable.
+
+    View the cache statistics named tuple (hits, misses, maxsize, currsize) with
+    f.cache_info().  Clear the cache and statistics with f.cache_clear().
+    Access the underlying function with f.__wrapped__.
+
+    See:  http://en.wikipedia.org/wiki/Cache_algorithms#Least_Recently_Used
+
+    """
+
+    # Users should only access the lru_cache through its public API:
+    #       cache_info, cache_clear, and f.__wrapped__
+    # The internals of the lru_cache are encapsulated for thread safety and
+    # to allow the implementation to change (including a possible C version).
+
+    def decorating_function(user_function):
+
+        cache = dict()
+        stats = [0, 0]  # make statistics updateable non-locally
+        HITS, MISSES = 0, 1  # names for the stats fields
+        make_key = _make_key
+        cache_get = cache.get  # bound method to lookup key or return None
+        _len = len  # localize the global len() function
+        lock = RLock()  # because linkedlist updates aren't threadsafe
+        root = []  # root of the circular doubly linked list
+        root[:] = [root, root, None, None]  # initialize by pointing to self
+        nonlocal_root = [root]  # make updateable non-locally
+        PREV, NEXT, KEY, RESULT = 0, 1, 2, 3  # names for the link fields
+
+        if maxsize == 0:
+
+            def wrapper(*args, **kwds):
+                # no caching, just do a statistics update after a successful call
+                result = user_function(*args, **kwds)
+                stats[MISSES] += 1
+                return result
+
+        elif maxsize is None:
+
+            def wrapper(*args, **kwds):
+                # simple caching without ordering or size limit
+                key = make_key(args, kwds, typed)
+                result = cache_get(
+                    key, root
+                )  # root used here as a unique not-found sentinel
+                if result is not root:
+                    stats[HITS] += 1
+                    return result
+                result = user_function(*args, **kwds)
+                cache[key] = result
+                stats[MISSES] += 1
+                return result
+
+        else:
+
+            def wrapper(*args, **kwds):
+                # size limited caching that tracks accesses by recency
+                key = make_key(args, kwds, typed) if kwds or typed else args
+                with lock:
+                    link = cache_get(key)
+                    if link is not None:
+                        # record recent use of the key by moving it
+                        # to the front of the list
+                        root, = nonlocal_root
+                        link_prev, link_next, key, result = link
+                        link_prev[NEXT] = link_next
+                        link_next[PREV] = link_prev
+                        last = root[PREV]
+                        last[NEXT] = root[PREV] = link
+                        link[PREV] = last
+                        link[NEXT] = root
+                        stats[HITS] += 1
+                        return result
+                result = user_function(*args, **kwds)
+                with lock:
+                    root, = nonlocal_root
+                    if key in cache:
+                        # getting here means that this same key was added to the
+                        # cache while the lock was released.  since the link
+                        # update is already done, we need only return the
+                        # computed result and update the count of misses.
+                        pass
+                    elif _len(cache) >= maxsize:
+                        # use the old root to store the new key and result
+                        oldroot = root
+                        oldroot[KEY] = key
+                        oldroot[RESULT] = result
+                        # empty the oldest link and make it the new root
+                        root = nonlocal_root[0] = oldroot[NEXT]
+                        oldkey = root[KEY]
+                        root[KEY] = root[RESULT] = None
+                        # now update the cache dictionary for the new links
+                        del cache[oldkey]
+                        cache[key] = oldroot
+                    else:
+                        # put result in a new link at the front of the list
+                        last = root[PREV]
+                        link = [last, root, key, result]
+                        last[NEXT] = root[PREV] = cache[key] = link
+                    stats[MISSES] += 1
+                return result
+
+        def cache_info():
+            """Report cache statistics"""
+            with lock:
+                return _CacheInfo(stats[HITS], stats[MISSES], maxsize, len(cache))
+
+        def cache_clear():
+            """Clear the cache and cache statistics"""
+            with lock:
+                cache.clear()
+                root = nonlocal_root[0]
+                root[:] = [root, root, None, None]
+                stats[:] = [0, 0]
+
+        wrapper.__wrapped__ = user_function
+        wrapper.cache_info = cache_info
+        wrapper.cache_clear = cache_clear
+        return update_wrapper(wrapper, user_function)
+
+    return decorating_function

Contents/Libraries/Shared/cloudscraper/__init__.py

@@ -2,6 +2,20 @@ import logging
 import re
 import sys
 import ssl
+import requests
+
+try:
+    import copyreg
+except ImportError:
+    import copy_reg as copyreg
+
+try:
+    from HTMLParser import HTMLParser
+except ImportError:
+    if sys.version_info >= (3, 4):
+        import html
+    else:
+        from html.parser import HTMLParser
 
 from copy import deepcopy
 from time import sleep
@@ -9,9 +23,17 @@ from collections import OrderedDict
 
 from requests.sessions import Session
 from requests.adapters import HTTPAdapter
-from requests.packages.urllib3.util.ssl_ import create_urllib3_context
+
+from .exceptions import (
+    CloudflareLoopProtection,
+    CloudflareCode1020,
+    CloudflareIUAMError,
+    CloudflareReCaptchaError,
+    CloudflareReCaptchaProvider
+)
 
 from .interpreters import JavaScriptInterpreter
+from .reCaptcha import reCaptcha
 from .user_agent import User_Agent
 
 try:
@@ -25,219 +47,540 @@ except ImportError:
     pass
 
 try:
-    from urlparse import urlparse
-    from urlparse import urlunparse
+    from urlparse import urlparse, urljoin
 except ImportError:
-    from urllib.parse import urlparse
-    from urllib.parse import urlunparse
+    from urllib.parse import urlparse, urljoin
 
-##########################################################################################################################################################
 
-__version__ = '1.1.9'
+# ------------------------------------------------------------------------------- #
 
-BUG_REPORT = 'Cloudflare may have changed their technique, or there may be a bug in the script.'
+__version__ = '1.2.31'
 
-##########################################################################################################################################################
+# ------------------------------------------------------------------------------- #
 
 
 class CipherSuiteAdapter(HTTPAdapter):
 
-    def __init__(self, cipherSuite=None, **kwargs):
-        self.cipherSuite = cipherSuite
+    __attrs__ = [
+        'ssl_context',
+        'max_retries',
+        'config',
+        '_pool_connections',
+        '_pool_maxsize',
+        '_pool_block'
+    ]
 
-        if hasattr(ssl, 'PROTOCOL_TLS'):
-            self.ssl_context = create_urllib3_context(
-                ssl_version=getattr(ssl, 'PROTOCOL_TLSv1_3', ssl.PROTOCOL_TLSv1_2),
-                ciphers=self.cipherSuite
-            )
-        else:
-            self.ssl_context = create_urllib3_context(ssl_version=ssl.PROTOCOL_TLSv1)
+    def __init__(self, *args, **kwargs):
+        self.ssl_context = kwargs.pop('ssl_context', None)
+        self.cipherSuite = kwargs.pop('cipherSuite', None)
+
+        if not self.ssl_context:
+            self.ssl_context = ssl.create_default_context(ssl.Purpose.SERVER_AUTH)
+            self.ssl_context.set_ciphers(self.cipherSuite)
+            self.ssl_context.options |= (ssl.OP_NO_SSLv2 | ssl.OP_NO_SSLv3 | ssl.OP_NO_TLSv1 | ssl.OP_NO_TLSv1_1)
 
         super(CipherSuiteAdapter, self).__init__(**kwargs)
 
-    ##########################################################################################################################################################
+    # ------------------------------------------------------------------------------- #
 
     def init_poolmanager(self, *args, **kwargs):
         kwargs['ssl_context'] = self.ssl_context
         return super(CipherSuiteAdapter, self).init_poolmanager(*args, **kwargs)
 
-    ##########################################################################################################################################################
+    # ------------------------------------------------------------------------------- #
 
     def proxy_manager_for(self, *args, **kwargs):
         kwargs['ssl_context'] = self.ssl_context
         return super(CipherSuiteAdapter, self).proxy_manager_for(*args, **kwargs)
 
-##########################################################################################################################################################
+# ------------------------------------------------------------------------------- #
 
 
 class CloudScraper(Session):
+
     def __init__(self, *args, **kwargs):
         self.debug = kwargs.pop('debug', False)
         self.delay = kwargs.pop('delay', None)
-        self.interpreter = kwargs.pop('interpreter', 'js2py')
-        self.allow_brotli = kwargs.pop('allow_brotli', True if 'brotli' in sys.modules.keys() else False)
-        self.cipherSuite = None
+        self.cipherSuite = kwargs.pop('cipherSuite', None)
+        self.interpreter = kwargs.pop('interpreter', 'native')
+        self.recaptcha = kwargs.pop('recaptcha', {})
+        self.allow_brotli = kwargs.pop(
+            'allow_brotli',
+            True if 'brotli' in sys.modules.keys() else False
+        )
+
+        self.user_agent = User_Agent(
+            allow_brotli=self.allow_brotli,
+            browser=kwargs.pop('browser', None)
+        )
+
+        self._solveDepthCnt = 0
+        self.solveDepth = kwargs.pop('solveDepth', 3)
 
         super(CloudScraper, self).__init__(*args, **kwargs)
 
+        # pylint: disable=E0203
         if 'requests' in self.headers['User-Agent']:
+            # ------------------------------------------------------------------------------- #
             # Set a random User-Agent if no custom User-Agent has been set
-            self.headers = User_Agent(allow_brotli=self.allow_brotli).headers
+            # ------------------------------------------------------------------------------- #
+            self.headers = self.user_agent.headers
+            if not self.cipherSuite:
+                self.cipherSuite = self.user_agent.cipherSuite
 
-        self.mount('https://', CipherSuiteAdapter(self.loadCipherSuite()))
+        if isinstance(self.cipherSuite, list):
+            self.cipherSuite = ':'.join(self.cipherSuite)
 
-    ##########################################################################################################################################################
+        self.mount(
+            'https://',
+            CipherSuiteAdapter(
+                cipherSuite=self.cipherSuite
+            )
+        )
+
+        # purely to allow us to pickle dump
+        copyreg.pickle(ssl.SSLContext, lambda obj: (obj.__class__, (obj.protocol,)))
+
+    # ------------------------------------------------------------------------------- #
+    # Allow us to pickle our session back with all variables
+    # ------------------------------------------------------------------------------- #
+
+    def __getstate__(self):
+        return self.__dict__
+
+    # ------------------------------------------------------------------------------- #
+    # Raise an Exception with no stacktrace and reset depth counter.
+    # ------------------------------------------------------------------------------- #
+
+    def simpleException(self, exception, msg):
+        self._solveDepthCnt = 0
+        sys.tracebacklimit = 0
+        raise exception(msg)
+
+    # ------------------------------------------------------------------------------- #
+    # debug the request via the response
+    # ------------------------------------------------------------------------------- #
 
     @staticmethod
     def debugRequest(req):
         try:
             print(dump.dump_all(req).decode('utf-8'))
-        except:  # noqa
-            pass
+        except ValueError as e:
+            print("Debug Error: {}".format(getattr(e, 'message', e)))
 
-    ##########################################################################################################################################################
+    # ------------------------------------------------------------------------------- #
+    # Unescape / decode html entities
+    # ------------------------------------------------------------------------------- #
 
-    def loadCipherSuite(self):
-        if self.cipherSuite:
-            return self.cipherSuite
+    @staticmethod
+    def unescape(html_text):
+        if sys.version_info >= (3, 0):
+            if sys.version_info >= (3, 4):
+                return html.unescape(html_text)
 
-        self.cipherSuite = ''
+            return HTMLParser().unescape(html_text)
 
-        if hasattr(ssl, 'PROTOCOL_TLS'):
-            ciphers = [
-                'ECDHE-ECDSA-AES128-GCM-SHA256', 'ECDHE-RSA-AES128-GCM-SHA256', 'ECDHE-ECDSA-AES256-GCM-SHA384',
-                'ECDHE-RSA-AES256-GCM-SHA384', 'ECDHE-ECDSA-CHACHA20-POLY1305-SHA256', 'ECDHE-RSA-CHACHA20-POLY1305-SHA256',
-                'ECDHE-RSA-AES128-CBC-SHA', 'ECDHE-RSA-AES256-CBC-SHA', 'RSA-AES128-GCM-SHA256', 'RSA-AES256-GCM-SHA384',
-                'ECDHE-RSA-AES128-GCM-SHA256', 'RSA-AES256-SHA', '3DES-EDE-CBC'
-            ]
+        return HTMLParser().unescape(html_text)
 
-            if hasattr(ssl, 'PROTOCOL_TLSv1_3'):
-                ciphers.insert(0, ['GREASE_3A', 'GREASE_6A', 'AES128-GCM-SHA256', 'AES256-GCM-SHA256', 'AES256-GCM-SHA384', 'CHACHA20-POLY1305-SHA256'])
+    # ------------------------------------------------------------------------------- #
+    # Decode Brotli on older versions of urllib3 manually
+    # ------------------------------------------------------------------------------- #
 
-            ctx = ssl.SSLContext(getattr(ssl, 'PROTOCOL_TLSv1_3', ssl.PROTOCOL_TLSv1_2))
-
-            for cipher in ciphers:
-                try:
-                    ctx.set_ciphers(cipher)
-                    self.cipherSuite = '{}:{}'.format(self.cipherSuite, cipher).rstrip(':')
-                except ssl.SSLError:
-                    pass
-
-        return self.cipherSuite
-
-    ##########################################################################################################################################################
-
-    def request(self, method, url, *args, **kwargs):
-        ourSuper = super(CloudScraper, self)
-        resp = ourSuper.request(method, url, *args, **kwargs)
-
-        if resp.headers.get('Content-Encoding') == 'br':
+    def decodeBrotli(self, resp):
+        if requests.packages.urllib3.__version__ < '1.25.1' and resp.headers.get('Content-Encoding') == 'br':
             if self.allow_brotli and resp._content:
                 resp._content = brotli.decompress(resp.content)
             else:
-                logging.warning('Brotli content detected, But option is disabled, we will not continue.')
-                return resp
+                logging.warning(
+                    'You\'re running urllib3 {}, Brotli content detected, '
+                    'Which requires manual decompression, '
+                    'But option allow_brotli is set to False, '
+                    'We will not continue to decompress.'.format(requests.packages.urllib3.__version__)
+                )
 
+        return resp
+
+    # ------------------------------------------------------------------------------- #
+    # Our hijacker request function
+    # ------------------------------------------------------------------------------- #
+
+    def request(self, method, url, *args, **kwargs):
+        # pylint: disable=E0203
+        if kwargs.get('proxies') and kwargs.get('proxies') != self.proxies:
+            self.proxies = kwargs.get('proxies')
+
+        resp = self.decodeBrotli(
+            super(CloudScraper, self).request(method, url, *args, **kwargs)
+        )
+
+        # ------------------------------------------------------------------------------- #
         # Debug request
+        # ------------------------------------------------------------------------------- #
+
         if self.debug:
             self.debugRequest(resp)
 
         # Check if Cloudflare anti-bot is on
-        if self.isChallengeRequest(resp):
-            if resp.request.method != 'GET':
-                # Work around if the initial request is not a GET,
-                # Supersede with a GET then re-request the original METHOD.
-                self.request('GET', resp.url)
-                resp = ourSuper.request(method, url, *args, **kwargs)
-            else:
-                # Solve Challenge
-                resp = self.sendChallengeResponse(resp, **kwargs)
+        if self.is_Challenge_Request(resp):
+            # ------------------------------------------------------------------------------- #
+            # Try to solve the challenge and send it back
+            # ------------------------------------------------------------------------------- #
+
+            if self._solveDepthCnt >= self.solveDepth:
+                _ = self._solveDepthCnt
+                self.simpleException(
+                    CloudflareLoopProtection,
+                    "!!Loop Protection!! We have tried to solve {} time(s) in a row.".format(_)
+                )
+
+            self._solveDepthCnt += 1
+
+            resp = self.Challenge_Response(resp, **kwargs)
+        else:
+            if not resp.is_redirect and resp.status_code not in [429, 503]:
+                self._solveDepthCnt = 0
 
         return resp
 
-    ##########################################################################################################################################################
+    # ------------------------------------------------------------------------------- #
+    # check if the response contains a valid Cloudflare challenge
+    # ------------------------------------------------------------------------------- #
 
     @staticmethod
-    def isChallengeRequest(resp):
-        if resp.headers.get('Server', '').startswith('cloudflare'):
-            if b'why_captcha' in resp.content or b'/cdn-cgi/l/chk_captcha' in resp.content:
-                raise ValueError('Captcha')
-
+    def is_IUAM_Challenge(resp):
+        try:
             return (
-                resp.status_code in [429, 503]
-                and all(s in resp.content for s in [b'jschl_vc', b'jschl_answer'])
+                resp.headers.get('Server', '').startswith('cloudflare')
+                and resp.status_code in [429, 503]
+                and re.search(
+                    r'action="/.*?__cf_chl_jschl_tk__=\S+".*?name="jschl_vc"\svalue=.*?',
+                    resp.text,
+                    re.M | re.DOTALL
+                )
             )
+        except AttributeError:
+            pass
 
         return False
 
-    ##########################################################################################################################################################
-
-    def sendChallengeResponse(self, resp, **original_kwargs):
-        body = resp.text
-
-        # Cloudflare requires a delay before solving the challenge
-        if not self.delay:
-            try:
-                delay = float(re.search(r'submit\(\);\r?\n\s*},\s*([0-9]+)', body).group(1)) / float(1000)
-                if isinstance(delay, (int, float)):
-                    self.delay = delay
-            except:  # noqa
-                pass
-
-        sleep(self.delay)
-
-        parsed_url = urlparse(resp.url)
-        domain = parsed_url.netloc
-        submit_url = '{}://{}/cdn-cgi/l/chk_jschl'.format(parsed_url.scheme, domain)
-
-        cloudflare_kwargs = deepcopy(original_kwargs)
+    # ------------------------------------------------------------------------------- #
+    # check if the response contains a valid Cloudflare reCaptcha challenge
+    # ------------------------------------------------------------------------------- #
 
+    @staticmethod
+    def is_reCaptcha_Challenge(resp):
         try:
-            params = OrderedDict()
-
-            s = re.search(r'name="s"\svalue="(?P<s_value>[^"]+)', body)
-            if s:
-                params['s'] = s.group('s_value')
-
-            params.update(
-                [
-                    ('jschl_vc', re.search(r'name="jschl_vc" value="(\w+)"', body).group(1)),
-                    ('pass', re.search(r'name="pass" value="(.+?)"', body).group(1))
-                ]
-            )
-
-            params = cloudflare_kwargs.setdefault('params', params)
-
-        except Exception as e:
-            raise ValueError('Unable to parse Cloudflare anti-bots page: {} {}'.format(e.message, BUG_REPORT))
-
-        # Solve the Javascript challenge
-        params['jschl_answer'] = JavaScriptInterpreter.dynamicImport(self.interpreter).solveChallenge(body, domain)
-
-        # Requests transforms any request into a GET after a redirect,
-        # so the redirect has to be handled manually here to allow for
-        # performing other types of requests even as the first request.
-
-        cloudflare_kwargs['allow_redirects'] = False
-
-        redirect = self.request(resp.request.method, submit_url, **cloudflare_kwargs)
-        redirect_location = urlparse(redirect.headers['Location'])
-        if not redirect_location.netloc:
-            redirect_url = urlunparse(
-                (
-                    parsed_url.scheme,
-                    domain,
-                    redirect_location.path,
-                    redirect_location.params,
-                    redirect_location.query,
-                    redirect_location.fragment
+            return (
+                resp.headers.get('Server', '').startswith('cloudflare')
+                and resp.status_code == 403
+                and re.search(
+                    r'action="/.*?__cf_chl_captcha_tk__=\S+".*?data\-sitekey=.*?',
+                    resp.text,
+                    re.M | re.DOTALL
                 )
             )
-            return self.request(resp.request.method, redirect_url, **original_kwargs)
+        except AttributeError:
+            pass
 
-        return self.request(resp.request.method, redirect.headers['Location'], **original_kwargs)
+        return False
 
-    ##########################################################################################################################################################
+    # ------------------------------------------------------------------------------- #
+    # check if the response contains Firewall 1020 Error
+    # ------------------------------------------------------------------------------- #
+
+    @staticmethod
+    def is_Firewall_Blocked(resp):
+        try:
+            return (
+                resp.headers.get('Server', '').startswith('cloudflare')
+                and resp.status_code == 403
+                and re.search(
+                    r'<span class="cf-error-code">1020</span>',
+                    resp.text,
+                    re.M | re.DOTALL
+                )
+            )
+        except AttributeError:
+            pass
+
+        return False
+
+    # ------------------------------------------------------------------------------- #
+    # Wrapper for is_reCaptcha_Challenge, is_IUAM_Challenge, is_Firewall_Blocked
+    # ------------------------------------------------------------------------------- #
+
+    def is_Challenge_Request(self, resp):
+        if self.is_Firewall_Blocked(resp):
+            self.simpleException(
+                CloudflareCode1020,
+                'Cloudflare has blocked this request (Code 1020 Detected).'
+            )
+
+        if self.is_reCaptcha_Challenge(resp) or self.is_IUAM_Challenge(resp):
+            return True
+
+        return False
+
+    # ------------------------------------------------------------------------------- #
+    # Try to solve cloudflare javascript challenge.
+    # ------------------------------------------------------------------------------- #
+
+    def IUAM_Challenge_Response(self, body, url, interpreter):
+        try:
+            formPayload = re.search(
+                r'<form (?P<form>id="challenge-form" action="(?P<challengeUUID>.*?'
+                r'__cf_chl_jschl_tk__=\S+)"(.*?)</form>)',
+                body,
+                re.M | re.DOTALL
+            ).groupdict()
+
+            if not all(key in formPayload for key in ['form', 'challengeUUID']):
+                self.simpleException(
+                    CloudflareIUAMError,
+                    "Cloudflare IUAM detected, unfortunately we can't extract the parameters correctly."
+                )
+
+            payload = OrderedDict(
+                re.findall(
+                    r'name="(r|jschl_vc|pass)"\svalue="(.*?)"',
+                    formPayload['form']
+                )
+            )
+
+        except AttributeError:
+            self.simpleException(
+                CloudflareIUAMError,
+                "Cloudflare IUAM detected, unfortunately we can't extract the parameters correctly."
+            )
+
+        hostParsed = urlparse(url)
+
+        try:
+            payload['jschl_answer'] = JavaScriptInterpreter.dynamicImport(
+                interpreter
+            ).solveChallenge(body, hostParsed.netloc)
+        except Exception as e:
+            self.simpleException(
+                CloudflareIUAMError,
+                'Unable to parse Cloudflare anti-bots page: {}'.format(
+                    getattr(e, 'message', e)
+                )
+            )
+
+        return {
+            'url': '{}://{}{}'.format(
+                hostParsed.scheme,
+                hostParsed.netloc,
+                self.unescape(formPayload['challengeUUID'])
+            ),
+            'data': payload
+        }
+
+    # ------------------------------------------------------------------------------- #
+    #  Try to solve the reCaptcha challenge via 3rd party.
+    # ------------------------------------------------------------------------------- #
+
+    def reCaptcha_Challenge_Response(self, provider, provider_params, body, url):
+        try:
+            formPayload = re.search(
+                r'<form class="challenge-form" (?P<form>id="challenge-form" '
+                r'action="(?P<challengeUUID>.*?__cf_chl_captcha_tk__=\S+)"(.*?)</form>)',
+                body,
+                re.M | re.DOTALL
+            ).groupdict()
+
+            if not all(key in formPayload for key in ['form', 'challengeUUID']):
+                self.simpleException(
+                    CloudflareReCaptchaError,
+                    "Cloudflare reCaptcha detected, unfortunately we can't extract the parameters correctly."
+                )
+
+            payload = OrderedDict(
+                re.findall(
+                    r'(name="r"\svalue|data-ray|data-sitekey)="(.*?)"',
+                    formPayload['form']
+                )
+            )
+        except (AttributeError):
+            self.simpleException(
+                CloudflareReCaptchaError,
+                "Cloudflare reCaptcha detected, unfortunately we can't extract the parameters correctly."
+            )
+
+        hostParsed = urlparse(url)
+
+        return {
+            'url': '{}://{}{}'.format(
+                hostParsed.scheme,
+                hostParsed.netloc,
+                self.unescape(formPayload['challengeUUID'])
+            ),
+            'data': OrderedDict([
+                ('r', payload.get('name="r" value', '')),
+                ('id', payload.get('data-ray')),
+                (
+                    'g-recaptcha-response',
+                    reCaptcha.dynamicImport(
+                        provider.lower()
+                    ).solveCaptcha(
+                        url,
+                        payload['data-sitekey'],
+                        provider_params
+                    )
+                )
+            ])
+        }
+
+    # ------------------------------------------------------------------------------- #
+    # Attempt to handle and send the challenge response back to cloudflare
+    # ------------------------------------------------------------------------------- #
+
+    def Challenge_Response(self, resp, **kwargs):
+        if self.is_reCaptcha_Challenge(resp):
+            # ------------------------------------------------------------------------------- #
+            # double down on the request as some websites are only checking
+            # if cfuid is populated before issuing reCaptcha.
+            # ------------------------------------------------------------------------------- #
+
+            resp = self.decodeBrotli(
+                super(CloudScraper, self).request(resp.request.method, resp.url, **kwargs)
+            )
+
+            if not self.is_reCaptcha_Challenge(resp):
+                return resp
+
+            # ------------------------------------------------------------------------------- #
+            # if no reCaptcha provider raise a runtime error.
+            # ------------------------------------------------------------------------------- #
+
+            if not self.recaptcha or not isinstance(self.recaptcha, dict) or not self.recaptcha.get('provider'):
+                self.simpleException(
+                    CloudflareReCaptchaProvider,
+                    "Cloudflare reCaptcha detected, unfortunately you haven't loaded an anti reCaptcha provider "
+                    "correctly via the 'recaptcha' parameter."
+                )
+
+            # ------------------------------------------------------------------------------- #
+            # if provider is return_response, return the response without doing anything.
+            # ------------------------------------------------------------------------------- #
+
+            if self.recaptcha.get('provider') == 'return_response':
+                return resp
+
+            self.recaptcha['proxies'] = self.proxies
+            submit_url = self.reCaptcha_Challenge_Response(
+                self.recaptcha.get('provider'),
+                self.recaptcha,
+                resp.text,
+                resp.url
+            )
+        else:
+            # ------------------------------------------------------------------------------- #
+            # Cloudflare requires a delay before solving the challenge
+            # ------------------------------------------------------------------------------- #
+
+            if not self.delay:
+                try:
+                    delay = float(
+                        re.search(
+                            r'submit\(\);\r?\n\s*},\s*([0-9]+)',
+                            resp.text
+                        ).group(1)
+                    ) / float(1000)
+                    if isinstance(delay, (int, float)):
+                        self.delay = delay
+                except (AttributeError, ValueError):
+                    self.simpleException(
+                        CloudflareIUAMError,
+                        "Cloudflare IUAM possibility malformed, issue extracing delay value."
+                    )
+
+            sleep(self.delay)
+
+            # ------------------------------------------------------------------------------- #
+
+            submit_url = self.IUAM_Challenge_Response(
+                resp.text,
+                resp.url,
+                self.interpreter
+            )
+
+        # ------------------------------------------------------------------------------- #
+        # Send the Challenge Response back to Cloudflare
+        # ------------------------------------------------------------------------------- #
+
+        if submit_url:
+
+            def updateAttr(obj, name, newValue):
+                try:
+                    obj[name].update(newValue)
+                    return obj[name]
+                except (AttributeError, KeyError):
+                    obj[name] = {}
+                    obj[name].update(newValue)
+                    return obj[name]
+
+            cloudflare_kwargs = deepcopy(kwargs)
+            cloudflare_kwargs['allow_redirects'] = False
+            cloudflare_kwargs['data'] = updateAttr(
+                cloudflare_kwargs,
+                'data',
+                submit_url['data']
+            )
+
+            urlParsed = urlparse(resp.url)
+            cloudflare_kwargs['headers'] = updateAttr(
+                cloudflare_kwargs,
+                'headers',
+                {
+                    'Origin': '{}://{}'.format(urlParsed.scheme, urlParsed.netloc),
+                    'Referer': resp.url
+                }
+            )
+
+            challengeSubmitResponse = self.request(
+                'POST',
+                submit_url['url'],
+                **cloudflare_kwargs
+            )
+
+            # ------------------------------------------------------------------------------- #
+            # Return response if Cloudflare is doing content pass through instead of 3xx
+            # else request with redirect URL also handle protocol scheme change http -> https
+            # ------------------------------------------------------------------------------- #
+
+            if not challengeSubmitResponse.is_redirect:
+                return challengeSubmitResponse
+            else:
+                cloudflare_kwargs = deepcopy(kwargs)
+                cloudflare_kwargs['headers'] = updateAttr(
+                    cloudflare_kwargs,
+                    'headers',
+                    {'Referer': challengeSubmitResponse.url}
+                )
+
+                if not urlparse(challengeSubmitResponse.headers['Location']).netloc:
+                    redirect_location = urljoin(
+                        challengeSubmitResponse.url,
+                        challengeSubmitResponse.headers['Location']
+                    )
+                else:
+                    redirect_location = challengeSubmitResponse.headers['Location']
+
+                return self.request(
+                    resp.request.method,
+                    redirect_location,
+                    **cloudflare_kwargs
+                )
+
+        # ------------------------------------------------------------------------------- #
+        # We shouldn't be here...
+        # Re-request the original query and/or process again....
+        # ------------------------------------------------------------------------------- #
+
+        return self.request(resp.request.method, resp.url, **kwargs)
+
+    # ------------------------------------------------------------------------------- #
 
     @classmethod
     def create_scraper(cls, sess=None, **kwargs):
@@ -247,24 +590,30 @@ class CloudScraper(Session):
         scraper = cls(**kwargs)
 
         if sess:
-            attrs = ['auth', 'cert', 'cookies', 'headers', 'hooks', 'params', 'proxies', 'data']
-            for attr in attrs:
+            for attr in ['auth', 'cert', 'cookies', 'headers', 'hooks', 'params', 'proxies', 'data']:
                 val = getattr(sess, attr, None)
                 if val:
                     setattr(scraper, attr, val)
 
         return scraper
 
-    ##########################################################################################################################################################
-
+    # ------------------------------------------------------------------------------- #
     # Functions for integrating cloudscraper with other applications and scripts
+    # ------------------------------------------------------------------------------- #
+
     @classmethod
     def get_tokens(cls, url, **kwargs):
         scraper = cls.create_scraper(
-            debug=kwargs.pop('debug', False),
-            delay=kwargs.pop('delay', None),
-            interpreter=kwargs.pop('interpreter', 'js2py'),
-            allow_brotli=kwargs.pop('allow_brotli', True),
+            **{
+                field: kwargs.pop(field, None) for field in [
+                    'allow_brotli',
+                    'browser',
+                    'debug',
+                    'delay',
+                    'interpreter',
+                    'recaptcha'
+                ] if field in kwargs
+            }
         )
 
         try:
@@ -283,7 +632,11 @@ class CloudScraper(Session):
                 cookie_domain = d
                 break
         else:
-            raise ValueError('Unable to find Cloudflare cookies. Does the site actually have Cloudflare IUAM ("I\'m Under Attack Mode") enabled?')
+            cls.simpleException(
+                CloudflareIUAMError,
+                "Unable to find Cloudflare cookies. Does the site actually "
+                "have Cloudflare IUAM (I'm Under Attack Mode) enabled?"
+            )
 
         return (
             {
@@ -293,7 +646,7 @@ class CloudScraper(Session):
             scraper.headers['User-Agent']
         )
 
-    ##########################################################################################################################################################
+    # ------------------------------------------------------------------------------- #
 
     @classmethod
     def get_cookie_string(cls, url, **kwargs):
@@ -304,7 +657,18 @@ class CloudScraper(Session):
         return '; '.join('='.join(pair) for pair in tokens.items()), user_agent
 
 
-##########################################################################################################################################################
+# ------------------------------------------------------------------------------- #
+
+if ssl.OPENSSL_VERSION_INFO < (1, 1, 1):
+    print(
+        "DEPRECATION: The OpenSSL being used by this python install ({}) does not meet the minimum supported "
+        "version (>= OpenSSL 1.1.1) in order to support TLS 1.3 required by Cloudflare, "
+        "You may encounter an unexpected reCaptcha or cloudflare 1020 blocks.".format(
+            ssl.OPENSSL_VERSION
+        )
+    )
+
+# ------------------------------------------------------------------------------- #
 
 create_scraper = CloudScraper.create_scraper
 get_tokens = CloudScraper.get_tokens

Contents/Libraries/Shared/cloudscraper/exceptions.py

@@ -0,0 +1,99 @@
+# -*- coding: utf-8 -*-
+
+# ------------------------------------------------------------------------------- #
+
+"""
+cloudscraper.exceptions
+~~~~~~~~~~~~~~~~~~~
+This module contains the set of cloudscraper exceptions.
+"""
+
+# ------------------------------------------------------------------------------- #
+
+
+class CloudflareException(Exception):
+    """
+    Base exception class for cloudscraper for Cloudflare
+    """
+
+
+class CloudflareLoopProtection(CloudflareException):
+    """
+    Raise an exception for recursive depth protection
+    """
+
+
+class CloudflareCode1020(CloudflareException):
+    """
+    Raise an exception for Cloudflare code 1020 block
+    """
+
+
+class CloudflareIUAMError(CloudflareException):
+    """
+    Raise an error for problem extracting IUAM paramters
+    from Cloudflare payload
+    """
+
+
+class CloudflareReCaptchaError(CloudflareException):
+    """
+    Raise an error for problem extracting reCaptcha paramters
+    from Cloudflare payload
+    """
+
+
+class CloudflareReCaptchaProvider(CloudflareException):
+    """
+    Raise an exception for no reCaptcha provider loaded for Cloudflare.
+    """
+
+# ------------------------------------------------------------------------------- #
+
+
+class reCaptchaException(Exception):
+    """
+    Base exception class for cloudscraper reCaptcha Providers
+    """
+
+
+class reCaptchaServiceUnavailable(reCaptchaException):
+    """
+    Raise an exception for external services that cannot be reached
+    """
+
+
+class reCaptchaAPIError(reCaptchaException):
+    """
+    Raise an error for error from API response.
+    """
+
+
+class reCaptchaAccountError(reCaptchaException):
+    """
+    Raise an error for reCaptcha provider account problem.
+    """
+
+
+class reCaptchaTimeout(reCaptchaException):
+    """
+    Raise an exception for reCaptcha provider taking too long.
+    """
+
+
+class reCaptchaParameter(reCaptchaException):
+    """
+    Raise an exception for bad or missing Parameter.
+    """
+
+
+class reCaptchaBadJobID(reCaptchaException):
+    """
+    Raise an exception for invalid job id.
+    """
+
+
+class reCaptchaReportError(reCaptchaException):
+    """
+    Raise an error for reCaptcha provider unable to report bad solve.
+    """

Contents/Libraries/Shared/cloudscraper/interpreters/__init__.py

@@ -1,4 +1,3 @@
-import re
 import sys
 import logging
 import abc
@@ -8,20 +7,24 @@ if sys.version_info >= (3, 4):
 else:
     ABC = abc.ABCMeta('ABC', (), {})
 
-##########################################################################################################################################################
-
-BUG_REPORT = 'Cloudflare may have changed their technique, or there may be a bug in the script.'
-
-##########################################################################################################################################################
+# ------------------------------------------------------------------------------- #
 
 interpreters = {}
+BUG_REPORT = 'Cloudflare may have changed their technique, or there may be a bug in the script.'
+
+# ------------------------------------------------------------------------------- #
 
 
 class JavaScriptInterpreter(ABC):
+
+    # ------------------------------------------------------------------------------- #
+
     @abc.abstractmethod
     def __init__(self, name):
         interpreters[name] = self
 
+    # ------------------------------------------------------------------------------- #
+
     @classmethod
     def dynamicImport(cls, name):
         if name not in interpreters:
@@ -35,55 +38,17 @@ class JavaScriptInterpreter(ABC):
 
         return interpreters[name]
 
+    # ------------------------------------------------------------------------------- #
+
     @abc.abstractmethod
     def eval(self, jsEnv, js):
         pass
 
+    # ------------------------------------------------------------------------------- #
+
     def solveChallenge(self, body, domain):
         try:
-            js = re.search(
-                r'setTimeout\(function\(\){\s+(var s,t,o,p,b,r,e,a,k,i,n,g,f.+?\r?\n[\s\S]+?a\.value =.+?)\r?\n',
-                body
-            ).group(1)
-        except Exception:
-            raise ValueError('Unable to identify Cloudflare IUAM Javascript on website. {}'.format(BUG_REPORT))
-
-        js = re.sub(r'\s{2,}', ' ', js, flags=re.MULTILINE | re.DOTALL).replace('\'; 121\'', '')
-        js += '\na.value;'
-
-        jsEnv = '''
-            String.prototype.italics=function(str) {{return "<i>" + this + "</i>";}};
-            var document = {{
-                createElement: function () {{
-                    return {{ firstChild: {{ href: "https://{domain}/" }} }}
-                }},
-                getElementById: function () {{
-                    return {{"innerHTML": "{innerHTML}"}};
-                }}
-            }};
-        '''
-
-        try:
-            innerHTML = re.search(
-                r'<div(?: [^<>]*)? id="([^<>]*?)">([^<>]*?)</div>',
-                body,
-                re.MULTILINE | re.DOTALL
-            )
-            innerHTML = innerHTML.group(2) if innerHTML else ''
-
-        except:  # noqa
-            logging.error('Error extracting Cloudflare IUAM Javascript. {}'.format(BUG_REPORT))
-            raise
-
-        try:
-            result = self.eval(
-                re.sub(r'\s{2,}', ' ', jsEnv.format(domain=domain, innerHTML=innerHTML), flags=re.MULTILINE | re.DOTALL),
-                js
-            )
-
-            float(result)
+            return float(self.eval(body, domain))
         except Exception:
             logging.error('Error executing Cloudflare IUAM Javascript. {}'.format(BUG_REPORT))
             raise
-
-        return result

Contents/Libraries/Shared/cloudscraper/interpreters/chakracore.py

@@ -0,0 +1,103 @@
+from __future__ import absolute_import
+
+import os
+import sys
+import ctypes.util
+
+from ctypes import c_void_p, c_size_t, byref, create_string_buffer, CDLL
+
+from . import JavaScriptInterpreter
+from .encapsulated import template
+
+# ------------------------------------------------------------------------------- #
+
+
+class ChallengeInterpreter(JavaScriptInterpreter):
+
+    # ------------------------------------------------------------------------------- #
+
+    def __init__(self):
+        super(ChallengeInterpreter, self).__init__('chakracore')
+
+    # ------------------------------------------------------------------------------- #
+
+    def eval(self, body, domain):
+        chakraCoreLibrary = None
+
+        # check current working directory.
+        for _libraryFile in ['libChakraCore.so', 'libChakraCore.dylib', 'ChakraCore.dll']:
+            if os.path.isfile(os.path.join(os.getcwd(), _libraryFile)):
+                chakraCoreLibrary = os.path.join(os.getcwd(), _libraryFile)
+                continue
+
+        if not chakraCoreLibrary:
+            chakraCoreLibrary = ctypes.util.find_library('ChakraCore')
+
+        if not chakraCoreLibrary:
+            sys.tracebacklimit = 0
+            raise RuntimeError(
+                'ChakraCore library not found in current path or any of your system library paths, '
+                'please download from https://www.github.com/VeNoMouS/cloudscraper/tree/ChakraCore/, '
+                'or https://github.com/Microsoft/ChakraCore/'
+            )
+
+        try:
+            chakraCore = CDLL(chakraCoreLibrary)
+        except OSError:
+            sys.tracebacklimit = 0
+            raise RuntimeError('There was an error loading the ChakraCore library {}'.format(chakraCoreLibrary))
+
+        if sys.platform != 'win32':
+            chakraCore.DllMain(0, 1, 0)
+            chakraCore.DllMain(0, 2, 0)
+
+        script = create_string_buffer(template(body, domain).encode('utf-16'))
+
+        runtime = c_void_p()
+        chakraCore.JsCreateRuntime(0, 0, byref(runtime))
+
+        context = c_void_p()
+        chakraCore.JsCreateContext(runtime, byref(context))
+        chakraCore.JsSetCurrentContext(context)
+
+        fname = c_void_p()
+        chakraCore.JsCreateString(
+            'iuam-challenge.js',
+            len('iuam-challenge.js'),
+            byref(fname)
+        )
+
+        scriptSource = c_void_p()
+        chakraCore.JsCreateExternalArrayBuffer(
+            script,
+            len(script),
+            0,
+            0,
+            byref(scriptSource)
+        )
+
+        jsResult = c_void_p()
+        chakraCore.JsRun(scriptSource, 0, fname, 0x02, byref(jsResult))
+
+        resultJSString = c_void_p()
+        chakraCore.JsConvertValueToString(jsResult, byref(resultJSString))
+
+        stringLength = c_size_t()
+        chakraCore.JsCopyString(resultJSString, 0, 0, byref(stringLength))
+
+        resultSTR = create_string_buffer(stringLength.value + 1)
+        chakraCore.JsCopyString(
+            resultJSString,
+            byref(resultSTR),
+            stringLength.value + 1,
+            0
+        )
+
+        chakraCore.JsDisposeRuntime(runtime)
+
+        return resultSTR.value
+
+
+# ------------------------------------------------------------------------------- #
+
+ChallengeInterpreter()

Contents/Libraries/Shared/cloudscraper/interpreters/encapsulated.py

@@ -0,0 +1,58 @@
+import logging
+import re
+
+# ------------------------------------------------------------------------------- #
+
+
+def template(body, domain):
+    BUG_REPORT = 'Cloudflare may have changed their technique, or there may be a bug in the script.'
+
+    try:
+        js = re.search(
+            r'setTimeout\(function\(\){\s+(var s,t,o,p,b,r,e,a,k,i,n,g,f.+?\r?\n[\s\S]+?a\.value =.+?)\r?\n',
+            body
+        ).group(1)
+    except Exception:
+        raise ValueError('Unable to identify Cloudflare IUAM Javascript on website. {}'.format(BUG_REPORT))
+
+    js = re.sub(r'\s{2,}', ' ', js, flags=re.MULTILINE | re.DOTALL).replace('\'; 121\'', '')
+    js += '\na.value;'
+
+    jsEnv = '''
+        String.prototype.italics=function(str) {{return "<i>" + this + "</i>";}};
+        var document = {{
+            createElement: function () {{
+                return {{ firstChild: {{ href: "https://{domain}/" }} }}
+            }},
+            getElementById: function () {{
+                return {{"innerHTML": "{innerHTML}"}};
+            }}
+        }};
+    '''
+
+    try:
+        innerHTML = re.search(
+            r'<div(?: [^<>]*)? id="([^<>]*?)">([^<>]*?)</div>',
+            body,
+            re.MULTILINE | re.DOTALL
+        )
+        innerHTML = innerHTML.group(2) if innerHTML else ''
+
+    except:  # noqa
+        logging.error('Error extracting Cloudflare IUAM Javascript. {}'.format(BUG_REPORT))
+        raise
+
+    return '{}{}'.format(
+        re.sub(
+            r'\s{2,}',
+            ' ',
+            jsEnv.format(
+                domain=domain,
+                innerHTML=innerHTML
+            ),
+            re.MULTILINE | re.DOTALL
+        ),
+        js
+    )
+
+# ------------------------------------------------------------------------------- #

Contents/Libraries/Shared/cloudscraper/interpreters/js2py.py

@@ -6,27 +6,39 @@ import base64
 
 from . import JavaScriptInterpreter
 
+from .encapsulated import template
 from .jsunfuck import jsunfuck
 
+# ------------------------------------------------------------------------------- #
+
 
 class ChallengeInterpreter(JavaScriptInterpreter):
 
+    # ------------------------------------------------------------------------------- #
+
     def __init__(self):
         super(ChallengeInterpreter, self).__init__('js2py')
 
-    def eval(self, jsEnv, js):
+    # ------------------------------------------------------------------------------- #
+
+    def eval(self, body, domain):
+
+        jsPayload = template(body, domain)
+
         if js2py.eval_js('(+(+!+[]+[+!+[]]+(!![]+[])[!+[]+!+[]+!+[]]+[!+[]+!+[]]+[+[]])+[])[+!+[]]') == '1':
             logging.warning('WARNING - Please upgrade your js2py https://github.com/PiotrDabkowski/Js2Py, applying work around for the meantime.')
-            js = jsunfuck(js)
+            jsPayload = jsunfuck(jsPayload)
 
         def atob(s):
             return base64.b64decode('{}'.format(s)).decode('utf-8')
 
         js2py.disable_pyimport()
         context = js2py.EvalJs({'atob': atob})
-        result = context.eval('{}{}'.format(jsEnv, js))
+        result = context.eval(jsPayload)
 
         return result
 
 
+# ------------------------------------------------------------------------------- #
+
 ChallengeInterpreter()

Contents/Libraries/Shared/cloudscraper/interpreters/native.py

@@ -0,0 +1,120 @@
+from __future__ import absolute_import
+
+import re
+import operator as op
+
+from . import JavaScriptInterpreter
+
+# ------------------------------------------------------------------------------- #
+
+
+class ChallengeInterpreter(JavaScriptInterpreter):
+
+    def __init__(self):
+        super(ChallengeInterpreter, self).__init__('native')
+
+    def eval(self, body, domain):
+        # ------------------------------------------------------------------------------- #
+
+        operators = {
+            '+': op.add,
+            '-': op.sub,
+            '*': op.mul,
+            '/': op.truediv
+        }
+
+        # ------------------------------------------------------------------------------- #
+
+        def jsfuckToNumber(jsFuck):
+            t = ''
+
+            split_numbers = re.compile(r'-?\d+').findall
+
+            for i in re.findall(
+                r'\((?:\d|\+|\-)*\)',
+                jsFuck.replace('!+[]', '1').replace('!![]', '1').replace('[]', '0').lstrip('+').replace('(+', '(')
+            ):
+                t = '{}{}'.format(t, sum(int(x) for x in split_numbers(i)))
+
+            return int(t)
+
+        # ------------------------------------------------------------------------------- #
+
+        def divisorMath(payload, needle, domain):
+            jsfuckMath = payload.split('/')
+            if needle in jsfuckMath[1]:
+                expression = re.findall(r"^(.*?)(.)\(function", jsfuckMath[1])[0]
+                expression_value = operators[expression[1]](
+                    float(jsfuckToNumber(expression[0])),
+                    float(ord(domain[jsfuckToNumber(jsfuckMath[1][
+                        jsfuckMath[1].find('"("+p+")")}') + len('"("+p+")")}'):-2
+                    ])]))
+                )
+            else:
+                expression_value = jsfuckToNumber(jsfuckMath[1])
+
+            expression_value = jsfuckToNumber(jsfuckMath[0]) / float(expression_value)
+
+            return expression_value
+
+        # ------------------------------------------------------------------------------- #
+
+        def challengeSolve(body, domain):
+            jschl_answer = 0
+
+            jsfuckChallenge = re.search(
+                r"setTimeout\(function\(\){\s+var.*?f,\s*(?P<variable>\w+).*?:(?P<init>\S+)};"
+                r".*?\('challenge-form'\);\s+;(?P<challenge>.*?a\.value)"
+                r"(?:.*id=\"cf-dn-.*?>(?P<k>\S+)<)?",
+                body,
+                re.DOTALL | re.MULTILINE
+            ).groupdict()
+
+            jsfuckChallenge['challenge'] = re.finditer(
+                r'{}.*?([+\-*/])=(.*?);(?=a\.value|{})'.format(
+                    jsfuckChallenge['variable'],
+                    jsfuckChallenge['variable']
+                ),
+                jsfuckChallenge['challenge']
+            )
+
+            # ------------------------------------------------------------------------------- #
+
+            if '/' in jsfuckChallenge['init']:
+                val = jsfuckChallenge['init'].split('/')
+                jschl_answer = jsfuckToNumber(val[0]) / float(jsfuckToNumber(val[1]))
+            else:
+                jschl_answer = jsfuckToNumber(jsfuckChallenge['init'])
+
+            # ------------------------------------------------------------------------------- #
+
+            for expressionMatch in jsfuckChallenge['challenge']:
+                oper, expression = expressionMatch.groups()
+
+                if '/' in expression:
+                    expression_value = divisorMath(expression, 'function(p)', domain)
+                else:
+                    if 'Element' in expression:
+                        expression_value = divisorMath(jsfuckChallenge['k'], '"("+p+")")}', domain)
+                    else:
+                        expression_value = jsfuckToNumber(expression)
+
+                jschl_answer = operators[oper](jschl_answer, expression_value)
+
+            # ------------------------------------------------------------------------------- #
+
+            if not jsfuckChallenge['k'] and '+ t.length' in body:
+                jschl_answer += len(domain)
+
+            # ------------------------------------------------------------------------------- #
+
+            return '{0:.10f}'.format(jschl_answer)
+
+        # ------------------------------------------------------------------------------- #
+
+        return challengeSolve(body, domain)
+
+
+# ------------------------------------------------------------------------------- #
+
+ChallengeInterpreter()

Contents/Libraries/Shared/cloudscraper/interpreters/nodejs.py

@@ -1,22 +1,23 @@
 import base64
-import logging
 import subprocess
+import sys
 
 from . import JavaScriptInterpreter
+from .encapsulated import template
 
-##########################################################################################################################################################
-
-BUG_REPORT = 'Cloudflare may have changed their technique, or there may be a bug in the script.'
-
-##########################################################################################################################################################
+# ------------------------------------------------------------------------------- #
 
 
 class ChallengeInterpreter(JavaScriptInterpreter):
 
+    # ------------------------------------------------------------------------------- #
+
     def __init__(self):
         super(ChallengeInterpreter, self).__init__('nodejs')
 
-    def eval(self, jsEnv, js):
+    # ------------------------------------------------------------------------------- #
+
+    def eval(self, body, domain):
         try:
             js = 'var atob = function(str) {return Buffer.from(str, "base64").toString("binary");};' \
                  'var challenge = atob("%s");' \
@@ -24,23 +25,25 @@ class ChallengeInterpreter(JavaScriptInterpreter):
                  'var options = {filename: "iuam-challenge.js", timeout: 4000};' \
                  'var answer = require("vm").runInNewContext(challenge, context, options);' \
                  'process.stdout.write(String(answer));' \
-                 % base64.b64encode('{}{}'.format(jsEnv, js).encode('UTF-8')).decode('ascii')
+                 % base64.b64encode(template(body, domain).encode('UTF-8')).decode('ascii')
 
             return subprocess.check_output(['node', '-e', js])
 
         except OSError as e:
             if e.errno == 2:
                 raise EnvironmentError(
-                    'Missing Node.js runtime. Node is required and must be in the PATH (check with `node -v`). Your Node binary may be called `nodejs` rather than `node`, '
-                    'in which case you may need to run `apt-get install nodejs-legacy` on some Debian-based systems. (Please read the cloudscraper'
-                    ' README\'s Dependencies section: https://github.com/VeNoMouS/cloudscraper#dependencies.'
+                    'Missing Node.js runtime. Node is required and must be in the PATH (check with `node -v`).\n\n'
+                    'Your Node binary may be called `nodejs` rather than `node`, '
+                    'in which case you may need to run `apt-get install nodejs-legacy` on some Debian-based systems.\n\n'
+                    '(Please read the cloudscraper README\'s Dependencies section: '
+                    'https://github.com/VeNoMouS/cloudscraper#dependencies.)'
                 )
             raise
         except Exception:
-            logging.error('Error executing Cloudflare IUAM Javascript. %s' % BUG_REPORT)
-            raise
+            sys.tracebacklimit = 0
+            raise RuntimeError('Error executing Cloudflare IUAM Javascript in nodejs')
 
-        pass
 
+# ------------------------------------------------------------------------------- #
 
 ChallengeInterpreter()

Contents/Libraries/Shared/cloudscraper/interpreters/v8.py

@@ -0,0 +1,33 @@
+from __future__ import absolute_import
+
+import sys
+
+try:
+    import v8eval
+except ImportError:
+    sys.tracebacklimit = 0
+    raise RuntimeError('Please install the python module v8eval either via pip or download it from https://github.com/sony/v8eval')
+
+from . import JavaScriptInterpreter
+from .encapsulated import template
+
+# ------------------------------------------------------------------------------- #
+
+
+class ChallengeInterpreter(JavaScriptInterpreter):
+
+    def __init__(self):
+        super(ChallengeInterpreter, self).__init__('v8')
+
+    # ------------------------------------------------------------------------------- #
+
+    def eval(self, body, domain):
+        try:
+            return v8eval.V8().eval(template(body, domain))
+        except (TypeError, v8eval.V8Error):
+            RuntimeError('We encountered an error running the V8 Engine.')
+
+
+# ------------------------------------------------------------------------------- #
+
+ChallengeInterpreter()

Contents/Libraries/Shared/cloudscraper/reCaptcha/2captcha.py

@@ -0,0 +1,236 @@
+from __future__ import absolute_import
+
+import requests
+
+
+from ..exceptions import (
+    reCaptchaServiceUnavailable,
+    reCaptchaAPIError,
+    reCaptchaTimeout,
+    reCaptchaParameter,
+    reCaptchaBadJobID,
+    reCaptchaReportError
+)
+
+try:
+    import polling
+except ImportError:
+    raise ImportError(
+        "Please install the python module 'polling' via pip or download it from "
+        "https://github.com/justiniso/polling/"
+    )
+
+from . import reCaptcha
+
+
+class captchaSolver(reCaptcha):
+
+    def __init__(self):
+        super(captchaSolver, self).__init__('2captcha')
+        self.host = 'https://2captcha.com'
+        self.session = requests.Session()
+
+    # ------------------------------------------------------------------------------- #
+
+    @staticmethod
+    def checkErrorStatus(response, request_type):
+        if response.status_code in [500, 502]:
+            raise reCaptchaServiceUnavailable('2Captcha: Server Side Error {}'.format(response.status_code))
+
+        errors = {
+            'in.php': {
+                "ERROR_WRONG_USER_KEY": "You've provided api_key parameter value is in incorrect format, it should contain 32 symbols.",
+                "ERROR_KEY_DOES_NOT_EXIST": "The api_key you've provided does not exists.",
+                "ERROR_ZERO_BALANCE": "You don't have sufficient funds on your account.",
+                "ERROR_PAGEURL": "pageurl parameter is missing in your request.",
+                "ERROR_NO_SLOT_AVAILABLE":
+                    "No Slots Available.\nYou can receive this error in two cases:\n"
+                    "1. If you solve ReCaptcha: the queue of your captchas that are not distributed to workers is too long. "
+                    "Queue limit changes dynamically and depends on total amount of captchas awaiting solution and usually it's between 50 and 100 captchas.\n"
+                    "2. If you solve Normal Captcha: your maximum rate for normal captchas is lower than current rate on the server."
+                    "You can change your maximum rate in your account's settings.",
+                "ERROR_IP_NOT_ALLOWED": "The request is sent from the IP that is not on the list of your allowed IPs.",
+                "IP_BANNED": "Your IP address is banned due to many frequent attempts to access the server using wrong authorization keys.",
+                "ERROR_BAD_TOKEN_OR_PAGEURL":
+                    "You can get this error code when sending ReCaptcha V2. "
+                    "That happens if your request contains invalid pair of googlekey and pageurl. "
+                    "The common reason for that is that ReCaptcha is loaded inside an iframe hosted on another domain/subdomain.",
+                "ERROR_GOOGLEKEY":
+                    "You can get this error code when sending ReCaptcha V2. "
+                    "That means that sitekey value provided in your request is incorrect: it's blank or malformed.",
+                "MAX_USER_TURN": "You made more than 60 requests within 3 seconds.Your account is banned for 10 seconds. Ban will be lifted automatically."
+            },
+            'res.php': {
+                "ERROR_CAPTCHA_UNSOLVABLE":
+                    "We are unable to solve your captcha - three of our workers were unable solve it "
+                    "or we didn't get an answer within 90 seconds (300 seconds for ReCaptcha V2). "
+                    "We will not charge you for that request.",
+                "ERROR_WRONG_USER_KEY": "You've provided api_key parameter value in incorrect format, it should contain 32 symbols.",
+                "ERROR_KEY_DOES_NOT_EXIST": "The api_key you've provided does not exists.",
+                "ERROR_WRONG_ID_FORMAT": "You've provided captcha ID in wrong format. The ID can contain numbers only.",
+                "ERROR_WRONG_CAPTCHA_ID": "You've provided incorrect captcha ID.",
+                "ERROR_BAD_DUPLICATES":
+                    "Error is returned when 100% accuracy feature is enabled. "
+                    "The error means that max numbers of tries is reached but min number of matches not found.",
+                "REPORT_NOT_RECORDED": "Error is returned to your complain request if you already complained lots of correctly solved captchas.",
+                "ERROR_IP_ADDRES":
+                    "You can receive this error code when registering a pingback (callback) IP or domain."
+                    "That happes if your request is coming from an IP address that doesn't match the IP address of your pingback IP or domain.",
+                "ERROR_TOKEN_EXPIRED": "You can receive this error code when sending GeeTest. That error means that challenge value you provided is expired.",
+                "ERROR_EMPTY_ACTION": "Action parameter is missing or no value is provided for action parameter."
+            }
+        }
+
+        if response.json().get('status') is False and response.json().get('request') in errors.get(request_type):
+            raise reCaptchaAPIError(
+                '{} {}'.format(
+                    response.json().get('request'),
+                    errors.get(request_type).get(response.json().get('request'))
+                )
+            )
+
+    # ------------------------------------------------------------------------------- #
+
+    def reportJob(self, jobID):
+        if not jobID:
+            raise reCaptchaBadJobID(
+                "2Captcha: Error bad job id to request reCaptcha."
+            )
+
+        def _checkRequest(response):
+            if response.ok and response.json().get('status') == 1:
+                return response
+
+            self.checkErrorStatus(response, 'res.php')
+
+            return None
+
+        response = polling.poll(
+            lambda: self.session.get(
+                '{}/res.php'.format(self.host),
+                params={
+                    'key': self.api_key,
+                    'action': 'reportbad',
+                    'id': jobID,
+                    'json': '1'
+                }
+            ),
+            check_success=_checkRequest,
+            step=5,
+            timeout=180
+        )
+
+        if response:
+            return True
+        else:
+            raise reCaptchaReportError(
+                "2Captcha: Error - Failed to report bad reCaptcha solve."
+            )
+
+    # ------------------------------------------------------------------------------- #
+
+    def requestJob(self, jobID):
+        if not jobID:
+            raise reCaptchaBadJobID("2Captcha: Error bad job id to request reCaptcha.")
+
+        def _checkRequest(response):
+            if response.ok and response.json().get('status') == 1:
+                return response
+
+            self.checkErrorStatus(response, 'res.php')
+
+            return None
+
+        response = polling.poll(
+            lambda: self.session.get(
+                '{}/res.php'.format(self.host),
+                params={
+                    'key': self.api_key,
+                    'action': 'get',
+                    'id': jobID,
+                    'json': '1'
+                }
+            ),
+            check_success=_checkRequest,
+            step=5,
+            timeout=180
+        )
+
+        if response:
+            return response.json().get('request')
+        else:
+            raise reCaptchaTimeout(
+                "2Captcha: Error failed to solve reCaptcha."
+            )
+
+    # ------------------------------------------------------------------------------- #
+
+    def requestSolve(self, site_url, site_key):
+        def _checkRequest(response):
+            if response.ok and response.json().get("status") == 1 and response.json().get('request'):
+                return response
+
+            self.checkErrorStatus(response, 'in.php')
+
+            return None
+
+        response = polling.poll(
+            lambda: self.session.post(
+                '{}/in.php'.format(self.host),
+                data={
+                    'key': self.api_key,
+                    'method': 'userrecaptcha',
+                    'googlekey': site_key,
+                    'pageurl': site_url,
+                    'json': '1',
+                    'soft_id': '5507698'
+                },
+                allow_redirects=False
+            ),
+            check_success=_checkRequest,
+            step=5,
+            timeout=180
+        )
+
+        if response:
+            return response.json().get('request')
+        else:
+            raise reCaptchaBadJobID(
+                '2Captcha: Error no job id was returned.'
+            )
+
+    # ------------------------------------------------------------------------------- #
+
+    def getCaptchaAnswer(self, site_url, site_key, reCaptchaParams):
+        jobID = None
+
+        if not reCaptchaParams.get('api_key'):
+            raise reCaptchaParameter(
+                "2Captcha: Missing api_key parameter."
+            )
+
+        self.api_key = reCaptchaParams.get('api_key')
+
+        if reCaptchaParams.get('proxy'):
+            self.session.proxies = reCaptchaParams.get('proxies')
+
+        try:
+            jobID = self.requestSolve(site_url, site_key)
+            return self.requestJob(jobID)
+        except polling.TimeoutException:
+            try:
+                if jobID:
+                    self.reportJob(jobID)
+            except polling.TimeoutException:
+                raise reCaptchaTimeout(
+                    "2Captcha: reCaptcha solve took to long and also failed reporting the job the job id {}.".format(jobID)
+                )
+
+            raise reCaptchaTimeout(
+                "2Captcha: reCaptcha solve took to long to execute job id {}, aborting.".format(jobID)
+            )
+
+
+# ------------------------------------------------------------------------------- #
+
+captchaSolver()

Contents/Libraries/Shared/cloudscraper/reCaptcha/9kw.py

@@ -0,0 +1,207 @@
+from __future__ import absolute_import
+
+import re
+import requests
+
+try:
+    import polling
+except ImportError:
+    raise ImportError(
+        "Please install the python module 'polling' via pip or download it from "
+        "https://github.com/justiniso/polling/"
+    )
+
+from ..exceptions import (
+    reCaptchaServiceUnavailable,
+    reCaptchaAPIError,
+    reCaptchaTimeout,
+    reCaptchaParameter,
+    reCaptchaBadJobID
+)
+
+from . import reCaptcha
+
+
+class captchaSolver(reCaptcha):
+
+    def __init__(self):
+        super(captchaSolver, self).__init__('9kw')
+        self.host = 'https://www.9kw.eu/index.cgi'
+        self.maxtimeout = 180
+        self.session = requests.Session()
+
+    # ------------------------------------------------------------------------------- #
+
+    @staticmethod
+    def checkErrorStatus(response):
+        if response.status_code in [500, 502]:
+            raise reCaptchaServiceUnavailable(
+                '9kw: Server Side Error {}'.format(response.status_code)
+            )
+
+        error_codes = {
+            1: 'No API Key available.',
+            2: 'No API key found.',
+            3: 'No active API key found.',
+            4: 'API Key has been disabled by the operator. ',
+            5: 'No user found.',
+            6: 'No data found.',
+            7: 'Found No ID.',
+            8: 'found No captcha.',
+            9: 'No image found.',
+            10: 'Image size not allowed.',
+            11: 'credit is not sufficient.',
+            12: 'what was done.',
+            13: 'No answer contain.',
+            14: 'Captcha already been answered.',
+            15: 'Captcha to quickly filed.',
+            16: 'JD check active.',
+            17: 'Unknown problem.',
+            18: 'Found No ID.',
+            19: 'Incorrect answer.',
+            20: 'Do not timely filed (Incorrect UserID).',
+            21: 'Link not allowed.',
+            22: 'Prohibited submit.',
+            23: 'Entering prohibited.',
+            24: 'Too little credit.',
+            25: 'No entry found.',
+            26: 'No Conditions accepted.',
+            27: 'No coupon code found in the database.',
+            28: 'Already unused voucher code.',
+            29: 'maxTimeout under 60 seconds.',
+            30: 'User not found.',
+            31: 'An account is not yet 24 hours in system.',
+            32: 'An account does not have the full rights.',
+            33: 'Plugin needed a update.',
+            34: 'No HTTPS allowed.',
+            35: 'No HTTP allowed.',
+            36: 'Source not allowed.',
+            37: 'Transfer denied.',
+            38: 'Incorrect answer without space',
+            39: 'Incorrect answer with space',
+            40: 'Incorrect answer with not only numbers',
+            41: 'Incorrect answer with not only A-Z, a-z',
+            42: 'Incorrect answer with not only 0-9, A-Z, a-z',
+            43: 'Incorrect answer with not only [0-9,- ]',
+            44: 'Incorrect answer with not only [0-9A-Za-z,- ]',
+            45: 'Incorrect answer with not only coordinates',
+            46: 'Incorrect answer with not only multiple coordinates',
+            47: 'Incorrect answer with not only data',
+            48: 'Incorrect answer with not only rotate number',
+            49: 'Incorrect answer with not only text',
+            50: 'Incorrect answer with not only text and too short',
+            51: 'Incorrect answer with not enough chars',
+            52: 'Incorrect answer with too many chars',
+            53: 'Incorrect answer without no or yes',
+            54: 'Assignment was not found.'
+        }
+
+        if response.text.startswith('{'):
+            if response.json().get('error'):
+                raise reCaptchaAPIError(error_codes.get(int(response.json().get('error'))))
+        else:
+            error_code = int(re.search(r'^00(?P<error_code>\d+)', response.text).groupdict().get('error_code', 0))
+            if error_code:
+                raise reCaptchaAPIError(error_codes.get(error_code))
+
+    # ------------------------------------------------------------------------------- #
+
+    def requestJob(self, jobID):
+        if not jobID:
+            raise reCaptchaBadJobID(
+                "9kw: Error bad job id to request reCaptcha against."
+            )
+
+        def _checkRequest(response):
+            if response.ok and response.json().get('answer') != 'NO DATA':
+                return response
+
+            self.checkErrorStatus(response)
+
+            return None
+
+        response = polling.poll(
+            lambda: self.session.get(
+                self.host,
+                params={
+                    'apikey': self.api_key,
+                    'action': 'usercaptchacorrectdata',
+                    'id': jobID,
+                    'info': 1,
+                    'json': 1
+                }
+            ),
+            check_success=_checkRequest,
+            step=10,
+            timeout=(self.maxtimeout + 10)
+        )
+
+        if response:
+            return response.json().get('answer')
+        else:
+            raise reCaptchaTimeout("9kw: Error failed to solve reCaptcha.")
+
+    # ------------------------------------------------------------------------------- #
+
+    def requestSolve(self, site_url, site_key):
+        def _checkRequest(response):
+            if response.ok and response.text.startswith('{') and response.json().get('captchaid'):
+                return response
+
+            self.checkErrorStatus(response)
+
+            return None
+
+        response = polling.poll(
+            lambda: self.session.post(
+                self.host,
+                data={
+                    'apikey': self.api_key,
+                    'action': 'usercaptchaupload',
+                    'interactive': 1,
+                    'file-upload-01': site_key,
+                    'oldsource': 'recaptchav2',
+                    'pageurl': site_url,
+                    'maxtimeout': self.maxtimeout,
+                    'json': 1
+                },
+                allow_redirects=False
+            ),
+            check_success=_checkRequest,
+            step=5,
+            timeout=(self.maxtimeout + 10)
+        )
+
+        if response:
+            return response.json().get('captchaid')
+        else:
+            raise reCaptchaBadJobID('9kw: Error no valid job id was returned.')
+
+    # ------------------------------------------------------------------------------- #
+
+    def getCaptchaAnswer(self, site_url, site_key, reCaptchaParams):
+        jobID = None
+
+        if not reCaptchaParams.get('api_key'):
+            raise reCaptchaParameter("9kw: Missing api_key parameter.")
+
+        self.api_key = reCaptchaParams.get('api_key')
+
+        if reCaptchaParams.get('maxtimeout'):
+            self.maxtimeout = reCaptchaParams.get('maxtimeout')
+
+        if reCaptchaParams.get('proxy'):
+            self.session.proxies = reCaptchaParams.get('proxies')
+
+        try:
+            jobID = self.requestSolve(site_url, site_key)
+            return self.requestJob(jobID)
+        except polling.TimeoutException:
+            raise reCaptchaTimeout(
+                "9kw: reCaptcha solve took to long to execute 'captchaid' {}, aborting.".format(jobID)
+            )
+
+# ------------------------------------------------------------------------------- #
+
+
+captchaSolver()

Contents/Libraries/Shared/cloudscraper/reCaptcha/__init__.py

@@ -0,0 +1,46 @@
+import abc
+import logging
+import sys
+
+if sys.version_info >= (3, 4):
+    ABC = abc.ABC  # noqa
+else:
+    ABC = abc.ABCMeta('ABC', (), {})
+
+# ------------------------------------------------------------------------------- #
+
+captchaSolvers = {}
+
+# ------------------------------------------------------------------------------- #
+
+
+class reCaptcha(ABC):
+    @abc.abstractmethod
+    def __init__(self, name):
+        captchaSolvers[name] = self
+
+    # ------------------------------------------------------------------------------- #
+
+    @classmethod
+    def dynamicImport(cls, name):
+        if name not in captchaSolvers:
+            try:
+                __import__('{}.{}'.format(cls.__module__, name))
+                if not isinstance(captchaSolvers.get(name), reCaptcha):
+                    raise ImportError('The anti reCaptcha provider was not initialized.')
+            except ImportError:
+                logging.error("Unable to load {} anti reCaptcha provider".format(name))
+                raise
+
+        return captchaSolvers[name]
+
+    # ------------------------------------------------------------------------------- #
+
+    @abc.abstractmethod
+    def getCaptchaAnswer(self, site_url, site_key, reCaptchaParams):
+        pass
+
+    # ------------------------------------------------------------------------------- #
+
+    def solveCaptcha(self, site_url, site_key, reCaptchaParams):
+        return self.getCaptchaAnswer(site_url, site_key, reCaptchaParams)

Contents/Libraries/Shared/cloudscraper/reCaptcha/anticaptcha.py

@@ -0,0 +1,49 @@
+from __future__ import absolute_import
+
+from ..exceptions import reCaptchaParameter
+
+try:
+    from python_anticaptcha import (
+        AnticaptchaClient,
+        NoCaptchaTaskProxylessTask
+    )
+except ImportError:
+    raise ImportError(
+        "Please install the python module 'python_anticaptcha' via pip or download it from "
+        "https://github.com/ad-m/python-anticaptcha"
+    )
+
+from . import reCaptcha
+
+
+class captchaSolver(reCaptcha):
+
+    def __init__(self):
+        super(captchaSolver, self).__init__('anticaptcha')
+
+    # ------------------------------------------------------------------------------- #
+
+    def getCaptchaAnswer(self, site_url, site_key, reCaptchaParams):
+        if not reCaptchaParams.get('api_key'):
+            raise reCaptchaParameter("anticaptcha: Missing api_key parameter.")
+
+        client = AnticaptchaClient(reCaptchaParams.get('api_key'))
+
+        if reCaptchaParams.get('proxy'):
+            client.session.proxies = reCaptchaParams.get('proxies')
+
+        task = NoCaptchaTaskProxylessTask(site_url, site_key)
+
+        if not hasattr(client, 'createTaskSmee'):
+            raise NotImplementedError(
+                "Please upgrade 'python_anticaptcha' via pip or download it from "
+                "https://github.com/ad-m/python-anticaptcha"
+            )
+
+        job = client.createTaskSmee(task)
+        return job.get_solution_response()
+
+
+# ------------------------------------------------------------------------------- #
+
+captchaSolver()

Contents/Libraries/Shared/cloudscraper/reCaptcha/deathbycaptcha.py

@@ -0,0 +1,227 @@
+from __future__ import absolute_import
+
+import json
+import requests
+
+try:
+    import polling
+except ImportError:
+    raise ImportError(
+        "Please install the python module 'polling' via pip or download it from "
+        "https://github.com/justiniso/polling/"
+    )
+
+from ..exceptions import (
+    reCaptchaServiceUnavailable,
+    reCaptchaAccountError,
+    reCaptchaTimeout,
+    reCaptchaParameter,
+    reCaptchaBadJobID,
+    reCaptchaReportError
+)
+
+from . import reCaptcha
+
+
+class captchaSolver(reCaptcha):
+
+    def __init__(self):
+        super(captchaSolver, self).__init__('deathbycaptcha')
+        self.host = 'http://api.dbcapi.me/api'
+        self.session = requests.Session()
+
+    # ------------------------------------------------------------------------------- #
+
+    @staticmethod
+    def checkErrorStatus(response):
+        errors = dict(
+            [
+                (400, "DeathByCaptcha: 400 Bad Request"),
+                (403, "DeathByCaptcha: 403 Forbidden - Invalid credentails or insufficient credits."),
+                # (500, "DeathByCaptcha: 500 Internal Server Error."),
+                (503, "DeathByCaptcha: 503 Service Temporarily Unavailable.")
+            ]
+        )
+
+        if response.status_code in errors:
+            raise reCaptchaServiceUnavailable(errors.get(response.status_code))
+
+    # ------------------------------------------------------------------------------- #
+
+    def login(self, username, password):
+        self.username = username
+        self.password = password
+
+        def _checkRequest(response):
+            if response.ok:
+                if response.json().get('is_banned'):
+                    raise reCaptchaAccountError('DeathByCaptcha: Your account is banned.')
+
+                if response.json().get('balanace') == 0:
+                    raise reCaptchaAccountError('DeathByCaptcha: insufficient credits.')
+
+                return response
+
+            self.checkErrorStatus(response)
+
+            return None
+
+        response = polling.poll(
+            lambda: self.session.post(
+                '{}/user'.format(self.host),
+                headers={'Accept': 'application/json'},
+                data={
+                    'username': self.username,
+                    'password': self.password
+                }
+            ),
+            check_success=_checkRequest,
+            step=10,
+            timeout=120
+        )
+
+        self.debugRequest(response)
+
+    # ------------------------------------------------------------------------------- #
+
+    def reportJob(self, jobID):
+        if not jobID:
+            raise reCaptchaBadJobID(
+                "DeathByCaptcha: Error bad job id to report failed reCaptcha."
+            )
+
+        def _checkRequest(response):
+            if response.status_code == 200:
+                return response
+
+            self.checkErrorStatus(response)
+
+            return None
+
+        response = polling.poll(
+            lambda: self.session.post(
+                '{}/captcha/{}/report'.format(self.host, jobID),
+                headers={'Accept': 'application/json'},
+                data={
+                    'username': self.username,
+                    'password': self.password
+                }
+            ),
+            check_success=_checkRequest,
+            step=10,
+            timeout=180
+        )
+
+        if response:
+            return True
+        else:
+            raise reCaptchaReportError(
+                "DeathByCaptcha: Error report failed reCaptcha."
+            )
+
+    # ------------------------------------------------------------------------------- #
+
+    def requestJob(self, jobID):
+        if not jobID:
+            raise reCaptchaBadJobID(
+                "DeathByCaptcha: Error bad job id to request reCaptcha."
+            )
+
+        def _checkRequest(response):
+            if response.ok and response.json().get('text'):
+                return response
+
+            self.checkErrorStatus(response)
+
+            return None
+
+        response = polling.poll(
+            lambda: self.session.get(
+                '{}/captcha/{}'.format(self.host, jobID),
+                headers={'Accept': 'application/json'}
+            ),
+            check_success=_checkRequest,
+            step=10,
+            timeout=180
+        )
+
+        if response:
+            return response.json().get('text')
+        else:
+            raise reCaptchaTimeout(
+                "DeathByCaptcha: Error failed to solve reCaptcha."
+            )
+
+    # ------------------------------------------------------------------------------- #
+
+    def requestSolve(self, site_url, site_key):
+        def _checkRequest(response):
+            if response.ok and response.json().get("is_correct") and response.json().get('captcha'):
+                return response
+
+            self.checkErrorStatus(response)
+
+            return None
+
+        response = polling.poll(
+            lambda: self.session.post(
+                '{}/captcha'.format(self.host),
+                headers={'Accept': 'application/json'},
+                data={
+                    'username': self.username,
+                    'password': self.password,
+                    'type': '4',
+                    'token_params': json.dumps({
+                        'googlekey': site_key,
+                        'pageurl': site_url
+                    })
+                },
+                allow_redirects=False
+            ),
+            check_success=_checkRequest,
+            step=10,
+            timeout=180
+        )
+
+        if response:
+            return response.json().get('captcha')
+        else:
+            raise reCaptchaBadJobID(
+                'DeathByCaptcha: Error no job id was returned.'
+            )
+
+    # ------------------------------------------------------------------------------- #
+
+    def getCaptchaAnswer(self, site_url, site_key, reCaptchaParams):
+        jobID = None
+
+        for param in ['username', 'password']:
+            if not reCaptchaParams.get(param):
+                raise reCaptchaParameter(
+                    "DeathByCaptcha: Missing '{}' parameter.".format(param)
+                )
+            setattr(self, param, reCaptchaParams.get(param))
+
+        if reCaptchaParams.get('proxy'):
+            self.session.proxies = reCaptchaParams.get('proxies')
+
+        try:
+            jobID = self.requestSolve(site_url, site_key)
+            return self.requestJob(jobID)
+        except polling.TimeoutException:
+            try:
+                if jobID:
+                    self.reportJob(jobID)
+            except polling.TimeoutException:
+                raise reCaptchaTimeout(
+                    "DeathByCaptcha: reCaptcha solve took to long and also failed reporting the job id {}.".format(jobID)
+                )
+
+            raise reCaptchaTimeout(
+                "DeathByCaptcha: reCaptcha solve took to long to execute job id {}, aborting.".format(jobID)
+            )
+
+
+# ------------------------------------------------------------------------------- #
+
+captchaSolver()

Contents/Libraries/Shared/cloudscraper/user_agent/__init__.py

@@ -1,40 +1,117 @@
-import os
 import json
+import os
 import random
-import logging
+import re
+import sys
+import ssl
 
 from collections import OrderedDict
 
-##########################################################################################################################################################
+# ------------------------------------------------------------------------------- #
 
 
 class User_Agent():
 
-    ##########################################################################################################################################################
+    # ------------------------------------------------------------------------------- #
 
     def __init__(self, *args, **kwargs):
         self.headers = None
+        self.cipherSuite = []
         self.loadUserAgent(*args, **kwargs)
 
-    ##########################################################################################################################################################
+    # ------------------------------------------------------------------------------- #
+
+    def loadHeaders(self, user_agents, user_agent_version):
+        if user_agents.get(self.browser).get('releases').get(user_agent_version).get('headers'):
+            self.headers = user_agents.get(self.browser).get('releases').get(user_agent_version).get('headers')
+        else:
+            self.headers = user_agents.get(self.browser).get('default_headers')
+
+    # ------------------------------------------------------------------------------- #
+
+    def filterAgents(self, releases):
+        filtered = {}
+
+        for release in releases:
+            if self.mobile and releases[release]['User-Agent']['mobile']:
+                filtered[release] = filtered.get(release, []) + releases[release]['User-Agent']['mobile']
+
+            if self.desktop and releases[release]['User-Agent']['desktop']:
+                filtered[release] = filtered.get(release, []) + releases[release]['User-Agent']['desktop']
+
+        return filtered
+
+    # ------------------------------------------------------------------------------- #
+
+    def tryMatchCustom(self, user_agents):
+        for browser in user_agents:
+            for release in user_agents[browser]['releases']:
+                for platform in ['mobile', 'desktop']:
+                    if re.search(re.escape(self.custom), ' '.join(user_agents[browser]['releases'][release]['User-Agent'][platform])):
+                        self.browser = browser
+                        self.loadHeaders(user_agents, release)
+                        self.headers['User-Agent'] = self.custom
+                        self.cipherSuite = user_agents[self.browser].get('cipherSuite', [])
+                        return True
+        return False
+
+    # ------------------------------------------------------------------------------- #
 
     def loadUserAgent(self, *args, **kwargs):
-        browser = kwargs.pop('browser', 'chrome')
+        self.browser = kwargs.pop('browser', None)
 
-        user_agents = json.load(
-            open(os.path.join(os.path.dirname(__file__), 'browsers.json'), 'r'),
-            object_pairs_hook=OrderedDict
-        )
+        if isinstance(self.browser, dict):
+            self.custom = self.browser.get('custom', None)
+            self.desktop = self.browser.get('desktop', True)
+            self.mobile = self.browser.get('mobile', True)
+            self.browser = self.browser.get('browser', None)
+        else:
+            self.custom = kwargs.pop('custom', None)
+            self.desktop = kwargs.pop('desktop', True)
+            self.mobile = kwargs.pop('mobile', True)
 
-        if not user_agents.get(browser):
-            logging.error('Sorry "{}" browser User-Agent was not found.'.format(browser))
-            raise
+        if not self.desktop and not self.mobile:
+            sys.tracebacklimit = 0
+            raise RuntimeError("Sorry you can't have mobile and desktop disabled at the same time.")
 
-        user_agent = random.choice(user_agents.get(browser))
+        with open(os.path.join(os.path.dirname(__file__), 'browsers.json'), 'r') as fp:
+            user_agents = json.load(
+                fp,
+                object_pairs_hook=OrderedDict
+            )
 
-        self.headers = user_agent.get('headers')
-        self.headers['User-Agent'] = random.choice(user_agent.get('User-Agent'))
+        if self.custom:
+            if not self.tryMatchCustom(user_agents):
+                self.cipherSuite = [
+                    ssl._DEFAULT_CIPHERS,
+                    '!AES128-SHA',
+                    '!ECDHE-RSA-AES256-SHA',
+                ]
+                self.headers = OrderedDict([
+                    ('User-Agent', self.custom),
+                    ('Accept', 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8'),
+                    ('Accept-Language', 'en-US,en;q=0.9'),
+                    ('Accept-Encoding', 'gzip, deflate, br')
+                ])
+        else:
+            if self.browser and not user_agents.get(self.browser):
+                sys.tracebacklimit = 0
+                raise RuntimeError('Sorry "{}" browser User-Agent was not found.'.format(self.browser))
 
-        if not kwargs.get('allow_brotli', False):
-            if 'br' in self.headers['Accept-Encoding']:
-                self.headers['Accept-Encoding'] = ','.join([encoding for encoding in self.headers['Accept-Encoding'].split(',') if encoding.strip() != 'br']).strip()
+            if not self.browser:
+                self.browser = random.SystemRandom().choice(list(user_agents))
+
+            self.cipherSuite = user_agents.get(self.browser).get('cipherSuite', [])
+
+            filteredAgents = self.filterAgents(user_agents.get(self.browser).get('releases'))
+
+            user_agent_version = random.SystemRandom().choice(list(filteredAgents))
+
+            self.loadHeaders(user_agents, user_agent_version)
+
+            self.headers['User-Agent'] = random.SystemRandom().choice(filteredAgents[user_agent_version])
+
+        if not kwargs.get('allow_brotli', False) and 'br' in self.headers['Accept-Encoding']:
+            self.headers['Accept-Encoding'] = ','.join([
+                encoding for encoding in self.headers['Accept-Encoding'].split(',') if encoding.strip() != 'br'
+            ]).strip()

Contents/Libraries/Shared/provider_test.sh

@@ -43,6 +43,8 @@ python -c "import logging; logging.basicConfig(level=logging.DEBUG); logging.get
 # subscenter:list
 python -c "import logging; logging.basicConfig(level=logging.DEBUG); logging.getLogger('rebulk').setLevel(logging.WARNING); import subliminal_patch, subliminal; subliminal.region.configure('dogpile.cache.memory'); from subliminal_patch.core import SZProviderPool; from babelfish import Language; from subliminal.core import scan_video; print SZProviderPool(providers=['subscenter'], )['subscenter'].list_subtitles(scan_video('FULL_PATH'), languages=[Language('heb')])"
 
+# subscene:list
+python -c "import logging; logging.basicConfig(level=logging.DEBUG); logging.getLogger('rebulk').setLevel(logging.WARNING); import subliminal_patch, subliminal; subliminal.region.configure('dogpile.cache.memory'); from subliminal_patch.core import SZProviderPool; from subzero.language import Language; from subzero.video import parse_video; SZProviderPool(providers=['subscene'], provider_configs={'subscene': {'username': 'USERNAME', 'password': 'PASSWORD'}})['subscene'].list_subtitles(parse_video('FILENAME', {}, {'type': 'episode'}, dry_run=True), languages=[Language('eng')])"
 
 # refining
 python -c "import logging; logging.basicConfig(level=logging.DEBUG); logging.getLogger('rebulk').setLevel(logging.WARNING); import os; os.environ['U1pfT01EQl9LRVk'] = '789CF30DAC2C8B0AF433F5C9AD34290A712DF30D7135F12D0FB3E502006FDE081E'; import subliminal_patch, subliminal; subliminal.region.configure('dogpile.cache.memory'); from subzero.video import parse_video, refine_video; video = parse_video('FILE_NAME', {'type': 'episode'}, dry_run=True); print refine_video(video)"

Contents/Libraries/Shared/pysubs2/exceptions.py

@@ -12,3 +12,6 @@ class UnknownFormatIdentifierError(Pysubs2Error):
 
 class FormatAutodetectionError(Pysubs2Error):
     """Subtitle format is ambiguous or unknown."""
+
+class ContentNotUsable(Pysubs2Error):
+    """Current content not usable for specified format"""

Contents/Libraries/Shared/pysubs2/ssastyle.py

@@ -41,6 +41,7 @@ class SSAStyle(object):
         self.italic = False #: Italic
         self.underline = False #: Underline (ASS only)
         self.strikeout = False #: Strikeout (ASS only)
+        self.drawing = False #: Drawing (ASS only, see http://docs.aegisub.org/3.1/ASS_Tags/#drawing-tags
         self.scalex = 100.0 #: Horizontal scaling (ASS only)
         self.scaley = 100.0 #: Vertical scaling (ASS only)
         self.spacing = 0.0 #: Letter spacing (ASS only)

Contents/Libraries/Shared/pysubs2/subrip.py

@@ -5,6 +5,7 @@ from .formatbase import FormatBase
 from .ssaevent import SSAEvent
 from .ssastyle import SSAStyle
 from .substation import parse_tags
+from .exceptions import ContentNotUsable
 from .time import ms_to_times, make_time, TIMESTAMP, timestamp_to_ms
 
 #: Largest timestamp allowed in SubRip, ie. 99:59:59,999.
@@ -81,6 +82,7 @@ class SubripFormat(FormatBase):
                 if sty.italic: fragment = "<i>%s</i>" % fragment
                 if sty.underline: fragment = "<u>%s</u>" % fragment
                 if sty.strikeout: fragment = "<s>%s</s>" % fragment
+                if sty.drawing: raise ContentNotUsable
                 body.append(fragment)
 
             return re.sub("\n+", "\n", "".join(body).strip())
@@ -90,7 +92,10 @@ class SubripFormat(FormatBase):
         for i, line in enumerate(visible_lines, 1):
             start = ms_to_timestamp(line.start)
             end = ms_to_timestamp(line.end)
-            text = prepare_text(line.text, subs.styles.get(line.style, SSAStyle.DEFAULT_STYLE))
+            try:
+                text = prepare_text(line.text, subs.styles.get(line.style, SSAStyle.DEFAULT_STYLE))
+            except ContentNotUsable:
+                continue
 
             print("%d" % i, file=fp) # Python 2.7 compat
             print(start, "-->", end, file=fp)

Contents/Libraries/Shared/pysubs2/substation.py

@@ -110,7 +110,7 @@ def parse_tags(text, style=SSAStyle.DEFAULT_STYLE, styles={}):
     
     def apply_overrides(all_overrides):
         s = style.copy()
-        for tag in re.findall(r"\\[ibus][10]|\\r[a-zA-Z_0-9 ]*", all_overrides):
+        for tag in re.findall(r"\\[ibusp][0-9]|\\r[a-zA-Z_0-9 ]*", all_overrides):
             if tag == r"\r":
                 s = style.copy() # reset to original line style
             elif tag.startswith(r"\r"):
@@ -122,6 +122,13 @@ def parse_tags(text, style=SSAStyle.DEFAULT_STYLE, styles={}):
                 elif "b" in tag: s.bold = "1" in tag
                 elif "u" in tag: s.underline = "1" in tag
                 elif "s" in tag: s.strikeout = "1" in tag
+                elif "p" in tag:
+                    try:
+                        scale = int(tag[2:])
+                    except (ValueError, IndexError):
+                        continue
+
+                    s.drawing = scale > 0
         return s
     
     overrides = SSAEvent.OVERRIDE_SEQUENCE.findall(text)

Contents/Libraries/Shared/subliminal/exceptions.py

@@ -27,3 +27,8 @@ class ServiceUnavailable(ProviderError):
 class DownloadLimitExceeded(ProviderError):
     """Exception raised by providers when download limit is exceeded."""
     pass
+
+
+class DownloadLimitPerDayExceeded(ProviderError):
+    """Exception raised by providers when download limit is exceeded."""
+    pass

Contents/Libraries/Shared/subliminal_patch/core.py

@@ -264,7 +264,7 @@ class SZProviderPool(ProviderPool):
                     requests.exceptions.SSLError,
                     requests.Timeout,
                     socket.timeout):
-                logger.error('Provider %r connection error', subtitle.provider_name)
+                logger.exception('Provider %r connection error', subtitle.provider_name)
 
             except ResponseNotReady:
                 logger.error('Provider %r response error, reinitializing', subtitle.provider_name)
@@ -354,15 +354,16 @@ class SZProviderPool(ProviderPool):
             orig_matches = matches.copy()
 
             logger.debug('%r: Found matches %r', s, matches)
+            score, score_without_hash = compute_score(matches, s, video, hearing_impaired=use_hearing_impaired)
             unsorted_subtitles.append(
-                (s, compute_score(matches, s, video, hearing_impaired=use_hearing_impaired), matches, orig_matches))
+                (s, score, score_without_hash, matches, orig_matches))
 
         # sort subtitles by score
-        scored_subtitles = sorted(unsorted_subtitles, key=operator.itemgetter(1), reverse=True)
+        scored_subtitles = sorted(unsorted_subtitles, key=operator.itemgetter(1, 2), reverse=True)
 
         # download best subtitles, falling back on the next on error
         downloaded_subtitles = []
-        for subtitle, score, matches, orig_matches in scored_subtitles:
+        for subtitle, score, score_without_hash, matches, orig_matches in scored_subtitles:
             # check score
             if score < min_score:
                 logger.info('%r: Score %d is below min_score (%d)', subtitle, score, min_score)

Contents/Libraries/Shared/subliminal_patch/http.py

@@ -20,7 +20,7 @@ from exceptions import APIThrottled
 from dogpile.cache.api import NO_VALUE
 from subliminal.cache import region
 from subliminal_patch.pitcher import pitchers
-from cloudscraper import CloudScraper
+from cloudscraper import CloudScraper, User_Agent
 
 try:
     import brotli
@@ -89,7 +89,9 @@ class CFSession(CloudScraper):
 
         # Check if Cloudflare anti-bot is on
         try:
-            if self.isChallengeRequest(resp):
+            print repr(resp)
+            if self.is_IUAM_Challenge(resp):
+                print "TRYYYYYYYYYY"
                 if resp.request.method != 'GET':
                     # Work around if the initial request is not a GET,
                     # Supersede with a GET then re-request the original METHOD.
@@ -97,9 +99,10 @@ class CFSession(CloudScraper):
                     resp = ourSuper.request(method, url, *args, **kwargs)
                 else:
                     # Solve Challenge
-                    resp = self.sendChallengeResponse(resp, **kwargs)
+                    resp = self.Challenge_Response(resp, **kwargs)
 
         except ValueError, e:
+            print "YEEEEEEEEEEEEEE"
             if e.message == "Captcha":
                 parsed_url = urlparse(url)
                 domain = parsed_url.netloc
@@ -241,12 +244,20 @@ class SubZeroRequestsTransport(xmlrpclib.SafeTransport):
     # change our user agent to reflect Requests
     user_agent = "Python XMLRPC with Requests (python-requests.org)"
     proxies = None
+    xm_ver = 1
+    session_var = "PHPSESSID"
 
     def __init__(self, use_https=True, verify=None, user_agent=None, timeout=10, *args, **kwargs):
         self.verify = pem_file if verify is None else verify
         self.use_https = use_https
         self.user_agent = user_agent if user_agent is not None else self.user_agent
         self.timeout = timeout
+        self.session = requests.Session()
+        self.session.headers['User-Agent'] = self.user_agent
+        # if 'requests' in self.session.headers['User-Agent']:
+        #     # Set a random User-Agent if no custom User-Agent has been set
+        #     self.session.headers = User_Agent(allow_brotli=False).headers
+
         proxy = os.environ.get('SZ_HTTP_PROXY')
         if proxy:
             self.proxies = {
@@ -260,18 +271,40 @@ class SubZeroRequestsTransport(xmlrpclib.SafeTransport):
         """
         Make an xmlrpc request.
         """
-        headers = {'User-Agent': self.user_agent}
         url = self._build_url(host, handler)
+        cache_key = "xm%s_%s" % (self.xm_ver, host)
+
+        old_sessvar = self.session.cookies.get(self.session_var, "")
+        if not old_sessvar:
+            data = region.get(cache_key)
+            if data is not NO_VALUE:
+                logger.debug("Trying to re-use headers/cookies for %s" % host)
+                self.session.cookies, self.session.headers = data
+                old_sessvar = self.session.cookies.get(self.session_var, "")
+
         try:
-            resp = requests.post(url, data=request_body, headers=headers,
-                                 stream=True, timeout=self.timeout, proxies=self.proxies,
-                                 verify=self.verify)
+            resp = self.session.post(url, data=request_body,
+                                     stream=True, timeout=self.timeout, proxies=self.proxies,
+                                     verify=self.verify)
+
+            if self.session_var in resp.cookies and resp.cookies[self.session_var] != old_sessvar:
+                logger.debug("Storing %s cookies" % host)
+                region.set(cache_key, [self.session.cookies, self.session.headers])
         except ValueError:
+            logger.debug("Wiping cookies/headers cache (VE) for %s" % host)
+            region.delete(cache_key)
             raise
         except Exception:
+            logger.debug("Wiping cookies/headers cache (EX) for %s" % host)
+            region.delete(cache_key)
             raise  # something went wrong
         else:
-            resp.raise_for_status()
+            try:
+                resp.raise_for_status()
+            except requests.exceptions.HTTPError:
+                logger.debug("Wiping cookies/headers cache (RE) for %s" % host)
+                region.delete(cache_key)
+                raise
 
             try:
                 if 'x-ratelimit-remaining' in resp.headers and int(resp.headers['x-ratelimit-remaining']) <= 2:

Contents/Libraries/Shared/subliminal_patch/providers/addic7ed.py

@@ -2,6 +2,8 @@
 import logging
 import re
 import datetime
+import types
+
 import subliminal
 import time
 
@@ -10,7 +12,8 @@ from random import randint
 from dogpile.cache.api import NO_VALUE
 from requests import Session
 from subliminal.cache import region
-from subliminal.exceptions import DownloadLimitExceeded, AuthenticationError, ConfigurationError
+from subliminal.exceptions import DownloadLimitExceeded, AuthenticationError, ConfigurationError, \
+    DownloadLimitPerDayExceeded
 from subliminal.providers.addic7ed import Addic7edProvider as _Addic7edProvider, \
     Addic7edSubtitle as _Addic7edSubtitle, ParserBeautifulSoup
 from subliminal.subtitle import fix_line_ending
@@ -64,6 +67,7 @@ class Addic7edProvider(_Addic7edProvider):
         'slk', 'slv', 'spa', 'sqi', 'srp', 'swe', 'tha', 'tur', 'ukr', 'vie', 'zho'
     ]} | {Language.fromietf(l) for l in ["sr-Latn", "sr-Cyrl"]}
 
+    vip = False
     USE_ADDICTED_RANDOM_AGENTS = False
     hearing_impaired_verifiable = True
     subtitle_class = Addic7edSubtitle
@@ -72,9 +76,10 @@ class Addic7edProvider(_Addic7edProvider):
     sanitize_characters = {'-', ':', '(', ')', '.', '/'}
     last_show_ids_fetch_key = "addic7ed_last_id_fetch"
 
-    def __init__(self, username=None, password=None, use_random_agents=False):
+    def __init__(self, username=None, password=None, use_random_agents=False, is_vip=False):
         super(Addic7edProvider, self).__init__(username=username, password=password)
         self.USE_ADDICTED_RANDOM_AGENTS = use_random_agents
+        self.vip = is_vip
 
         if not all((username, password)):
             raise ConfigurationError('Username and password must be specified')
@@ -397,6 +402,27 @@ class Addic7edProvider(_Addic7edProvider):
         return subtitles
 
     def download_subtitle(self, subtitle):
+        last_dls = region.get("addic7ed_dls")
+        now = datetime.datetime.now()
+        one_day = datetime.timedelta(hours=24)
+
+        def raise_limit():
+            logger.info("Addic7ed: Downloads per day exceeded (%s)", cap)
+            raise DownloadLimitPerDayExceeded
+
+        if not isinstance(last_dls, types.ListType):
+            last_dls = []
+        else:
+            # filter all non-expired DLs
+            last_dls = filter(lambda t: t + one_day > now, last_dls)
+            region.set("addic7ed_dls", last_dls)
+
+        cap = self.vip and 80 or 40
+        amount = len(last_dls)
+
+        if amount >= cap:
+            raise_limit()
+
         # download the subtitle
         r = self.session.get(self.server_url + subtitle.download_link, headers={'Referer': subtitle.page_link},
                              timeout=10)
@@ -408,7 +434,7 @@ class Addic7edProvider(_Addic7edProvider):
         if not r.content:
             # Provider wrongful return a status of 304 Not Modified with an empty content
             # raise_for_status won't raise exception for that status code
-            logger.error('Unable to download subtitle. No data returned from provider')
+            logger.error('Addic7ed: Unable to download subtitle. No data returned from provider')
             return
 
         # detect download limit exceeded
@@ -416,3 +442,10 @@ class Addic7edProvider(_Addic7edProvider):
             raise DownloadLimitExceeded
 
         subtitle.content = fix_line_ending(r.content)
+        last_dls.append(datetime.datetime.now())
+        region.set("addic7ed_dls", last_dls)
+        logger.info("Addic7ed: Used %s/%s downloads", amount + 1, cap)
+
+        if amount + 1 >= cap:
+            raise_limit()
+

Contents/Libraries/Shared/subliminal_patch/providers/bsplayer.py

@@ -19,9 +19,11 @@ from xml.etree import ElementTree
 
 logger = logging.getLogger(__name__)
 
+
 class BSPlayerSubtitle(Subtitle):
     """BSPlayer Subtitle."""
     provider_name = 'bsplayer'
+    hash_verifiable = True
 
     def __init__(self, language, filename, subtype, video, link):
         super(BSPlayerSubtitle, self).__init__(language)
@@ -41,27 +43,12 @@ class BSPlayerSubtitle(Subtitle):
 
     def get_matches(self, video):
         matches = set()
-
-        video_filename = video.name
-        video_filename = os.path.basename(video_filename)
-        video_filename, _ = os.path.splitext(video_filename)
-        video_filename = sanitize_release_group(video_filename)
-
-        subtitle_filename = self.filename
-        subtitle_filename = os.path.basename(subtitle_filename)
-        subtitle_filename, _ = os.path.splitext(subtitle_filename)
-        subtitle_filename = sanitize_release_group(subtitle_filename)
-
-
         matches |= guess_matches(video, guessit(self.filename))
-
-        matches.add(id(self))
         matches.add('hash')
 
         return matches
 
 
-
 class BSPlayerProvider(Provider):
     """BSPlayer Provider."""
     languages = {Language('por', 'BR')} | {Language(l) for l in [
@@ -69,6 +56,7 @@ class BSPlayerProvider(Provider):
         'ron', 'rus', 'spa', 'swe', 'tur', 'ukr', 'zho'
     ]}
     SEARCH_THROTTLE = 8
+    hash_verifiable = True
 
     # batantly based on kodi's bsplayer plugin
     # also took from BSPlayer-Subtitles-Downloader
@@ -108,18 +96,11 @@ class BSPlayerProvider(Provider):
                 res = self.session.post(self.search_url, data)
                 return ElementTree.fromstring(res.text)
 
-                ### with requests
-                # res = requests.post(
-                #     url=self.search_url,
-                #     data=data,
-                #     headers=headers
-                # ) 
-                # return ElementTree.fromstring(res.text)
-               
             except Exception as ex:
                 logger.info("ERROR: %s." % ex)
                 if func_name == 'logIn':
                     self.search_url = self.get_sub_domain()
+
                 sleep(1)
         logger.info('ERROR: Too many tries (%d)...' % tries)
         raise Exception('Too many tries...')
@@ -167,7 +148,6 @@ class BSPlayerProvider(Provider):
             # language_ids = 'spa'
             language_ids = ','.join(sorted(l.opensubtitles for l in language))
 
-
         if video.imdb_id is None:
             imdbId = '*'
         else:
@@ -193,13 +173,13 @@ class BSPlayerProvider(Provider):
         if items:
             logger.info("Subtitles Found.")
             for item in items:
-                subID=item.find('subID').text
-                subDownloadLink=item.find('subDownloadLink').text
-                subLang= Language.fromopensubtitles(item.find('subLang').text)
-                subName=item.find('subName').text
-                subFormat=item.find('subFormat').text
+                subID = item.find('subID').text
+                subDownloadLink = item.find('subDownloadLink').text
+                subLang = Language.fromopensubtitles(item.find('subLang').text)
+                subName = item.find('subName').text
+                subFormat = item.find('subFormat').text
                 subtitles.append(
-                    BSPlayerSubtitle(subLang,subName, subFormat, video, subDownloadLink)
+                    BSPlayerSubtitle(subLang, subName, subFormat, video, subDownloadLink)
                 )
         return subtitles
 
@@ -207,9 +187,9 @@ class BSPlayerProvider(Provider):
         return self.query(video, video.hashes['bsplayer'], languages)
 
     def get_sub_domain(self):
-    # s1-9, s101-109
+        # s1-9, s101-109
         SUB_DOMAINS = ['s1', 's2', 's3', 's4', 's5', 's6', 's7', 's8', 's9',
-                's101', 's102', 's103', 's104', 's105', 's106', 's107', 's108', 's109']
+                       's101', 's102', 's103', 's104', 's105', 's106', 's107', 's108', 's109']
         API_URL_TEMPLATE = "http://{sub_domain}.api.bsplayer-subtitles.com/v1.php"
         sub_domains_end = len(SUB_DOMAINS) - 1
         return API_URL_TEMPLATE.format(sub_domain=SUB_DOMAINS[random.randint(0, sub_domains_end)])
@@ -226,10 +206,8 @@ class BSPlayerProvider(Provider):
                 raise ValueError('Error 500 on server')
 
             with gzip.GzipFile(fileobj=io.BytesIO(res.content)) as gf:
-                subtitle.content = gf.read() 
+                subtitle.content = gf.read()
                 subtitle.normalize()
 
             return subtitle
         raise ValueError('Problems conecting to the server')
-
-

Contents/Libraries/Shared/subliminal_patch/providers/opensubtitles.py

@@ -105,7 +105,7 @@ class OpenSubtitlesProvider(ProviderRetryMixin, _OpenSubtitlesProvider):
 
     def __init__(self, username=None, password=None, use_tag_search=False, only_foreign=False, also_foreign=False,
                  skip_wrong_fps=True, is_vip=False, use_ssl=True, timeout=15):
-        if any((username, password)) and not all((username, password)):
+        if not all((username, password)):
             raise ConfigurationError('Username and password must be specified')
 
         self.username = username or ''
@@ -154,6 +154,7 @@ class OpenSubtitlesProvider(ProviderRetryMixin, _OpenSubtitlesProvider):
         logger.debug('Logged in with token %r', self.token[:10]+"X"*(len(self.token)-10))
 
         region.set("os_token", self.token)
+        time.sleep(1)
 
     def use_token_or_login(self, func):
         if not self.token:
@@ -162,6 +163,7 @@ class OpenSubtitlesProvider(ProviderRetryMixin, _OpenSubtitlesProvider):
         try:
             return func()
         except Unauthorized:
+            logger.debug("Token not valid, logging in again")
             self.log_in()
             return func()
 
@@ -197,16 +199,11 @@ class OpenSubtitlesProvider(ProviderRetryMixin, _OpenSubtitlesProvider):
                     return
 
             logger.error("Login failed, please check your credentials")
+            raise
                 
     def terminate(self):
-        if self.token:
-            try:
-                checked(lambda: self.server.LogOut(self.token))
-            except:
-                logger.error("Logout failed: %s", traceback.format_exc())
-
         self.server = None
-        self.token = None
+        #self.token = None
 
     def list_subtitles(self, video, languages):
         """

Contents/Libraries/Shared/subliminal_patch/score.py

@@ -60,6 +60,8 @@ def compute_score(matches, subtitle, video, hearing_impaired=None):
     episode_hash_valid_if = {"series", "season", "episode", "format"}
     movie_hash_valid_if = {"video_codec", "format"}
 
+    orig_matches = matches.copy()
+
     # on hash match, discard everything else
     if subtitle.hash_verifiable:
         if 'hash' in matches:
@@ -83,41 +85,47 @@ def compute_score(matches, subtitle, video, hearing_impaired=None):
         matches &= {'hash'}
 
     # handle equivalent matches
+    eq_matches = set()
     if is_episode:
         if 'title' in matches:
             logger.debug('Adding title match equivalent')
-            matches.add('episode')
+            eq_matches.add('episode')
         if 'series_imdb_id' in matches:
             logger.debug('Adding series_imdb_id match equivalent')
-            matches |= {'series', 'year'}
+            eq_matches |= {'series', 'year'}
         if 'imdb_id' in matches:
             logger.debug('Adding imdb_id match equivalents')
-            matches |= {'series', 'year', 'season', 'episode'}
+            eq_matches |= {'series', 'year', 'season', 'episode'}
         if 'tvdb_id' in matches:
             logger.debug('Adding tvdb_id match equivalents')
-            matches |= {'series', 'year', 'season', 'episode', 'title'}
+            eq_matches |= {'series', 'year', 'season', 'episode', 'title'}
         if 'series_tvdb_id' in matches:
             logger.debug('Adding series_tvdb_id match equivalents')
-            matches |= {'series', 'year'}
+            eq_matches |= {'series', 'year'}
 
         # specials
         if video.is_special and 'title' in matches and 'series' in matches \
                 and 'year' in matches:
             logger.debug('Adding special title match equivalent')
-            matches |= {'season', 'episode'}
+            eq_matches |= {'season', 'episode'}
 
     elif is_movie:
         if 'imdb_id' in matches:
             logger.debug('Adding imdb_id match equivalents')
-            matches |= {'title', 'year'}
+            eq_matches |= {'title', 'year'}
+
+    matches |= eq_matches
 
     # handle hearing impaired
     if hearing_impaired is not None and subtitle.hearing_impaired == hearing_impaired:
         logger.debug('Matched hearing_impaired')
         matches.add('hearing_impaired')
+        orig_matches.add('hearing_impaired')
 
     # compute the score
     score = sum((scores.get(match, 0) for match in matches))
     logger.info('%r: Computed score %r with final matches %r', subtitle, score, matches)
 
-    return score
+    score_without_hash = sum((scores.get(match, 0) for match in orig_matches | eq_matches if match != "hash"))
+
+    return score, score_without_hash

Contents/Libraries/Shared/subliminal_patch/subtitle.py

@@ -278,6 +278,12 @@ class Subtitle(Subtitle_):
 
     @classmethod
     def pysubs2_to_unicode(cls, sub, format="srt"):
+        """
+        this is a modified version of pysubs2.SubripFormat.to_file with special handling for drawing tags in ASS
+        :param sub:
+        :param format:
+        :return:
+        """
         def ms_to_timestamp(ms, mssep=","):
             """Convert ms to 'HH:MM:SS,mmm'"""
             # XXX throw on overflow/underflow?
@@ -289,9 +295,12 @@ class Subtitle(Subtitle_):
         def prepare_text(text, style):
             body = []
             for fragment, sty in parse_tags(text, style, sub.styles):
-                fragment = fragment.replace(ur"\h", u" ")
-                fragment = fragment.replace(ur"\n", u"\n")
-                fragment = fragment.replace(ur"\N", u"\n")
+                fragment = fragment.replace(r"\h", u" ")
+                fragment = fragment.replace(r"\n", u"\n")
+                fragment = fragment.replace(r"\N", u"\n")
+                if sty.drawing:
+                    raise pysubs2.ContentNotUsable
+
                 if format == "srt":
                     if sty.italic:
                         fragment = u"<i>%s</i>" % fragment
@@ -323,7 +332,10 @@ class Subtitle(Subtitle_):
         for i, line in enumerate(visible_lines, 1):
             start = ms_to_timestamp(line.start, mssep=mssep)
             end = ms_to_timestamp(line.end, mssep=mssep)
-            text = prepare_text(line.text, sub.styles.get(line.style, SSAStyle.DEFAULT_STYLE))
+            try:
+                text = prepare_text(line.text, sub.styles.get(line.style, SSAStyle.DEFAULT_STYLE))
+            except pysubs2.ContentNotUsable:
+                continue
 
             out.append(u"%d\n" % i)
             out.append(u"%s --> %s\n" % (start, end))

Contents/Libraries/Shared/submod_test.py

@@ -24,6 +24,7 @@ if debug:
 sub = Subtitle(Language.fromietf("eng"), mods=["common", "remove_HI", "OCR_fixes", "fix_uppercase", "shift_offset(ms=0,s=1)"])
 sub.content = open(fn).read()
 sub.normalize()
+sub.is_valid()
 content = sub.get_modified_content(debug=True)
 
 #submod = SubMod(debug=debug)

Contents/Libraries/Shared/subzero/modification/exc.py

@@ -0,0 +1,7 @@
+# coding=utf-8
+class EmptyEntryError(Exception):
+    pass
+
+
+class EmptyLineError(Exception):
+    pass

Contents/Libraries/Shared/subzero/modification/main.py

@@ -6,7 +6,8 @@ import pysubs2
 import logging
 import time
 
-from mods import EMPTY_TAG_PROCESSOR, EmptyEntryError
+from mods import EMPTY_TAG_PROCESSOR
+from exc import EmptyEntryError
 from registry import registry
 from subzero.language import Language
 
@@ -300,11 +301,11 @@ class SubtitleModifications(object):
                     mod = self.initialized_mods[identifier]
 
                     try:
-                        line = mod.modify(line.strip(), entry=entry.text, debug=self.debug, parent=self, index=index,
+                        line = mod.modify(line.strip(), entry=t, debug=self.debug, parent=self, index=index,
                                           **args)
                     except EmptyEntryError:
                         if self.debug:
-                            logger.debug(u"%d: %s: %r -> ''", index, identifier, entry.text)
+                            logger.debug(u"%d: %s: %r -> ''", index, identifier, t)
                         skip_entry = True
                         break
 
@@ -329,11 +330,11 @@ class SubtitleModifications(object):
                     mod = self.initialized_mods[identifier]
 
                     try:
-                        line = mod.modify(line.strip(), entry=entry.text, debug=self.debug, parent=self, index=index,
+                        line = mod.modify(line.strip(), entry=t, debug=self.debug, parent=self, index=index,
                                           procs=["last_process"], **args)
                     except EmptyEntryError:
                         if self.debug:
-                            logger.debug(u"%d: %s: %r -> ''", index, identifier, entry.text)
+                            logger.debug(u"%d: %s: %r -> ''", index, identifier, t)
                         skip_entry = True
                         break
 

Contents/Libraries/Shared/subzero/modification/mods/__init__.py

@@ -107,9 +107,3 @@ empty_line_post_processors = [
 ]
 
 
-class EmptyEntryError(Exception):
-    pass
-
-
-class EmptyLineError(Exception):
-    pass

Contents/Libraries/Shared/subzero/modification/mods/common.py

@@ -7,6 +7,7 @@ from subzero.modification.mods import SubtitleTextModification, empty_line_post_
 from subzero.modification.processors import FuncProcessor
 from subzero.modification.processors.re_processor import NReProcessor
 from subzero.modification import registry
+from tld import get_tld
 
 
 ENGLISH = Language("eng")
@@ -28,7 +29,7 @@ class CommonFixes(SubtitleTextModification):
         NReProcessor(re.compile(r'(?u)(\w|\b|\s|^)(-\s?-{1,2})'), ur"\1—", name="CM_multidash"),
 
         # line = _/-/\s
-        NReProcessor(re.compile(r'(?u)(^\W*[-_.:>~]+\W*$)'), "", name="<CM_non_word_only"),
+        NReProcessor(re.compile(r'(?u)(^\W*[-_.:<>~"\']+\W*$)'), "", name="CM_non_word_only"),
 
         # remove >>
         NReProcessor(re.compile(r'(?u)^\s?>>\s*'), "", name="CM_leading_crocodiles"),
@@ -113,7 +114,9 @@ class CommonFixes(SubtitleTextModification):
         NReProcessor(re.compile(r'(?u)(?:(?<=^)|(?<=\w)) +([!?.,](?![!?.,]| \.))'), r"\1", name="CM_punctuation_space"),
 
         # add space after punctuation
-        NReProcessor(re.compile(r'(?u)([!?.,:])([A-zÀ-ž]{2,})'), r"\1 \2", name="CM_punctuation_space2"),
+        NReProcessor(re.compile(r'(?u)(([^\s]*)([!?.,:])([A-zÀ-ž]{2,}))'),
+                     lambda match: u"%s%s %s" % (match.group(2), match.group(3), match.group(4)) if not get_tld(match.group(1), fail_silently=True, fix_protocol=True) else match.group(1),
+                     name="CM_punctuation_space2"),
 
         # fix lowercase I in english
         NReProcessor(re.compile(r'(?u)(\b)i(\b)'), r"\1I\2", name="CM_EN_lowercase_i",

Contents/Libraries/Shared/subzero/modification/mods/hearing_impaired.py

@@ -1,7 +1,8 @@
 # coding=utf-8
 import re
 
-from subzero.modification.mods import SubtitleTextModification, empty_line_post_processors, EmptyEntryError, TAG
+from subzero.modification.mods import SubtitleTextModification, empty_line_post_processors, TAG
+from subzero.modification.exc import EmptyEntryError
 from subzero.modification.processors.re_processor import NReProcessor
 from subzero.modification import registry
 
@@ -46,7 +47,7 @@ class HearingImpaired(SubtitleTextModification):
                      name="HI_before_colon_noncaps"),
 
         # brackets (only remove if at least 3 chars in brackets)
-        NReProcessor(re.compile(ur'(?sux)-?%(t)s[([][^([)\]]+?(?=[A-zÀ-ž"\'.]{3,})[^([)\]]+[)\]][\s:]*%(t)s' %
+        NReProcessor(re.compile(ur'(?sux)-?%(t)s["\']*[([][^([)\]]+?(?=[A-zÀ-ž"\'.]{3,})[^([)\]]+[)\]]["\']*[\s:]*%(t)s' %
                                 {"t": TAG}), "", name="HI_brackets"),
 
         #NReProcessor(re.compile(ur'(?sux)-?%(t)s[([]%(t)s(?=[A-zÀ-ž"\'.]{3,})[^([)\]]+%(t)s$' % {"t": TAG}),
@@ -90,8 +91,8 @@ class HearingImpaired(SubtitleTextModification):
                      "", name="HI_music_symbols_only"),
 
         # remove music entries
-        NReProcessor(re.compile(ur'(?ums)(^[-\s>~]*[♫♪]+\s*.+|.+\s*[♫♪]+\s*$)'),
-                     "", name="HI_music"),
+        NReProcessor(re.compile(ur'(?ums)(^[-\s>~]*[*#¶♫♪]+\s*.+|.+\s*[*#¶♫♪]+\s*$)'),
+                     "", name="HI_music", entry=True),
     ]
 
 

Contents/Libraries/Shared/subzero/modification/processors/__init__.py

@@ -10,7 +10,7 @@ class Processor(object):
     supported = None
     enabled = True
 
-    def __init__(self, name=None, parent=None, supported=None):
+    def __init__(self, name=None, parent=None, supported=None, **kwargs):
         self.name = name
         self.parent = parent
         self.supported = supported if supported else lambda parent: True
@@ -35,7 +35,7 @@ class Processor(object):
 class FuncProcessor(Processor):
     func = None
 
-    def __init__(self, func, name=None, parent=None, supported=None):
+    def __init__(self, func, name=None, parent=None, supported=None, **kwargs):
         super(FuncProcessor, self).__init__(name=name, supported=supported)
         self.func = func
 

Contents/Libraries/Shared/subzero/modification/processors/re_processor.py

@@ -2,6 +2,7 @@
 import re
 import logging
 
+from subzero.modification.exc import EmptyEntryError
 from subzero.modification.processors import Processor
 
 logger = logging.getLogger(__name__)
@@ -14,13 +15,22 @@ class ReProcessor(Processor):
     pattern = None
     replace_with = None
 
-    def __init__(self, pattern, replace_with, name=None, supported=None):
+    def __init__(self, pattern, replace_with, name=None, supported=None, entry=False, **kwargs):
         super(ReProcessor, self).__init__(name=name, supported=supported)
         self.pattern = pattern
         self.replace_with = replace_with
+        self.use_entry = entry
 
-    def process(self, content, debug=False, **kwargs):
-        return self.pattern.sub(self.replace_with, content)
+    def process(self, content, debug=False, entry=None, **kwargs):
+        if not self.use_entry:
+            return self.pattern.sub(self.replace_with, content)
+
+        ret = self.pattern.sub(self.replace_with, entry)
+        if not ret:
+            raise EmptyEntryError()
+        elif ret != entry:
+            return ret
+        return content
 
 
 class NReProcessor(ReProcessor):
@@ -36,7 +46,7 @@ class MultipleWordReProcessor(ReProcessor):
     }
     replaces found key in pattern with the corresponding value in data
     """
-    def __init__(self, snr_dict, name=None, parent=None, supported=None):
+    def __init__(self, snr_dict, name=None, parent=None, supported=None, **kwargs):
         super(ReProcessor, self).__init__(name=name, supported=supported)
         self.snr_dict = snr_dict
 

Contents/Libraries/Shared/subzero/modification/processors/string_processor.py

@@ -12,7 +12,7 @@ class StringProcessor(Processor):
     String replacement processor base
     """
 
-    def __init__(self, search, replace, name=None, parent=None, supported=None):
+    def __init__(self, search, replace, name=None, parent=None, supported=None, **kwargs):
         super(StringProcessor, self).__init__(name=name, supported=supported)
         self.search = search
         self.replace = replace
@@ -31,7 +31,7 @@ class MultipleLineProcessor(Processor):
         "data": {"old_value": "new_value"}
     }
     """
-    def __init__(self, snr_dict, name=None, parent=None, supported=None):
+    def __init__(self, snr_dict, name=None, parent=None, supported=None, **kwargs):
         super(MultipleLineProcessor, self).__init__(name=name, supported=supported)
         self.snr_dict = snr_dict
 

Contents/Libraries/Shared/test.srt

@@ -19,6 +19,8 @@ I can't keep running. L can't!
 <b>i don't know. Some kind of wrong "1 00" number---
 of signal, drawing the Tardis off.... course.</b>
 # I'm singing in the rain
+www.website.com
+www.nowebsite.badlol
 
 4
 00:00:16,099 --> 00:00:17,224

Contents/Libraries/Shared/tld/__init__.py

@@ -0,0 +1,14 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals
+from .utils import get_fld, get_tld, get_tld_names, is_tld, parse_tld, Result, update_tld_names
+__title__ = u'tld'
+__version__ = u'0.11.10'
+__author__ = u'Artur Barseghyan'
+__copyright__ = u'2013-2019 Artur Barseghyan'
+__license__ = u'MPL-1.1 OR GPL-2.0-only OR LGPL-2.1-or-later'
+__all__ = (u'get_fld', u'get_tld', u'get_tld_names', u'is_tld',
+           u'parse_tld', u'Result', u'update_tld_names')

Contents/Libraries/Shared/tld/base.py

@@ -0,0 +1,57 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals
+from six import with_metaclass as _py_backwards_six_withmetaclass
+from codecs import open as codecs_open
+try:
+    from urllib.request import urlopen
+except ImportError:
+    from six.moves.urllib.request import urlopen as urlopen
+from .exceptions import TldIOError, TldImproperlyConfigured
+from .helpers import project_dir
+from .registry import Registry
+__author__ = u'Artur Barseghyan'
+__copyright__ = u'2013-2019 Artur Barseghyan'
+__license__ = u'MPL-1.1 OR GPL-2.0-only OR LGPL-2.1-or-later'
+__all__ = (u'BaseTLDSourceParser',)
+
+
+class BaseTLDSourceParser(
+        _py_backwards_six_withmetaclass(Registry, *[object])):
+    u'Base TLD source parser.'
+    uid = None
+    source_url = None
+    local_path = None
+
+    @classmethod
+    def validate(cls):
+        u'Constructor.'
+        if (not cls.uid):
+            raise TldImproperlyConfigured(
+                u'The `uid` property of the TLD source parser shall be defined.')
+
+    @classmethod
+    def get_tld_names(cls, fail_silently=False, retry_count=0):
+        u'Get tld names.\n\n        :param fail_silently:\n        :param retry_count:\n        :return:\n        '
+        cls.validate()
+        raise NotImplementedError(
+            u'Your TLD source parser shall implement `get_tld_names` method.')
+
+    @classmethod
+    def update_tld_names(cls, fail_silently=False):
+        u'Update the local copy of the TLD file.\n\n        :param fail_silently:\n        :return:\n        '
+        try:
+            remote_file = urlopen(cls.source_url)
+            local_file = codecs_open(project_dir(
+                cls.local_path), u'wb', encoding='utf8')
+            local_file.write(remote_file.read().decode(u'utf8'))
+            local_file.close()
+            remote_file.close()
+        except Exception as err:
+            if fail_silently:
+                return False
+            raise TldIOError(err)
+        return True

Contents/Libraries/Shared/tld/conf.py

@@ -0,0 +1,45 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals
+from typing import Any
+from . import defaults
+__author__ = u'Artur Barseghyan'
+__copyright__ = u'2013-2019 Artur Barseghyan'
+__license__ = u'MPL-1.1 OR GPL-2.0-only OR LGPL-2.1-or-later'
+__all__ = (u'get_setting', u'reset_settings', u'set_setting', u'settings')
+
+
+class Settings(object):
+    u'Settings registry.'
+
+    def __init__(self):
+        self._settings = {
+
+        }
+        self._settings_get = self._settings.get
+
+    def set(self, name, value):
+        u'\n        Override default settings.\n\n        :param str name:\n        :param mixed value:\n        '
+        self._settings[name] = value
+
+    def get(self, name, default=None):
+        u'\n        Gets a variable from local settings.\n\n        :param str name:\n        :param mixed default: Default value.\n        :return mixed:\n        '
+        if (name in self._settings):
+            return self._settings_get(name, default)
+        elif hasattr(defaults, name):
+            return getattr(defaults, name, default)
+        return default
+
+    def reset(self):
+        u'Reset settings.'
+        for name in defaults.__all__:
+            self.set(name, getattr(defaults, name))
+
+
+settings = Settings()
+get_setting = settings.get
+set_setting = settings.set
+reset_settings = settings.reset

Contents/Libraries/Shared/tld/defaults.py

@@ -0,0 +1,13 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals
+from os.path import dirname
+__author__ = u'Artur Barseghyan'
+__copyright__ = u'2013-2019 Artur Barseghyan'
+__license__ = u'MPL-1.1 OR GPL-2.0-only OR LGPL-2.1-or-later'
+__all__ = (u'DEBUG', u'NAMES_LOCAL_PATH_PARENT')
+NAMES_LOCAL_PATH_PARENT = dirname(__file__)
+DEBUG = False

Contents/Libraries/Shared/tld/exceptions.py

@@ -0,0 +1,49 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals
+from .conf import get_setting
+__author__ = u'Artur Barseghyan'
+__copyright__ = u'2013-2019 Artur Barseghyan'
+__license__ = u'MPL-1.1 OR GPL-2.0-only OR LGPL-2.1-or-later'
+__all__ = (u'TldBadUrl', u'TldDomainNotFound',
+           u'TldImproperlyConfigured', u'TldIOError')
+
+
+class TldIOError(IOError):
+    u'TldIOError.\n\n    Supposed to be thrown when problems with reading/writing occur.\n    '
+
+    def __init__(self, msg=None):
+        tld_names_local_path = get_setting(u'NAMES_LOCAL_PATH')
+        if (msg is None):
+            msg = (u"Can't read from or write to the %s file!" %
+                   tld_names_local_path)
+        super(TldIOError, self).__init__(msg)
+
+
+class TldDomainNotFound(ValueError):
+    u"TldDomainNotFound.\n\n    Supposed to be thrown when domain name is not found (didn't match) the\n    local TLD policy.\n    "
+
+    def __init__(self, domain_name):
+        super(TldDomainNotFound, self).__init__(
+            (u"Domain %s didn't match any existing TLD name!" % domain_name))
+
+
+class TldBadUrl(ValueError):
+    u'TldBadUrl.\n\n    Supposed to be thrown when bad URL is given.\n    '
+
+    def __init__(self, url):
+        super(TldBadUrl, self).__init__((u'Is not a valid URL %s!' % url))
+
+
+class TldImproperlyConfigured(Exception):
+    u'TldImproperlyConfigured.\n\n    Supposed to be thrown when code is improperly configured. Typical use-case\n    is when user tries to use `get_tld` function with both `search_public` and\n    `search_private` set to False.\n    '
+
+    def __init__(self, msg=None):
+        if (msg is None):
+            msg = u'Improperly configured.'
+        else:
+            msg = (u'Improperly configured. %s' % msg)
+        super(TldImproperlyConfigured, self).__init__(msg)

Contents/Libraries/Shared/tld/helpers.py

@@ -0,0 +1,21 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals
+from os.path import abspath, join
+from .conf import get_setting
+__author__ = u'Artur Barseghyan'
+__copyright__ = u'2013-2019 Artur Barseghyan'
+__license__ = u'MPL-1.1 OR GPL-2.0-only OR LGPL-2.1-or-later'
+__all__ = (u'project_dir', u'PROJECT_DIR')
+
+
+def project_dir(base):
+    u'Project dir.'
+    tld_names_local_path_parent = get_setting(u'NAMES_LOCAL_PATH_PARENT')
+    return abspath(join(tld_names_local_path_parent, base).replace(u'\\', u'/'))
+
+
+PROJECT_DIR = project_dir

Contents/Libraries/Shared/tld/parsers/__init__.py

@@ -0,0 +1,5 @@
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals

Contents/Libraries/Shared/tld/parsers/mozilla.py

@@ -0,0 +1,5 @@
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals

Contents/Libraries/Shared/tld/registry.py

@@ -0,0 +1,41 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals
+from typing import Type, Dict
+__author__ = u'Artur Barseghyan'
+__copyright__ = u'2013-2019 Artur Barseghyan'
+__license__ = u'MPL-1.1 OR GPL-2.0-only OR LGPL-2.1-or-later'
+__all__ = (u'Registry',)
+
+
+class Registry(type):
+    REGISTRY = {
+
+    }
+
+    def __new__(cls, name, bases, attrs):
+        new_cls = type.__new__(cls, name, bases, attrs)
+        if getattr(new_cls, u'_uid', None):
+            cls.REGISTRY[new_cls._uid] = new_cls
+        return new_cls
+
+    @property
+    def _uid(cls):
+        return getattr(cls, 'uid', cls.__name__)
+
+    @classmethod
+    def reset(cls):
+        cls.REGISTRY = {
+
+        }
+
+    @classmethod
+    def get(cls, key, default=None):
+        return cls.REGISTRY.get(key, default)
+
+    @classmethod
+    def items(cls):
+        return cls.REGISTRY.items()

Contents/Libraries/Shared/tld/result.py

@@ -0,0 +1,57 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals
+from typing import Dict
+try:
+    from urllib.parse import SplitResult
+except ImportError:
+    from six.moves.urllib_parse import SplitResult
+__author__ = u'Artur Barseghyan'
+__copyright__ = u'2013-2019 Artur Barseghyan'
+__license__ = u'MPL-1.1 OR GPL-2.0-only OR LGPL-2.1-or-later'
+__all__ = (u'Result',)
+
+
+class Result(object):
+    u'Container.'
+    __slots__ = (u'subdomain', u'domain', u'tld', u'__fld', u'parsed_url')
+
+    def __init__(self, tld, domain, subdomain, parsed_url):
+        self.tld = tld
+        self.domain = (domain if (domain != u'') else tld)
+        self.subdomain = subdomain
+        self.parsed_url = parsed_url
+        if domain:
+            self.__fld = u''.join(
+                [u'{}'.format(self.domain), u'.', u'{}'.format(self.tld)])
+        else:
+            self.__fld = self.tld
+
+    @property
+    def extension(self):
+        u'Alias of ``tld``.\n\n        :return str:\n        '
+        return self.tld
+    suffix = extension
+
+    @property
+    def fld(self):
+        u'First level domain.\n\n        :return:\n        :rtype: str\n        '
+        return self.__fld
+
+    def __str__(self):
+        return self.tld
+    __repr__ = __str__
+
+    @property
+    def __dict__(self):
+        u'Mimic __dict__ functionality.\n\n        :return:\n        :rtype: dict\n        '
+        return {
+            u'tld': self.tld,
+            u'domain': self.domain,
+            u'subdomain': self.subdomain,
+            u'fld': self.fld,
+            u'parsed_url': self.parsed_url,
+        }

Contents/Libraries/Shared/tld/tests/__init__.py

@@ -0,0 +1,11 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals
+import unittest
+from .test_core import *
+from .test_commands import *
+if (__name__ == u'__main__'):
+    unittest.main()

Contents/Libraries/Shared/tld/tests/base.py

@@ -0,0 +1,65 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals
+from backports.functools_lru_cache import lru_cache
+import logging
+import socket
+__author__ = u'Artur Barseghyan'
+__copyright__ = u'2013-2019 Artur Barseghyan'
+__license__ = u'MPL-1.1 OR GPL-2.0-only OR LGPL-2.1-or-later'
+__all__ = (u'internet_available_only', u'log_info')
+LOG_INFO = True
+LOGGER = logging.getLogger(__name__)
+
+
+def log_info(func):
+    u'Log some useful info.'
+    if (not LOG_INFO):
+        return func
+
+    def inner(self, *args, **kwargs):
+        u'Inner.'
+        result = func(*([self] + list(args)), **kwargs)
+        LOGGER.debug(u'\n\n%s', func.__name__)
+        LOGGER.debug(u'============================')
+        if func.__doc__:
+            LOGGER.debug(u'""" %s """', func.__doc__.strip())
+        LOGGER.debug(u'----------------------------')
+        if (result is not None):
+            LOGGER.debug(result)
+        LOGGER.debug(u'\n++++++++++++++++++++++++++++')
+        return result
+    return inner
+
+
+@lru_cache(maxsize=32)
+def is_internet_available(host='8.8.8.8', port=53, timeout=3):
+    u'Check if internet is available.\n\n    Host: 8.8.8.8 (google-public-dns-a.google.com)\n    OpenPort: 53/tcp\n    Service: domain (DNS/TCP)\n    '
+    try:
+        socket.setdefaulttimeout(timeout)
+        socket.socket(socket.AF_INET, socket.SOCK_STREAM).connect((host, port))
+        return True
+    except socket.error as ex:
+        print(ex)
+        return False
+
+
+def internet_available_only(func):
+
+    def inner(self, *args, **kwargs):
+        u'Inner.'
+        if (not is_internet_available()):
+            LOGGER.debug(u'\n\n%s', func.__name__)
+            LOGGER.debug(u'============================')
+            if func.__doc__:
+                LOGGER.debug(u'""" %s """', func.__doc__.strip())
+            LOGGER.debug(u'----------------------------')
+            LOGGER.debug(u'Skipping because no Internet connection available.')
+            LOGGER.debug(u'\n++++++++++++++++++++++++++++')
+            return None
+        result = func(*([self] + list(args)), **kwargs)
+        return result
+    return inner

Contents/Libraries/Shared/tld/tests/test_commands.py

@@ -0,0 +1,43 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals
+import logging
+import unittest
+import subprocess
+from .base import log_info, internet_available_only
+__author__ = u'Artur Barseghyan'
+__copyright__ = u'2013-2019 Artur Barseghyan'
+__license__ = u'GPL 2.0/LGPL 2.1'
+__all__ = (u'TestCommands',)
+LOGGER = logging.getLogger(__name__)
+
+
+class TestCommands(unittest.TestCase):
+    u'Tld commands tests.'
+
+    def setUp(self):
+        u'Set up.'
+
+    @internet_available_only
+    @log_info
+    def test_1_update_tld_names_command(self):
+        u'Test updating the tld names (re-fetch mozilla source).'
+        res = subprocess.check_output([u'update-tld-names']).strip()
+        self.assertEqual(res, b'')
+        return res
+
+    @internet_available_only
+    @log_info
+    def test_1_update_tld_names_mozilla_command(self):
+        u'Test updating the tld names (re-fetch mozilla source).'
+        res = subprocess.check_output(
+            [u'update-tld-names', u'mozilla']).strip()
+        self.assertEqual(res, b'')
+        return res
+
+
+if (__name__ == u'__main__'):
+    unittest.main()

Contents/Libraries/Shared/tld/tests/test_core.py

@@ -0,0 +1,708 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import copy
+import logging
+from os.path import abspath, join
+import unittest
+from tempfile import gettempdir
+from typing import Type
+try:
+    from urllib.parse import urlsplit
+except ImportError:
+    from six.moves.urllib_parse import urlsplit
+from faker import Faker
+from .. import defaults
+from ..base import BaseTLDSourceParser
+from ..conf import get_setting, reset_settings, set_setting
+from ..exceptions import TldBadUrl, TldDomainNotFound, TldImproperlyConfigured, TldIOError
+from ..helpers import project_dir
+from ..registry import Registry
+from ..utils import get_fld, get_tld, get_tld_names, get_tld_names_container, is_tld, MozillaTLDSourceParser, BaseMozillaTLDSourceParser, parse_tld, reset_tld_names, update_tld_names, update_tld_names_cli
+from .base import internet_available_only, log_info
+__author__ = u'Artur Barseghyan'
+__copyright__ = u'2013-2019 Artur Barseghyan'
+__license__ = u'MPL-1.1 OR GPL-2.0-only OR LGPL-2.1-or-later'
+__all__ = (u'TestCore',)
+LOGGER = logging.getLogger(__name__)
+
+
+class TestCore(unittest.TestCase):
+    u'Core tld functionality tests.'
+
+    @classmethod
+    def setUpClass(cls):
+        cls.faker = Faker()
+        cls.temp_dir = gettempdir()
+
+    def setUp(self):
+        u'Set up.'
+        self.good_patterns = [{
+            u'url': u'http://www.google.co.uk',
+            u'fld': u'google.co.uk',
+            u'subdomain': u'www',
+            u'domain': u'google',
+            u'suffix': u'co.uk',
+            u'tld': u'co.uk',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }, {
+            u'url': u'http://www.v2.google.co.uk',
+            u'fld': u'google.co.uk',
+            u'subdomain': u'www.v2',
+            u'domain': u'google',
+            u'suffix': u'co.uk',
+            u'tld': u'co.uk',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }, {
+            u'url': u'http://хром.гугл.рф',
+            u'fld': u'гугл.рф',
+            u'subdomain': u'хром',
+            u'domain': u'гугл',
+            u'suffix': u'рф',
+            u'tld': u'рф',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }, {
+            u'url': u'http://www.google.co.uk:8001/lorem-ipsum/',
+            u'fld': u'google.co.uk',
+            u'subdomain': u'www',
+            u'domain': u'google',
+            u'suffix': u'co.uk',
+            u'tld': u'co.uk',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }, {
+            u'url': u'http://www.me.cloudfront.net',
+            u'fld': u'me.cloudfront.net',
+            u'subdomain': u'www',
+            u'domain': u'me',
+            u'suffix': u'cloudfront.net',
+            u'tld': u'cloudfront.net',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }, {
+            u'url': u'http://www.v2.forum.tech.google.co.uk:8001/lorem-ipsum/',
+            u'fld': u'google.co.uk',
+            u'subdomain': u'www.v2.forum.tech',
+            u'domain': u'google',
+            u'suffix': u'co.uk',
+            u'tld': u'co.uk',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }, {
+            u'url': u'https://pantheon.io/',
+            u'fld': u'pantheon.io',
+            u'subdomain': u'',
+            u'domain': u'pantheon',
+            u'suffix': u'io',
+            u'tld': u'io',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }, {
+            u'url': u'v2.www.google.com',
+            u'fld': u'google.com',
+            u'subdomain': u'v2.www',
+            u'domain': u'google',
+            u'suffix': u'com',
+            u'tld': u'com',
+            u'kwargs': {
+                u'fail_silently': True,
+                u'fix_protocol': True,
+            },
+        }, {
+            u'url': u'//v2.www.google.com',
+            u'fld': u'google.com',
+            u'subdomain': u'v2.www',
+            u'domain': u'google',
+            u'suffix': u'com',
+            u'tld': u'com',
+            u'kwargs': {
+                u'fail_silently': True,
+                u'fix_protocol': True,
+            },
+        }, {
+            u'url': u'http://foo@bar.com',
+            u'fld': u'bar.com',
+            u'subdomain': u'',
+            u'domain': u'bar',
+            u'suffix': u'com',
+            u'tld': u'com',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }, {
+            u'url': u'http://user:foo@bar.com',
+            u'fld': u'bar.com',
+            u'subdomain': u'',
+            u'domain': u'bar',
+            u'suffix': u'com',
+            u'tld': u'com',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }, {
+            u'url': u'https://faguoren.xn--fiqs8s',
+            u'fld': u'faguoren.xn--fiqs8s',
+            u'subdomain': u'',
+            u'domain': u'faguoren',
+            u'suffix': u'xn--fiqs8s',
+            u'tld': u'xn--fiqs8s',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }, {
+            u'url': u'blogs.lemonde.paris',
+            u'fld': u'lemonde.paris',
+            u'subdomain': u'blogs',
+            u'domain': u'lemonde',
+            u'suffix': u'paris',
+            u'tld': u'paris',
+            u'kwargs': {
+                u'fail_silently': True,
+                u'fix_protocol': True,
+            },
+        }, {
+            u'url': u'axel.brighton.ac.uk',
+            u'fld': u'brighton.ac.uk',
+            u'subdomain': u'axel',
+            u'domain': u'brighton',
+            u'suffix': u'ac.uk',
+            u'tld': u'ac.uk',
+            u'kwargs': {
+                u'fail_silently': True,
+                u'fix_protocol': True,
+            },
+        }, {
+            u'url': u'm.fr.blogspot.com.au',
+            u'fld': u'fr.blogspot.com.au',
+            u'subdomain': u'm',
+            u'domain': u'fr',
+            u'suffix': u'blogspot.com.au',
+            u'tld': u'blogspot.com.au',
+            u'kwargs': {
+                u'fail_silently': True,
+                u'fix_protocol': True,
+            },
+        }, {
+            u'url': u'help.www.福岡.jp',
+            u'fld': u'www.福岡.jp',
+            u'subdomain': u'help',
+            u'domain': u'www',
+            u'suffix': u'福岡.jp',
+            u'tld': u'福岡.jp',
+            u'kwargs': {
+                u'fail_silently': True,
+                u'fix_protocol': True,
+            },
+        }, {
+            u'url': u'syria.arabic.variant.سوريا',
+            u'fld': u'variant.سوريا',
+            u'subdomain': u'syria.arabic',
+            u'domain': u'variant',
+            u'suffix': u'سوريا',
+            u'tld': u'سوريا',
+            u'kwargs': {
+                u'fail_silently': True,
+                u'fix_protocol': True,
+            },
+        }, {
+            u'url': u'http://www.help.kawasaki.jp',
+            u'fld': u'www.help.kawasaki.jp',
+            u'subdomain': u'',
+            u'domain': u'www',
+            u'suffix': u'help.kawasaki.jp',
+            u'tld': u'help.kawasaki.jp',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }, {
+            u'url': u'http://www.city.kawasaki.jp',
+            u'fld': u'city.kawasaki.jp',
+            u'subdomain': u'www',
+            u'domain': u'city',
+            u'suffix': u'kawasaki.jp',
+            u'tld': u'kawasaki.jp',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }, {
+            u'url': u'http://fedoraproject.org',
+            u'fld': u'fedoraproject.org',
+            u'subdomain': u'',
+            u'domain': u'fedoraproject',
+            u'suffix': u'org',
+            u'tld': u'org',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }, {
+            u'url': u'http://www.cloud.fedoraproject.org',
+            u'fld': u'www.cloud.fedoraproject.org',
+            u'subdomain': u'',
+            u'domain': u'www',
+            u'suffix': u'cloud.fedoraproject.org',
+            u'tld': u'cloud.fedoraproject.org',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }, {
+            u'url': u'https://www.john.app.os.fedoraproject.org',
+            u'fld': u'john.app.os.fedoraproject.org',
+            u'subdomain': u'www',
+            u'domain': u'john',
+            u'suffix': u'app.os.fedoraproject.org',
+            u'tld': u'app.os.fedoraproject.org',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }, {
+            u'url': u'ftp://www.xn--mxail5aa.xn--11b4c3d',
+            u'fld': u'xn--mxail5aa.xn--11b4c3d',
+            u'subdomain': u'www',
+            u'domain': u'xn--mxail5aa',
+            u'suffix': u'xn--11b4c3d',
+            u'tld': u'xn--11b4c3d',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }, {
+            u'url': u'http://cloud.fedoraproject.org',
+            u'fld': u'cloud.fedoraproject.org',
+            u'subdomain': u'',
+            u'domain': u'cloud.fedoraproject.org',
+            u'suffix': u'cloud.fedoraproject.org',
+            u'tld': u'cloud.fedoraproject.org',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }, {
+            u'url': u'github.io',
+            u'fld': u'github.io',
+            u'subdomain': u'',
+            u'domain': u'github.io',
+            u'suffix': u'github.io',
+            u'tld': u'github.io',
+            u'kwargs': {
+                u'fail_silently': True,
+                u'fix_protocol': True,
+            },
+        }, {
+            u'url': urlsplit(u'http://lemonde.fr/article.html'),
+            u'fld': u'lemonde.fr',
+            u'subdomain': u'',
+            u'domain': u'lemonde',
+            u'suffix': u'fr',
+            u'tld': u'fr',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }]
+        self.bad_patterns = {
+            u'v2.www.google.com': {
+                u'exception': TldBadUrl,
+            },
+            u'/index.php?a=1&b=2': {
+                u'exception': TldBadUrl,
+            },
+            u'http://www.tld.doesnotexist': {
+                u'exception': TldDomainNotFound,
+            },
+            u'https://2001:0db8:0000:85a3:0000:0000:ac1f:8001': {
+                u'exception': TldDomainNotFound,
+            },
+            u'http://192.169.1.1': {
+                u'exception': TldDomainNotFound,
+            },
+            u'http://localhost:8080': {
+                u'exception': TldDomainNotFound,
+            },
+            u'https://localhost': {
+                u'exception': TldDomainNotFound,
+            },
+            u'https://localhost2': {
+                u'exception': TldImproperlyConfigured,
+                u'kwargs': {
+                    u'search_public': False,
+                    u'search_private': False,
+                },
+            },
+        }
+        self.invalid_tlds = {u'v2.www.google.com', u'tld.doesnotexist',
+                             u'2001:0db8:0000:85a3:0000:0000:ac1f', u'192.169.1.1', 'localhost', u'google.com'}
+        self.tld_names_local_path_custom = project_dir(
+            join(u'tests', u'res', u'effective_tld_names_custom.dat.txt'))
+        self.good_patterns_custom_parser = [{
+            u'url': u'http://www.foreverchild',
+            u'fld': u'www.foreverchild',
+            u'subdomain': u'',
+            u'domain': u'www',
+            u'suffix': u'foreverchild',
+            u'tld': u'foreverchild',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }, {
+            u'url': u'http://www.v2.foreverchild',
+            u'fld': u'v2.foreverchild',
+            u'subdomain': u'www',
+            u'domain': u'v2',
+            u'suffix': u'foreverchild',
+            u'tld': u'foreverchild',
+            u'kwargs': {
+                u'fail_silently': True,
+            },
+        }]
+        reset_settings()
+
+    def tearDown(self):
+        u'Tear down.'
+        reset_settings()
+        Registry.reset()
+
+    @property
+    def good_url(self):
+        return self.good_patterns[0][u'url']
+
+    @property
+    def bad_url(self):
+        return list(self.bad_patterns.keys())[0]
+
+    def get_custom_parser_class(self, uid='custom_mozilla', source_url=None, local_path='tests/res/effective_tld_names_custom.dat.txt'):
+        parser_class = type('CustomMozillaTLDSourceParser', (BaseMozillaTLDSourceParser,), {
+            'uid': uid,
+            'source_url': source_url,
+            'local_path': local_path,
+        })
+        return parser_class
+
+    @log_info
+    def test_0_tld_names_loaded(self):
+        u'Test if tld names are loaded.'
+        get_fld(u'http://www.google.co.uk')
+        from ..utils import tld_names
+        res = (len(tld_names) > 0)
+        self.assertTrue(res)
+        return res
+
+    @internet_available_only
+    @log_info
+    def test_1_update_tld_names(self):
+        u'Test updating the tld names (re-fetch mozilla source).'
+        res = update_tld_names(fail_silently=False)
+        self.assertTrue(res)
+        return res
+
+    @log_info
+    def test_2_fld_good_patterns_pass(self):
+        u'Test good URL patterns.'
+        res = []
+        for data in self.good_patterns:
+            _res = get_fld(data[u'url'], **data[u'kwargs'])
+            self.assertEqual(_res, data[u'fld'])
+            res.append(_res)
+        return res
+
+    @log_info
+    def test_3_fld_bad_patterns_pass(self):
+        u'Test bad URL patterns.'
+        res = []
+        for (url, params) in self.bad_patterns.items():
+            _res = get_fld(url, fail_silently=True)
+            self.assertEqual(_res, None)
+            res.append(_res)
+        return res
+
+    @log_info
+    def test_4_override_settings(self):
+        u'Testing settings override.'
+
+        def override_settings():
+            u'Override settings.'
+            return get_setting(u'DEBUG')
+        self.assertEqual(defaults.DEBUG, override_settings())
+        set_setting(u'DEBUG', True)
+        self.assertEqual(True, override_settings())
+        return override_settings()
+
+    @log_info
+    def test_5_tld_good_patterns_pass_parsed_object(self):
+        u'Test good URL patterns.'
+        res = []
+        for data in self.good_patterns:
+            kwargs = copy.copy(data[u'kwargs'])
+            kwargs.update({
+                u'as_object': True,
+            })
+            _res = get_tld(data[u'url'], **kwargs)
+            self.assertEqual(_res.tld, data[u'tld'])
+            self.assertEqual(_res.subdomain, data[u'subdomain'])
+            self.assertEqual(_res.domain, data[u'domain'])
+            self.assertEqual(_res.suffix, data[u'suffix'])
+            self.assertEqual(_res.fld, data[u'fld'])
+            self.assertEqual(unicode(_res).encode(u'utf8'),
+                             data[u'tld'].encode(u'utf8'))
+            self.assertEqual(_res.__dict__, {
+                u'tld': _res.tld,
+                u'domain': _res.domain,
+                u'subdomain': _res.subdomain,
+                u'fld': _res.fld,
+                u'parsed_url': _res.parsed_url,
+            })
+            res.append(_res)
+        return res
+
+    @log_info
+    def test_6_override_full_names_path(self):
+        default = project_dir(u'dummy.txt')
+        override_base = u'/tmp/test'
+        set_setting(u'NAMES_LOCAL_PATH_PARENT', override_base)
+        modified = project_dir(u'dummy.txt')
+        self.assertNotEqual(default, modified)
+        self.assertEqual(modified, abspath(u'/tmp/test/dummy.txt'))
+
+    @log_info
+    def test_7_public_private(self):
+        res = get_fld(u'http://silly.cc.ua',
+                      fail_silently=True, search_private=False)
+        self.assertEqual(res, None)
+        res = get_fld(u'http://silly.cc.ua',
+                      fail_silently=True, search_private=True)
+        self.assertEqual(res, u'silly.cc.ua')
+        res = get_fld(u'mercy.compute.amazonaws.com',
+                      fail_silently=True, search_private=False, fix_protocol=True)
+        self.assertEqual(res, None)
+        res = get_fld(u'http://whatever.com',
+                      fail_silently=True, search_public=False)
+        self.assertEqual(res, None)
+
+    @log_info
+    def test_8_fld_bad_patterns_exceptions(self):
+        u'Test exceptions.'
+        res = []
+        for (url, params) in self.bad_patterns.items():
+            kwargs = (params[u'kwargs'] if (u'kwargs' in params) else {
+
+            })
+            kwargs.update({
+                u'fail_silently': False,
+            })
+            with self.assertRaises(params[u'exception']):
+                _res = get_fld(url, **kwargs)
+                res.append(_res)
+        return res
+
+    @log_info
+    def test_9_tld_good_patterns_pass(self):
+        u'Test `get_tld` good URL patterns.'
+        res = []
+        for data in self.good_patterns:
+            _res = get_tld(data[u'url'], **data[u'kwargs'])
+            self.assertEqual(_res, data[u'tld'])
+            res.append(_res)
+        return res
+
+    @log_info
+    def test_10_tld_bad_patterns_pass(self):
+        u'Test `get_tld` bad URL patterns.'
+        res = []
+        for (url, params) in self.bad_patterns.items():
+            _res = get_tld(url, fail_silently=True)
+            self.assertEqual(_res, None)
+            res.append(_res)
+        return res
+
+    @log_info
+    def test_11_parse_tld_good_patterns(self):
+        u'Test `parse_tld` good URL patterns.'
+        res = []
+        for data in self.good_patterns:
+            _res = parse_tld(data[u'url'], **data[u'kwargs'])
+            self.assertEqual(
+                _res, (data[u'tld'], data[u'domain'], data[u'subdomain']))
+            res.append(_res)
+        return res
+
+    @log_info
+    def test_12_is_tld_good_patterns(self):
+        u'Test `is_tld` good URL patterns.'
+        for data in self.good_patterns:
+            self.assertTrue(is_tld(data[u'tld']))
+
+    @log_info
+    def test_13_is_tld_bad_patterns(self):
+        u'Test `is_tld` bad URL patterns.'
+        for _tld in self.invalid_tlds:
+            self.assertFalse(is_tld(_tld))
+
+    @log_info
+    def test_14_fail_update_tld_names(self):
+        u'Test fail `update_tld_names`.'
+        parser_class = self.get_custom_parser_class(
+            uid='custom_mozilla_2', source_url='i-do-not-exist')
+        with self.assertRaises(TldIOError):
+            update_tld_names(fail_silently=False, parser_uid=parser_class.uid)
+        self.assertFalse(update_tld_names(
+            fail_silently=True, parser_uid=parser_class.uid))
+
+    @log_info
+    def test_15_fail_get_fld_wrong_kwargs(self):
+        u'Test fail `get_fld` with wrong kwargs.'
+        with self.assertRaises(TldImproperlyConfigured):
+            get_fld(self.good_url, as_object=True)
+
+    @log_info
+    def test_16_fail_parse_tld(self):
+        u'Test fail `parse_tld`.\n\n        Assert raise TldIOError on wrong `NAMES_SOURCE_URL` for `parse_tld`.\n        '
+        parser_class = self.get_custom_parser_class(
+            source_url='i-do-not-exist')
+        parsed_tld = parse_tld(
+            self.bad_url, fail_silently=False, parser_class=parser_class)
+        self.assertEqual(parsed_tld, (None, None, None))
+
+    @log_info
+    def test_17_get_tld_names_and_reset_tld_names(self):
+        u'Test fail `get_tld_names` and repair using `reset_tld_names`.'
+        tmp_filename = join(gettempdir(), u''.join(
+            [u'{}'.format(self.faker.uuid4()), u'.dat.txt']))
+        parser_class = self.get_custom_parser_class(
+            source_url='i-do-not-exist', local_path=tmp_filename)
+        reset_tld_names()
+        if True:
+            with self.assertRaises(TldIOError):
+                get_tld_names(fail_silently=False, parser_class=parser_class)
+        tmp_filename = join(gettempdir(), u''.join(
+            [u'{}'.format(self.faker.uuid4()), u'.dat.txt']))
+        parser_class_2 = self.get_custom_parser_class(
+            source_url='i-do-not-exist-2', local_path=tmp_filename)
+        reset_tld_names()
+        if True:
+            self.assertIsNone(get_tld_names(
+                fail_silently=True, parser_class=parser_class_2))
+
+    @internet_available_only
+    @log_info
+    def test_18_update_tld_names_cli(self):
+        u'Test the return code of the CLI version of `update_tld_names`.'
+        reset_tld_names()
+        res = update_tld_names_cli()
+        self.assertEqual(res, 0)
+
+    @log_info
+    def test_19_parse_tld_custom_tld_names_good_patterns(self):
+        u'Test `parse_tld` good URL patterns for custom tld names.'
+        res = []
+        for data in self.good_patterns_custom_parser:
+            kwargs = copy.copy(data[u'kwargs'])
+            kwargs.update({
+                u'parser_class': self.get_custom_parser_class(),
+            })
+            _res = parse_tld(data[u'url'], **kwargs)
+            self.assertEqual(
+                _res, (data[u'tld'], data[u'domain'], data[u'subdomain']))
+            res.append(_res)
+        return res
+
+    @log_info
+    def test_20_tld_custom_tld_names_good_patterns_pass_parsed_object(self):
+        u'Test `get_tld` good URL patterns for custom tld names.'
+        res = []
+        for data in self.good_patterns_custom_parser:
+            kwargs = copy.copy(data[u'kwargs'])
+            kwargs.update({
+                u'as_object': True,
+                u'parser_class': self.get_custom_parser_class(),
+            })
+            _res = get_tld(data[u'url'], **kwargs)
+            self.assertEqual(_res.tld, data[u'tld'])
+            self.assertEqual(_res.subdomain, data[u'subdomain'])
+            self.assertEqual(_res.domain, data[u'domain'])
+            self.assertEqual(_res.suffix, data[u'suffix'])
+            self.assertEqual(_res.fld, data[u'fld'])
+            self.assertEqual(unicode(_res).encode(u'utf8'),
+                             data[u'tld'].encode(u'utf8'))
+            self.assertEqual(_res.__dict__, {
+                u'tld': _res.tld,
+                u'domain': _res.domain,
+                u'subdomain': _res.subdomain,
+                u'fld': _res.fld,
+                u'parsed_url': _res.parsed_url,
+            })
+            res.append(_res)
+        return res
+
+    @log_info
+    def test_21_reset_tld_names_for_custom_parser(self):
+        u'Test `reset_tld_names` for `tld_names_local_path`.'
+        res = []
+        parser_class = self.get_custom_parser_class()
+        for data in self.good_patterns_custom_parser:
+            kwargs = copy.copy(data[u'kwargs'])
+            kwargs.update({
+                u'as_object': True,
+                u'parser_class': self.get_custom_parser_class(),
+            })
+            _res = get_tld(data[u'url'], **kwargs)
+            self.assertEqual(_res.tld, data[u'tld'])
+            self.assertEqual(_res.subdomain, data[u'subdomain'])
+            self.assertEqual(_res.domain, data[u'domain'])
+            self.assertEqual(_res.suffix, data[u'suffix'])
+            self.assertEqual(_res.fld, data[u'fld'])
+            self.assertEqual(unicode(_res).encode(u'utf8'),
+                             data[u'tld'].encode(u'utf8'))
+            self.assertEqual(_res.__dict__, {
+                u'tld': _res.tld,
+                u'domain': _res.domain,
+                u'subdomain': _res.subdomain,
+                u'fld': _res.fld,
+                u'parsed_url': _res.parsed_url,
+            })
+            res.append(_res)
+        tld_names = get_tld_names_container()
+        self.assertIn(parser_class.local_path, tld_names)
+        reset_tld_names(parser_class.local_path)
+        self.assertNotIn(parser_class.local_path, tld_names)
+        return res
+
+    @log_info
+    def test_22_fail_define_custom_parser_class_without_uid(self):
+        u'Test fail define custom parser class without `uid`.'
+
+        class CustomParser(BaseTLDSourceParser):
+            pass
+
+        class AnotherCustomParser(BaseTLDSourceParser):
+            uid = u'another-custom-parser'
+        with self.assertRaises(TldImproperlyConfigured):
+            CustomParser.get_tld_names()
+        with self.assertRaises(NotImplementedError):
+            AnotherCustomParser.get_tld_names()
+
+    @log_info
+    def test_23_len_trie_nodes(self):
+        u'Test len of the trie nodes.'
+        get_tld(u'http://delusionalinsanity.com')
+        tld_names = get_tld_names_container()
+        self.assertGreater(
+            len(tld_names[MozillaTLDSourceParser.local_path]), 0)
+
+    @log_info
+    def test_24_get_tld_names_no_arguments(self):
+        u'Test len of the trie nodes.'
+        tld_names = get_tld_names()
+        self.assertGreater(len(tld_names), 0)
+
+
+if (__name__ == u'__main__'):
+    unittest.main()

Contents/Libraries/Shared/tld/trie.py

@@ -0,0 +1,54 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals
+__author__ = u'Artur Barseghyan'
+__copyright__ = u'2013-2019 Artur Barseghyan'
+__license__ = u'MPL-1.1 OR GPL-2.0-only OR LGPL-2.1-or-later'
+__all__ = (u'Trie', u'TrieNode')
+
+
+class TrieNode(object):
+    u'Class representing a single Trie node.'
+    __slots__ = (u'children', u'exception', u'leaf', u'private')
+
+    def __init__(self):
+        self.children = None
+        self.exception = None
+        self.leaf = False
+        self.private = False
+
+
+class Trie(object):
+    u'An adhoc Trie data structure to store tlds in reverse notation order.'
+
+    def __init__(self):
+        self.root = TrieNode()
+        self.__nodes = 0
+
+    def __len__(self):
+        return self.__nodes
+
+    def add(self, tld, private=False):
+        node = self.root
+        for part in reversed(tld.split(u'.')):
+            if part.startswith(u'!'):
+                node.exception = part[1:]
+                break
+            if (node.children is None):
+                node.children = {
+
+                }
+                child = TrieNode()
+            else:
+                child = node.children.get(part)
+                if (child is None):
+                    child = TrieNode()
+            node.children[part] = child
+            node = child
+        node.leaf = True
+        if private:
+            node.private = True
+        self.__nodes += 1

Contents/Libraries/Shared/tld/utils.py

@@ -0,0 +1,271 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals
+from __future__ import unicode_literals
+import argparse
+from codecs import open as codecs_open
+from backports.functools_lru_cache import lru_cache
+from os.path import isabs
+import sys
+from typing import Dict, Type, Union, Tuple, List
+try:
+    from urllib.parse import urlsplit, SplitResult
+except ImportError:
+    from six.moves.urllib_parse import urlsplit, SplitResult
+from .base import BaseTLDSourceParser
+from .exceptions import TldBadUrl, TldDomainNotFound, TldImproperlyConfigured, TldIOError
+from .helpers import project_dir
+from .trie import Trie
+from .registry import Registry
+from .result import Result
+__author__ = u'Artur Barseghyan'
+__copyright__ = u'2013-2019 Artur Barseghyan'
+__license__ = u'MPL-1.1 OR GPL-2.0-only OR LGPL-2.1-or-later'
+__all__ = (u'BaseMozillaTLDSourceParser', u'get_fld', u'get_tld', u'get_tld_names', u'get_tld_names_container', u'is_tld', u'MozillaTLDSourceParser', u'parse_tld',
+           u'pop_tld_names_container', u'process_url', u'reset_tld_names', u'Result', u'update_tld_names', u'update_tld_names_cli', u'update_tld_names_container')
+tld_names = {
+
+}
+
+
+def get_tld_names_container():
+    u'Get container of all tld names.\n\n    :return:\n    :rtype dict:\n    '
+    global tld_names
+    return tld_names
+
+
+def update_tld_names_container(tld_names_local_path, trie_obj):
+    u'Update TLD Names container item.\n\n    :param tld_names_local_path:\n    :param trie_obj:\n    :return:\n    '
+    global tld_names
+    tld_names.update({
+        tld_names_local_path: trie_obj,
+    })
+
+
+def pop_tld_names_container(tld_names_local_path):
+    u'Remove TLD names container item.\n\n    :param tld_names_local_path:\n    :return:\n    '
+    global tld_names
+    tld_names.pop(tld_names_local_path, None)
+
+
+@lru_cache(maxsize=128, typed=True)
+def update_tld_names(fail_silently=False, parser_uid=None):
+    u'Update TLD names.\n\n    :param fail_silently:\n    :param parser_uid:\n    :return:\n    '
+    results = []
+    results_append = results.append
+    if parser_uid:
+        parser_cls = Registry.get(parser_uid, None)
+        if (parser_cls and parser_cls.source_url):
+            results_append(parser_cls.update_tld_names(
+                fail_silently=fail_silently))
+    else:
+        for (parser_uid, parser_cls) in Registry.items():
+            if (parser_cls and parser_cls.source_url):
+                results_append(parser_cls.update_tld_names(
+                    fail_silently=fail_silently))
+    return all(results)
+
+
+def update_tld_names_cli():
+    u'CLI wrapper for update_tld_names.\n\n    Since update_tld_names returns True on success, we need to negate the\n    result to match CLI semantics.\n    '
+    parser = argparse.ArgumentParser(description='Update TLD names')
+    parser.add_argument(u'parser_uid', nargs='?', default=None,
+                        help='UID of the parser to update TLD names for.')
+    parser.add_argument(u'--fail-silently', dest='fail_silently',
+                        default=False, action='store_true', help='Fail silently')
+    args = parser.parse_args(sys.argv[1:])
+    parser_uid = args.parser_uid
+    fail_silently = args.fail_silently
+    return int((not update_tld_names(parser_uid=parser_uid, fail_silently=fail_silently)))
+
+
+def get_tld_names(fail_silently=False, retry_count=0, parser_class=None):
+    u'Build the ``tlds`` list if empty. Recursive.\n\n    :param fail_silently: If set to True, no exceptions are raised and None\n        is returned on failure.\n    :param retry_count: If greater than 1, we raise an exception in order\n        to avoid infinite loops.\n    :param parser_class:\n    :type fail_silently: bool\n    :type retry_count: int\n    :type parser_class: BaseTLDSourceParser\n    :return: List of TLD names\n    :rtype: obj:`tld.utils.Trie`\n    '
+    if (not parser_class):
+        parser_class = MozillaTLDSourceParser
+    return parser_class.get_tld_names(fail_silently=fail_silently, retry_count=retry_count)
+
+
+class BaseMozillaTLDSourceParser(BaseTLDSourceParser):
+
+    @classmethod
+    def get_tld_names(cls, fail_silently=False, retry_count=0):
+        u'Parse.\n\n        :param fail_silently:\n        :param retry_count:\n        :return:\n        '
+        if (retry_count > 1):
+            if fail_silently:
+                return None
+            else:
+                raise TldIOError
+        global tld_names
+        _tld_names = tld_names
+        if ((cls.local_path in _tld_names) and (_tld_names[cls.local_path] is not None)):
+            return _tld_names
+        local_file = None
+        try:
+            if isabs(cls.local_path):
+                local_path = cls.local_path
+            else:
+                local_path = project_dir(cls.local_path)
+            local_file = codecs_open(local_path, u'r', encoding='utf8')
+            trie = Trie()
+            trie_add = trie.add
+            private_section = False
+            for line in local_file:
+                if (u'===BEGIN PRIVATE DOMAINS===' in line):
+                    private_section = True
+                if (u'// xn--' in line):
+                    line = line.split()[1]
+                if (line[0] in (u'/', u'\n')):
+                    continue
+                trie_add(u''.join([u'{}'.format(line.strip())]),
+                         private=private_section)
+            update_tld_names_container(cls.local_path, trie)
+            local_file.close()
+        except IOError as err:
+            cls.update_tld_names(fail_silently=fail_silently)
+            retry_count += 1
+            return cls.get_tld_names(fail_silently=fail_silently, retry_count=retry_count)
+        except Exception as err:
+            if fail_silently:
+                return None
+            else:
+                raise err
+        finally:
+            try:
+                local_file.close()
+            except Exception:
+                pass
+        return _tld_names
+
+
+class MozillaTLDSourceParser(BaseMozillaTLDSourceParser):
+    u'Mozilla TLD source.'
+    uid = u'mozilla'
+    source_url = u'http://mxr.mozilla.org/mozilla/source/netwerk/dns/src/effective_tld_names.dat?raw=1'
+    local_path = u'res/effective_tld_names.dat.txt'
+
+
+def process_url(url, fail_silently=False, fix_protocol=False, search_public=True, search_private=True, parser_class=MozillaTLDSourceParser):
+    u'Process URL.\n\n    :param parser_class:\n    :param url:\n    :param fail_silently:\n    :param fix_protocol:\n    :param search_public:\n    :param search_private:\n    :return:\n    '
+    if (not (search_public or search_private)):
+        raise TldImproperlyConfigured(
+            u'Either `search_public` or `search_private` (or both) shall be set to True.')
+    _tld_names = get_tld_names(
+        fail_silently=fail_silently, parser_class=parser_class)
+    if (not isinstance(url, SplitResult)):
+        url = url.lower()
+        if (fix_protocol and (not url.startswith((u'//', u'http://', u'https://')))):
+            url = u''.join([u'https://', u'{}'.format(url)])
+        parsed_url = urlsplit(url)
+    else:
+        parsed_url = url
+    domain_name = parsed_url.hostname
+    if (not domain_name):
+        if fail_silently:
+            return (None, None, parsed_url)
+        else:
+            raise TldBadUrl(url=url)
+    domain_parts = domain_name.split(u'.')
+    tld_names_local_path = parser_class.local_path
+    node = _tld_names[tld_names_local_path].root
+    current_length = 0
+    tld_length = 0
+    match = None
+    len_domain_parts = len(domain_parts)
+    for i in reversed(range(len_domain_parts)):
+        part = domain_parts[i]
+        if (node.children is None):
+            break
+        if (part == node.exception):
+            break
+        child = node.children.get(part)
+        if (child is None):
+            child = node.children.get(u'*')
+        if (child is None):
+            break
+        current_length += 1
+        node = child
+        if node.leaf:
+            tld_length = current_length
+            match = node
+    if ((match is None) or (not match.leaf) or ((not search_public) and (not match.private)) or ((not search_private) and match.private)):
+        if fail_silently:
+            return (None, None, parsed_url)
+        else:
+            raise TldDomainNotFound(domain_name=domain_name)
+    if (len_domain_parts == tld_length):
+        non_zero_i = (- 1)
+    else:
+        non_zero_i = max(1, (len_domain_parts - tld_length))
+    return (domain_parts, non_zero_i, parsed_url)
+
+
+def get_fld(url, fail_silently=False, fix_protocol=False, search_public=True, search_private=True, parser_class=MozillaTLDSourceParser, **kwargs):
+    u"Extract the first level domain.\n\n    Extract the top level domain based on the mozilla's effective TLD names\n    dat file. Returns a string. May throw ``TldBadUrl`` or\n    ``TldDomainNotFound`` exceptions if there's bad URL provided or no TLD\n    match found respectively.\n\n    :param url: URL to get top level domain from.\n    :param fail_silently: If set to True, no exceptions are raised and None\n        is returned on failure.\n    :param fix_protocol: If set to True, missing or wrong protocol is\n        ignored (https is appended instead).\n    :param search_public: If set to True, search in public domains.\n    :param search_private: If set to True, search in private domains.\n    :param parser_class:\n    :type url: str\n    :type fail_silently: bool\n    :type fix_protocol: bool\n    :type search_public: bool\n    :type search_private: bool\n    :return: String with top level domain (if ``as_object`` argument\n        is set to False) or a ``tld.utils.Result`` object (if ``as_object``\n        argument is set to True); returns None on failure.\n    :rtype: str\n    "
+    if (u'as_object' in kwargs):
+        raise TldImproperlyConfigured(
+            u'`as_object` argument is deprecated for `get_fld`. Use `get_tld` instead.')
+    (domain_parts, non_zero_i, parsed_url) = process_url(url=url, fail_silently=fail_silently,
+                                                         fix_protocol=fix_protocol, search_public=search_public, search_private=search_private, parser_class=parser_class)
+    if (domain_parts is None):
+        return None
+    if (non_zero_i < 0):
+        return parsed_url.hostname
+    return u'.'.join(domain_parts[(non_zero_i - 1):])
+
+
+def get_tld(url, fail_silently=False, as_object=False, fix_protocol=False, search_public=True, search_private=True, parser_class=MozillaTLDSourceParser):
+    u"Extract the top level domain.\n\n    Extract the top level domain based on the mozilla's effective TLD names\n    dat file. Returns a string. May throw ``TldBadUrl`` or\n    ``TldDomainNotFound`` exceptions if there's bad URL provided or no TLD\n    match found respectively.\n\n    :param url: URL to get top level domain from.\n    :param fail_silently: If set to True, no exceptions are raised and None\n        is returned on failure.\n    :param as_object: If set to True, ``tld.utils.Result`` object is returned,\n        ``domain``, ``suffix`` and ``tld`` properties.\n    :param fix_protocol: If set to True, missing or wrong protocol is\n        ignored (https is appended instead).\n    :param search_public: If set to True, search in public domains.\n    :param search_private: If set to True, search in private domains.\n    :param parser_class:\n    :type url: str\n    :type fail_silently: bool\n    :type as_object: bool\n    :type fix_protocol: bool\n    :type search_public: bool\n    :type search_private: bool\n    :return: String with top level domain (if ``as_object`` argument\n        is set to False) or a ``tld.utils.Result`` object (if ``as_object``\n        argument is set to True); returns None on failure.\n    :rtype: str\n    "
+    (domain_parts, non_zero_i, parsed_url) = process_url(url=url, fail_silently=fail_silently,
+                                                         fix_protocol=fix_protocol, search_public=search_public, search_private=search_private, parser_class=parser_class)
+    if (domain_parts is None):
+        return None
+    if (not as_object):
+        if (non_zero_i < 0):
+            return parsed_url.hostname
+        return u'.'.join(domain_parts[non_zero_i:])
+    if (non_zero_i < 0):
+        subdomain = u''
+        domain = u''
+        _tld = parsed_url.hostname
+    else:
+        subdomain = u'.'.join(domain_parts[:(non_zero_i - 1)])
+        domain = u'.'.join(domain_parts[(non_zero_i - 1):non_zero_i])
+        _tld = u'.'.join(domain_parts[non_zero_i:])
+    return Result(subdomain=subdomain, domain=domain, tld=_tld, parsed_url=parsed_url)
+
+
+def parse_tld(url, fail_silently=False, fix_protocol=False, search_public=True, search_private=True, parser_class=MozillaTLDSourceParser):
+    u'Parse TLD into parts.\n\n    :param url:\n    :param fail_silently:\n    :param fix_protocol:\n    :param search_public:\n    :param search_private:\n    :param parser_class:\n    :return:\n    :rtype: tuple\n    '
+    try:
+        obj = get_tld(url, fail_silently=fail_silently, as_object=True, fix_protocol=fix_protocol,
+                      search_public=search_public, search_private=search_private, parser_class=parser_class)
+        _tld = obj.tld
+        domain = obj.domain
+        subdomain = obj.subdomain
+    except (TldBadUrl, TldDomainNotFound, TldImproperlyConfigured, TldIOError):
+        _tld = None
+        domain = None
+        subdomain = None
+    return (_tld, domain, subdomain)
+
+
+def is_tld(value, search_public=True, search_private=True, parser_class=MozillaTLDSourceParser):
+    u'Check if given URL is tld.\n\n    :param value: URL to get top level domain from.\n    :param search_public: If set to True, search in public domains.\n    :param search_private: If set to True, search in private domains.\n    :param parser_class:\n    :type value: str\n    :type search_public: bool\n    :type search_private: bool\n    :return:\n    :rtype: bool\n    '
+    _tld = get_tld(url=value, fail_silently=True, fix_protocol=True,
+                   search_public=search_public, search_private=search_private, parser_class=parser_class)
+    return (value == _tld)
+
+
+def reset_tld_names(tld_names_local_path=None):
+    u'Reset the ``tld_names`` to empty value.\n\n    If ``tld_names_local_path`` is given, removes specified\n    entry from ``tld_names`` instead.\n\n    :param tld_names_local_path:\n    :type tld_names_local_path: str\n    :return:\n    '
+    if tld_names_local_path:
+        pop_tld_names_container(tld_names_local_path)
+    else:
+        global tld_names
+        tld_names = {
+
+        }

README.md

@@ -94,6 +94,15 @@ the.vbm, mmgoodnow, Vertig0ne, thliu78, tattoomees, ostman, count_confucius, ehe
 
 ## Changelog
 
+2.6.5.3223
+
+subscene, addic7ed
+- either of those providers might impose a reCAPTCHA verification. In order to use those providers, please create an account at an AntiCaptcha service ([anti-captcha.com](http://getcaptchasolution.com/kkvviom7nh) or [deathbycaptcha.com](http://deathbycaptcha.com)), add funds, then supply your credentials/apikey in the configuration
+
+Changelog
+- core: scoring: reorder subtitles based on second non-hash-score if main hash score is the same; morpheus65535/bazarr#821
+- providers: bsplayer: verify hash; clean up
+
 
 2.6.5.3217