ripristinato doppio-cloudscrape

This commit is contained in:
Alhaziel
2019-12-06 20:13:53 +01:00
committed by marco
parent 528b2e1c75
commit d75d771fe0
31 changed files with 13997 additions and 1252 deletions

View File

@@ -0,0 +1,89 @@
import re
import sys
import logging
import abc
if sys.version_info >= (3, 4):
ABC = abc.ABC # noqa
else:
ABC = abc.ABCMeta('ABC', (), {})
##########################################################################################################################################################
BUG_REPORT = 'Cloudflare may have changed their technique, or there may be a bug in the script.'
##########################################################################################################################################################
interpreters = {}
class JavaScriptInterpreter(ABC):
@abc.abstractmethod
def __init__(self, name):
interpreters[name] = self
@classmethod
def dynamicImport(cls, name):
if name not in interpreters:
try:
__import__('{}.{}'.format(cls.__module__, name))
if not isinstance(interpreters.get(name), JavaScriptInterpreter):
raise ImportError('The interpreter was not initialized.')
except ImportError:
logging.error('Unable to load {} interpreter'.format(name))
raise
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)
except Exception:
logging.error('Error executing Cloudflare IUAM Javascript. {}'.format(BUG_REPORT))
raise
return result

View File

@@ -0,0 +1,95 @@
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
class ChallengeInterpreter(JavaScriptInterpreter):
def __init__(self):
super(ChallengeInterpreter, self).__init__('chakracore')
def eval(self, jsEnv, js):
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('{}{}'.format(jsEnv, js).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()

View File

@@ -0,0 +1,35 @@
from __future__ import absolute_import
import js2py
import logging
import base64
from . import JavaScriptInterpreter
from .jsunfuck import jsunfuck
class ChallengeInterpreter(JavaScriptInterpreter):
def __init__(self):
super(ChallengeInterpreter, self).__init__('js2py')
def eval(self, jsEnv, js):
### blocca lo script
# from core.support import dbg; dbg()
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)
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))
return result
ChallengeInterpreter()

View File

@@ -0,0 +1,97 @@
MAPPING = {
'a': '(false+"")[1]',
'b': '([]["entries"]()+"")[2]',
'c': '([]["fill"]+"")[3]',
'd': '(undefined+"")[2]',
'e': '(true+"")[3]',
'f': '(false+"")[0]',
'g': '(false+[0]+String)[20]',
'h': '(+(101))["to"+String["name"]](21)[1]',
'i': '([false]+undefined)[10]',
'j': '([]["entries"]()+"")[3]',
'k': '(+(20))["to"+String["name"]](21)',
'l': '(false+"")[2]',
'm': '(Number+"")[11]',
'n': '(undefined+"")[1]',
'o': '(true+[]["fill"])[10]',
'p': '(+(211))["to"+String["name"]](31)[1]',
'q': '(+(212))["to"+String["name"]](31)[1]',
'r': '(true+"")[1]',
's': '(false+"")[3]',
't': '(true+"")[0]',
'u': '(undefined+"")[0]',
'v': '(+(31))["to"+String["name"]](32)',
'w': '(+(32))["to"+String["name"]](33)',
'x': '(+(101))["to"+String["name"]](34)[1]',
'y': '(NaN+[Infinity])[10]',
'z': '(+(35))["to"+String["name"]](36)',
'A': '(+[]+Array)[10]',
'B': '(+[]+Boolean)[10]',
'C': 'Function("return escape")()(("")["italics"]())[2]',
'D': 'Function("return escape")()([]["fill"])["slice"]("-1")',
'E': '(RegExp+"")[12]',
'F': '(+[]+Function)[10]',
'G': '(false+Function("return Date")()())[30]',
'I': '(Infinity+"")[0]',
'M': '(true+Function("return Date")()())[30]',
'N': '(NaN+"")[0]',
'O': '(NaN+Function("return{}")())[11]',
'R': '(+[]+RegExp)[10]',
'S': '(+[]+String)[10]',
'T': '(NaN+Function("return Date")()())[30]',
'U': '(NaN+Function("return{}")()["to"+String["name"]]["call"]())[11]',
' ': '(NaN+[]["fill"])[11]',
'"': '("")["fontcolor"]()[12]',
'%': 'Function("return escape")()([]["fill"])[21]',
'&': '("")["link"](0+")[10]',
'(': '(undefined+[]["fill"])[22]',
')': '([0]+false+[]["fill"])[20]',
'+': '(+(+!+[]+(!+[]+[])[!+[]+!+[]+!+[]]+[+!+[]]+[+[]]+[+[]])+[])[2]',
',': '([]["slice"]["call"](false+"")+"")[1]',
'-': '(+(.+[0000000001])+"")[2]',
'.': '(+(+!+[]+[+!+[]]+(!![]+[])[!+[]+!+[]+!+[]]+[!+[]+!+[]]+[+[]])+[])[+!+[]]',
'/': '(false+[0])["italics"]()[10]',
':': '(RegExp()+"")[3]',
';': '("")["link"](")[14]',
'<': '("")["italics"]()[0]',
'=': '("")["fontcolor"]()[11]',
'>': '("")["italics"]()[2]',
'?': '(RegExp()+"")[2]',
'[': '([]["entries"]()+"")[0]',
']': '([]["entries"]()+"")[22]',
'{': '(true+[]["fill"])[20]',
'}': '([]["fill"]+"")["slice"]("-1")'
}
SIMPLE = {
'false': '![]',
'true': '!![]',
'undefined': '[][[]]',
'NaN': '+[![]]',
'Infinity': '+(+!+[]+(!+[]+[])[!+[]+!+[]+!+[]]+[+!+[]]+[+[]]+[+[]]+[+[]])' # +"1e1000"
}
CONSTRUCTORS = {
'Array': '[]',
'Number': '(+[])',
'String': '([]+[])',
'Boolean': '(![])',
'Function': '[]["fill"]',
'RegExp': 'Function("return/"+false+"/")()'
}
def jsunfuck(jsfuckString):
for key in sorted(MAPPING, key=lambda k: len(MAPPING[k]), reverse=True):
if MAPPING.get(key) in jsfuckString:
jsfuckString = jsfuckString.replace(MAPPING.get(key), '"{}"'.format(key))
for key in sorted(SIMPLE, key=lambda k: len(SIMPLE[k]), reverse=True):
if SIMPLE.get(key) in jsfuckString:
jsfuckString = jsfuckString.replace(SIMPLE.get(key), '{}'.format(key))
# for key in sorted(CONSTRUCTORS, key=lambda k: len(CONSTRUCTORS[k]), reverse=True):
# if CONSTRUCTORS.get(key) in jsfuckString:
# jsfuckString = jsfuckString.replace(CONSTRUCTORS.get(key), '{}'.format(key))
return jsfuckString

View File

@@ -0,0 +1,46 @@
import base64
import logging
import subprocess
from . import JavaScriptInterpreter
##########################################################################################################################################################
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):
try:
js = 'var atob = function(str) {return Buffer.from(str, "base64").toString("binary");};' \
'var challenge = atob("%s");' \
'var context = {atob: atob};' \
'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')
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.'
)
raise
except Exception:
logging.error('Error executing Cloudflare IUAM Javascript. %s' % BUG_REPORT)
raise
pass
ChallengeInterpreter()

View File

@@ -0,0 +1,26 @@
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
class ChallengeInterpreter(JavaScriptInterpreter):
def __init__(self):
super(ChallengeInterpreter, self).__init__('v8')
def eval(self, jsEnv, js):
try:
return v8eval.V8().eval('{}{}'.format(jsEnv, js))
except: # noqa
RuntimeError('We encountered an error running the V8 Engine.')
ChallengeInterpreter()