improve and document cloudflare bypass code

pull/86/head
Mike Fährmann 7 years ago
parent 728c64a3fb
commit ff643793bd
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88

@ -1,6 +1,6 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
# Copyright 2015-2017 Mike Fährmann # Copyright 2015-2018 Mike Fährmann
# #
# This program is free software; you can redistribute it and/or modify # This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as # it under the terms of the GNU General Public License version 2 as
@ -8,6 +8,7 @@
"""Methods to access sites behind Cloudflare protection""" """Methods to access sites behind Cloudflare protection"""
import re
import time import time
import operator import operator
import urllib.parse import urllib.parse
@ -30,6 +31,7 @@ def request_func(self, *args, **kwargs):
def solve_challenge(session, response): def solve_challenge(session, response):
session.headers["Referer"] = response.url session.headers["Referer"] = response.url
page = response.text page = response.text
params = text.extract_all(page, ( params = text.extract_all(page, (
@ -37,6 +39,7 @@ def solve_challenge(session, response):
('pass' , 'name="pass" value="', '"'), ('pass' , 'name="pass" value="', '"'),
))[0] ))[0]
params["jschl_answer"] = solve_jschl(response.url, page) params["jschl_answer"] = solve_jschl(response.url, page)
time.sleep(4) time.sleep(4)
url = urllib.parse.urljoin(response.url, "/cdn-cgi/l/chk_jschl") url = urllib.parse.urljoin(response.url, "/cdn-cgi/l/chk_jschl")
return session.get(url, params=params) return session.get(url, params=params)
@ -44,51 +47,66 @@ def solve_challenge(session, response):
def solve_jschl(url, page): def solve_jschl(url, page):
"""Solve challenge to get 'jschl_answer' value""" """Solve challenge to get 'jschl_answer' value"""
# build variable name
# e.g. '...f, wqnVscP={"DERKbJk":+(...' --> wqnVscP.DERKbJk
data, pos = text.extract_all(page, ( data, pos = text.extract_all(page, (
('var' , ',f, ', '='), ('var' , ',f, ', '='),
('key' , '"', '"'), ('key' , '"', '"'),
('expr', ':', '}'), ('expr', ':', '}'),
)) ))
solution = evaluate_expression(data["expr"])
variable = "{}.{}".format(data["var"], data["key"]) variable = "{}.{}".format(data["var"], data["key"])
vlength = len(variable) vlength = len(variable)
# evaluate the initial expression
solution = evaluate_expression(data["expr"])
# iterator over all remaining expressions
# and combine their values in 'solution'
expressions = text.extract( expressions = text.extract(
page, "'challenge-form');", "f.submit();", pos page, "'challenge-form');", "f.submit();", pos)[0]
)[0]
for expr in expressions.split(";")[1:]: for expr in expressions.split(";")[1:]:
if expr.startswith(variable): if expr.startswith(variable):
# select arithmetc function based on operator (+, -, *)
func = operator_functions[expr[vlength]] func = operator_functions[expr[vlength]]
# evaluate the rest of the expression
value = evaluate_expression(expr[vlength+2:]) value = evaluate_expression(expr[vlength+2:])
# combine the expression value with our current solution
solution = func(solution, value) solution = func(solution, value)
elif expr.startswith("a.value"): elif expr.startswith("a.value"):
# add length of the hostname, i.e. add 11 for 'example.org'
solution += len(urllib.parse.urlsplit(url).netloc) solution += len(urllib.parse.urlsplit(url).netloc)
if ".toFixed(" in expr: if ".toFixed(" in expr:
# trim the solution to 10 decimal places
# and strip trailing zeros
solution = "{:.10f}".format(solution).rstrip("0") solution = "{:.10f}".format(solution).rstrip("0")
return solution return solution
def evaluate_expression(expr): def evaluate_expression(expr, split_re=re.compile(r"\(+([^)]*)\)")):
"""Evaluate a Javascript expression for the challenge""" """Evaluate a Javascript expression for the challenge"""
if "/" in expr: if "/" in expr:
# split the expression in numerator and denominator subexpressions,
# evaluate them separately,
# and return their fraction-result
num, _, denom = expr.partition("/") num, _, denom = expr.partition("/")
return evaluate_expression(num) / evaluate_expression(denom) return evaluate_expression(num) / evaluate_expression(denom)
stack = [] # iterate over all subexpressions,
ranges = [] # evaluate them,
value = "" # and accumulate their values in 'result'
for index, char in enumerate(expr): result = ""
if char == "(": for subexpr in split_re.findall(expr):
stack.append(index+1) result += str(sum(
elif char == ")": expression_values[part]
begin = stack.pop() for part in subexpr.split("[]")
if stack: ))
ranges.append((begin, index)) return int(result)
for subexpr in [expr[begin:end] for begin, end in ranges] or (expr,):
num = 0
for part in subexpr.split("[]"):
num += expression_values[part]
value += str(num)
return int(value)
operator_functions = { operator_functions = {

Loading…
Cancel
Save