def solve_challenge(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\'', '').replace('; ;', ';')
js += '\na.value;'
js_env = '''
String.prototype.italics=function(str) {{return "<i>" + this + "</i>";}};
var document = {{
createElement: function () {{
return {{ firstChild: {{ href: "https://{domain}/" }} }}
}},
getElementById: function () {{
return {{"innerHTML": "{innerHTML}"}};
}}
}};
'''
try:
inner_html = re.search(
r'<div(?: [^<>]*)? id="([^<>]*?)">([^<>]*?)</div>', body,
re.MULTILINE | re.DOTALL)
inner_html = inner_html.group(2) if inner_html else ''
except:
logging.error(
'Error extracting Cloudflare IUAM Javascript. {}'.format(
BUG_REPORT))
raise
try:
js_env = re.sub(r'\s{2,}',
' ',
js_env.format(domain=domain, innerHTML=inner_html),
flags=re.MULTILINE | re.DOTALL)
def atob(s):
return base64.b64decode('{}'.format(s)).decode('utf-8')
js2py.disable_pyimport()
with LOCK:
context = js2py.EvalJs({'atob': atob})
result = context.eval('{}{}'.format(js_env, js))
float(result)
except Exception:
raise ValueError(
"Cloudflare IUAM challenge returned unexpected answer. {}".
format(BUG_REPORT))
return result
def __init__(self, pac_js, recursion_limit=ARBITRARY_HIGH_RECURSION_LIMIT):
"""
Load a PAC file from a given string of JavaScript.
Errors during parsing and validation may raise a specialized exception.
:param str pac_js: JavaScript that defines the FindProxyForURL() function.
:param int recursion_limit: Python recursion limit when executing JavaScript.
PAC files are often complex enough to need this to be higher than the interpreter default.
:raises MalformedPacError: If the JavaScript could not be parsed, does not define FindProxyForURL(),
or is otherwise invalid.
:raises PyImportError: If the JavaScript tries to use Js2Py's `pyimport` keyword,
which is not legitimate in the context of a PAC file.
:raises PacComplexityError: If the JavaScript was complex enough that the
Python recursion limit was hit during parsing.
"""
self._recursion_limit = recursion_limit
if 'pyimport' in pac_js:
raise PyimportError()
# Disallow parsing of the unsafe 'pyimport' statement in Js2Py.
js2py.disable_pyimport()
try:
with _temp_recursion_limit(self._recursion_limit):
context = js2py.EvalJs(function_injections)
context.execute(pac_js)
# A test call to weed out errors like unimplemented functions.
context.FindProxyForURL('/', '0.0.0.0')
self._context = context
self._func = context.FindProxyForURL
except PyJsException: # as e:
raise MalformedPacError() # from e
except RuntimeError:
# RecursionError in PY >= 3.5.
raise PacComplexityError()
def findvideos(item):
logger.info()
itemlist = []
data = httptools.downloadpage(item.url).data
_sa = scrapertools.find_single_match(data, 'var _sa = (true|false);')
_sl = scrapertools.find_single_match(data, 'var _sl = ([^;]+);')
sl = eval(_sl)
#buttons = scrapertools.find_multiple_matches(data, '<button href="" class="selop" sl="([^"]+)">')
buttons = [0, 1, 2]
for id in buttons:
new_url = golink(int(id), _sa, sl)
data_new = httptools.downloadpage(new_url).data
matches = scrapertools.find_multiple_matches(
data_new, 'javascript">(.*?)</script>')
js = ""
for part in matches:
js += part
#logger.info("test before:" + js)
try:
matches = scrapertools.find_multiple_matches(
data_new, '" id="(.*?)" val="(.*?)"')
for zanga, val in matches:
js = js.replace(
'var %s = document.getElementById("%s");' % (zanga, zanga),
"")
js = js.replace('%s.getAttribute("val")' % zanga, '"%s"' % val)
#logger.info("test1 after:" +js)
except:
pass
js = re.sub('(document\[.*?)=', 'prem=', js)
import js2py
js2py.disable_pyimport()
context = js2py.EvalJs({'atob': atob})
result = context.eval(js)
url = scrapertools.find_single_match(result, 'src="(.*?)"')
title = '%s'
itemlist.append(
Item(channel=item.channel,
title=title,
url=url,
action='play',
language='latino',
infoLabels=item.infoLabels))
itemlist = servertools.get_servers_itemlist(
itemlist, lambda i: i.title % i.server.capitalize())
# Requerido para FilterTools
itemlist = filtertools.get_links(itemlist, item, list_language)
# Requerido para AutoPlay
autoplay.start(itemlist, item)
return itemlist
def eval(self, jsEnv, js):
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
def solve_cf(self, body, domain):
# Adaptado de: https://github.com/VeNoMouS/cloudflare-scrape-js2py
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)
js = re.sub(r"a\.value = ((.+).toFixed\(10\))?", r"\1", js)
js = re.sub(r'(e\s=\sfunction\(s\)\s{.*?};)',
'',
js,
flags=re.DOTALL | re.MULTILINE)
js = re.sub(r"\s{3,}[a-z](?: = |\.).+", "",
js).replace("t.length", str(len(domain)))
js = js.replace('; 121', '')
js = re.sub(r"[\n\\']", "", js)
jsEnv = """
var t = "{domain}";
var g = String.fromCharCode;
o = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=";
e = function(s) {{
s += "==".slice(2 - (s.length & 3));
var bm, r = "", r1, r2, i = 0;
for (; i < s.length;) {{
bm = o.indexOf(s.charAt(i++)) << 18 | o.indexOf(s.charAt(i++)) << 12 | (r1 = o.indexOf(s.charAt(i++))) << 6 | (r2 = o.indexOf(s.charAt(i++)));
r += r1 === 64 ? g(bm >> 16 & 255) : r2 === 64 ? g(bm >> 16 & 255, bm >> 8 & 255) : g(bm >> 16 & 255, bm >> 8 & 255, bm & 255);
}}
return r;
}};
function italics (str) {{ return '<i>' + this + '</i>'; }};
var document = {{
getElementById: function () {{
return {{'innerHTML': '{innerHTML}'}};
}}
}};
{js}
"""
innerHTML = re.search(
'<div(?: [^<>]*)? id="([^<>]*?)">([^<>]*?)<\/div>', body,
re.MULTILINE | re.DOTALL)
innerHTML = innerHTML.group(2).replace("'", r"\'") if innerHTML else ""
import js2py
from jsc import jsunc
js = jsunc(jsEnv.format(domain=domain, innerHTML=innerHTML, js=js))
def atob(s):
return base64.b64decode('{}'.format(s)).decode('utf-8')
js2py.disable_pyimport()
context = js2py.EvalJs({'atob': atob})
result = context.eval(js)
return float(result)
def eval(self, jsEnv, js):
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
assert js2py.eval_js('1 + "1"') == '11'
assert js2py.eval_js('function (r) {return r}')(5) == 5
x, c = js2py.run_file('examples/esprima.js')
assert c.esprima.parse('var abc = 40').to_dict() == {'type': 'Program', 'body': [{'type': 'VariableDeclaration', 'kind': 'var', 'declarations': [{'id': {'type': 'Identifier', 'name': 'abc'}, 'type': 'VariableDeclarator', 'init': {'type': 'Literal', 'raw': '40', 'value': 40}}]}], 'sourceType': 'script'}
try:
assert js2py.eval_js('syntax error!') and 0
except js2py.PyJsException as err:
assert str(err).startswith('SyntaxError: ')
assert js2py.eval_js('pyimport time; time.time()') <= time.time()
js2py.disable_pyimport()
try:
assert js2py.eval_js('pyimport time') and 0
except js2py.PyJsException as err:
assert str(err).startswith('SyntaxError: ')
# Simple PyWrapper test
class Foo:
def __init__(self, bar):
self.bar = bar
self.bar_history = []
def set_bar(self, x):
import copy
self.bar_history.append(copy.deepcopy(self))
def __init__(self):
self._lock = Lock()
self._libraries = VDOM_javascript_libraries(self)
js2py.disable_pyimport()
def solve_challenge(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"a\.value = ((.+).toFixed\(10\))?", r"\1", js)
js = re.sub(r'(e\s=\sfunction\(s\)\s{.*?};)',
'',
js,
flags=re.DOTALL | re.MULTILINE)
js = re.sub(r"\s{3,}[a-z](?: = |\.).+", "",
js).replace("t.length", str(len(domain)))
js = js.replace('; 121', '')
# Strip characters that could be used to exit the string context
# These characters are not currently used in Cloudflare's arithmetic snippet
js = re.sub(r"[\n\\']", "", js)
if 'toFixed' not in js:
raise ValueError(
"Error parsing Cloudflare IUAM Javascript challenge. {}".
format(BUG_REPORT))
try:
jsEnv = """
var t = "{domain}";
var g = String.fromCharCode;
o = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=";
e = function(s) {{
s += "==".slice(2 - (s.length & 3));
var bm, r = "", r1, r2, i = 0;
for (; i < s.length;) {{
bm = o.indexOf(s.charAt(i++)) << 18 | o.indexOf(s.charAt(i++)) << 12 | (r1 = o.indexOf(s.charAt(i++))) << 6 | (r2 = o.indexOf(s.charAt(i++)));
r += r1 === 64 ? g(bm >> 16 & 255) : r2 === 64 ? g(bm >> 16 & 255, bm >> 8 & 255) : g(bm >> 16 & 255, bm >> 8 & 255, bm & 255);
}}
return r;
}};
function italics (str) {{ return '<i>' + this + '</i>'; }};
var document = {{
getElementById: function () {{
return {{'innerHTML': '{innerHTML}'}};
}}
}};
{js}
"""
innerHTML = re.search(
'<div(?: [^<>]*)? id="([^<>]*?)">([^<>]*?)<\/div>', body,
re.MULTILINE | re.DOTALL)
innerHTML = innerHTML.group(2).replace("'",
r"\'") if innerHTML else ""
js = jsunfuck(
jsEnv.format(domain=domain, innerHTML=innerHTML, js=js))
def atob(s):
return base64.b64decode('{}'.format(s)).decode('utf-8')
js2py.disable_pyimport()
context = js2py.EvalJs({'atob': atob})
result = context.eval(js)
except Exception:
logging.error(
"Error executing Cloudflare IUAM Javascript. {}".format(
BUG_REPORT))
raise
try:
float(result)
except Exception:
raise ValueError(
"Cloudflare IUAM challenge returned unexpected answer. {}".
format(BUG_REPORT))
return result
def solve_challenge(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"a\.value = ((.+).toFixed\(10\))?", r"\1", js)
js = re.sub(r'(e\s=\sfunction\(s\)\s{.*?};)', '', js, flags=re.DOTALL|re.MULTILINE)
js = re.sub(r"\s{3,}[a-z](?: = |\.).+", "", js).replace("t.length", str(len(domain)))
js = js.replace('; 121', '')
# Strip characters that could be used to exit the string context
# These characters are not currently used in Cloudflare's arithmetic snippet
js = re.sub(r"[\n\\']", "", js)
if 'toFixed' not in js:
raise ValueError("Error parsing Cloudflare IUAM Javascript challenge. {}".format(BUG_REPORT))
try:
jsEnv = """
var t = "{domain}";
var g = String.fromCharCode;
o = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=";
e = function(s) {{
s += "==".slice(2 - (s.length & 3));
var bm, r = "", r1, r2, i = 0;
for (; i < s.length;) {{
bm = o.indexOf(s.charAt(i++)) << 18 | o.indexOf(s.charAt(i++)) << 12 | (r1 = o.indexOf(s.charAt(i++))) << 6 | (r2 = o.indexOf(s.charAt(i++)));
r += r1 === 64 ? g(bm >> 16 & 255) : r2 === 64 ? g(bm >> 16 & 255, bm >> 8 & 255) : g(bm >> 16 & 255, bm >> 8 & 255, bm & 255);
}}
return r;
}};
function italics (str) {{ return '<i>' + this + '</i>'; }};
var document = {{
getElementById: function () {{
return {{'innerHTML': '{innerHTML}'}};
}}
}};
{js}
"""
innerHTML = re.search(
'<div(?: [^<>]*)? id="([^<>]*?)">([^<>]*?)<\/div>',
body,
re.MULTILINE | re.DOTALL
)
innerHTML = innerHTML.group(2).replace("'", r"\'") if innerHTML else ""
js = jsunfuck(jsEnv.format(domain=domain, innerHTML=innerHTML, js=js))
def atob(s):
return base64.b64decode('{}'.format(s)).decode('utf-8')
js2py.disable_pyimport()
context = js2py.EvalJs({'atob': atob})
result = context.eval(js)
except Exception:
logging.error("Error executing Cloudflare IUAM Javascript. {}".format(BUG_REPORT))
raise
try:
float(result)
except Exception:
raise ValueError("Cloudflare IUAM challenge returned unexpected answer. {}".format(BUG_REPORT))
return result
