Cloudflare improvements (#1448)
* Upgraded cloudscraper to fix multiple issues with providers that uses antibot page. * Fixed subs4series provider. It now require anti-captcha provider to download subtitles. One captcha will have to be solved for each download. #1442pull/1451/head
morpheus65535
3 years ago
committed by
GitHub
parent
058ae489f0
commit
cb420628f8
@ -0,0 +1,260 @@
|
||||
from __future__ import absolute_import
|
||||
|
||||
import requests
|
||||
try:
|
||||
from urlparse import urlparse
|
||||
except ImportError:
|
||||
from urllib.parse import urlparse
|
||||
|
||||
from ..exceptions import (
|
||||
CaptchaServiceUnavailable,
|
||||
CaptchaAPIError,
|
||||
CaptchaTimeout,
|
||||
CaptchaParameter,
|
||||
CaptchaBadJobID,
|
||||
CaptchaReportError
|
||||
)
|
||||
|
||||
try:
|
||||
import polling2
|
||||
except ImportError:
|
||||
raise ImportError("Please install the python module 'polling2' via pip")
|
||||
|
||||
from . import Captcha
|
||||
|
||||
|
||||
class captchaSolver(Captcha):
|
||||
|
||||
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 CaptchaServiceUnavailable(f'2Captcha: Server Side Error {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."
|
||||
}
|
||||
}
|
||||
|
||||
rPayload = response.json()
|
||||
if rPayload.get('status') == 0 and rPayload.get('request') in errors.get(request_type):
|
||||
raise CaptchaAPIError(
|
||||
f"{rPayload['request']} {errors.get(request_type).get(rPayload['request'])}"
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def reportJob(self, jobID):
|
||||
if not jobID:
|
||||
raise CaptchaBadJobID(
|
||||
"2Captcha: Error bad job id to request Captcha."
|
||||
)
|
||||
|
||||
def _checkRequest(response):
|
||||
self.checkErrorStatus(response, 'res.php')
|
||||
if response.ok and response.json().get('status') == 1:
|
||||
return response
|
||||
return None
|
||||
|
||||
response = polling2.poll(
|
||||
lambda: self.session.get(
|
||||
f'{self.host}/res.php',
|
||||
params={
|
||||
'key': self.api_key,
|
||||
'action': 'reportbad',
|
||||
'id': jobID,
|
||||
'json': '1'
|
||||
},
|
||||
timeout=30
|
||||
),
|
||||
check_success=_checkRequest,
|
||||
step=5,
|
||||
timeout=180
|
||||
)
|
||||
|
||||
if response:
|
||||
return True
|
||||
else:
|
||||
raise CaptchaReportError(
|
||||
"2Captcha: Error - Failed to report bad Captcha solve."
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def requestJob(self, jobID):
|
||||
if not jobID:
|
||||
raise CaptchaBadJobID("2Captcha: Error bad job id to request Captcha.")
|
||||
|
||||
def _checkRequest(response):
|
||||
self.checkErrorStatus(response, 'res.php')
|
||||
if response.ok and response.json().get('status') == 1:
|
||||
return response
|
||||
return None
|
||||
|
||||
response = polling2.poll(
|
||||
lambda: self.session.get(
|
||||
f'{self.host}/res.php',
|
||||
params={
|
||||
'key': self.api_key,
|
||||
'action': 'get',
|
||||
'id': jobID,
|
||||
'json': '1'
|
||||
},
|
||||
timeout=30
|
||||
),
|
||||
check_success=_checkRequest,
|
||||
step=5,
|
||||
timeout=180
|
||||
)
|
||||
|
||||
if response:
|
||||
return response.json().get('request')
|
||||
else:
|
||||
raise CaptchaTimeout(
|
||||
"2Captcha: Error failed to solve Captcha."
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def requestSolve(self, captchaType, url, siteKey):
|
||||
def _checkRequest(response):
|
||||
self.checkErrorStatus(response, 'in.php')
|
||||
if response.ok and response.json().get("status") == 1 and response.json().get('request'):
|
||||
return response
|
||||
return None
|
||||
|
||||
data = {
|
||||
'key': self.api_key,
|
||||
'pageurl': url,
|
||||
'json': 1,
|
||||
'soft_id': 2905
|
||||
}
|
||||
|
||||
data.update(
|
||||
{
|
||||
'method': 'userrcaptcha',
|
||||
'googlekey': siteKey
|
||||
} if captchaType == 'reCaptcha' else {
|
||||
'method': 'hcaptcha',
|
||||
'sitekey': siteKey
|
||||
}
|
||||
)
|
||||
|
||||
if self.proxy:
|
||||
data.update(
|
||||
{
|
||||
'proxy': self.proxy,
|
||||
'proxytype': self.proxyType
|
||||
}
|
||||
)
|
||||
|
||||
response = polling2.poll(
|
||||
lambda: self.session.post(
|
||||
f'{self.host}/in.php',
|
||||
data=data,
|
||||
allow_redirects=False,
|
||||
timeout=30
|
||||
),
|
||||
check_success=_checkRequest,
|
||||
step=5,
|
||||
timeout=180
|
||||
)
|
||||
|
||||
if response:
|
||||
return response.json().get('request')
|
||||
else:
|
||||
raise CaptchaBadJobID(
|
||||
'2Captcha: Error no job id was returned.'
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def getCaptchaAnswer(self, captchaType, url, siteKey, captchaParams):
|
||||
jobID = None
|
||||
|
||||
if not captchaParams.get('api_key'):
|
||||
raise CaptchaParameter(
|
||||
"2Captcha: Missing api_key parameter."
|
||||
)
|
||||
|
||||
self.api_key = captchaParams.get('api_key')
|
||||
|
||||
if captchaParams.get('proxy') and not captchaParams.get('no_proxy'):
|
||||
hostParsed = urlparse(captchaParams.get('proxy', {}).get('https'))
|
||||
|
||||
if not hostParsed.scheme:
|
||||
raise CaptchaParameter('Cannot parse proxy correctly, bad scheme')
|
||||
|
||||
if not hostParsed.netloc:
|
||||
raise CaptchaParameter('Cannot parse proxy correctly, bad netloc')
|
||||
|
||||
self.proxyType = hostParsed.scheme
|
||||
self.proxy = hostParsed.netloc
|
||||
else:
|
||||
self.proxy = None
|
||||
|
||||
try:
|
||||
jobID = self.requestSolve(captchaType, url, siteKey)
|
||||
return self.requestJob(jobID)
|
||||
except polling2.TimeoutException:
|
||||
try:
|
||||
if jobID:
|
||||
self.reportJob(jobID)
|
||||
except polling2.TimeoutException:
|
||||
raise CaptchaTimeout(
|
||||
f"2Captcha: Captcha solve took to long and also failed reporting the job the job id {jobID}."
|
||||
)
|
||||
|
||||
raise CaptchaTimeout(
|
||||
f"2Captcha: Captcha solve took to long to execute job id {jobID}, aborting."
|
||||
)
|
||||
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
captchaSolver()
|
||||
@ -0,0 +1,212 @@
|
||||
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(
|
||||
f'9kw: Server Side Error {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, captchaType, url, siteKey):
|
||||
def _checkRequest(response):
|
||||
if response.ok and response.text.startswith('{') and response.json().get('captchaid'):
|
||||
return response
|
||||
|
||||
self.checkErrorStatus(response)
|
||||
|
||||
return None
|
||||
|
||||
captchaMap = {
|
||||
'reCaptcha': 'recaptchav2',
|
||||
'hCaptcha': 'hcaptcha'
|
||||
}
|
||||
|
||||
response = polling.poll(
|
||||
lambda: self.session.post(
|
||||
self.host,
|
||||
data={
|
||||
'apikey': self.api_key,
|
||||
'action': 'usercaptchaupload',
|
||||
'interactive': 1,
|
||||
'file-upload-01': siteKey,
|
||||
'oldsource': captchaMap[captchaType],
|
||||
'pageurl': 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, captchaType, url, siteKey, 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(captchaType, url, siteKey)
|
||||
return self.requestJob(jobID)
|
||||
except polling.TimeoutException:
|
||||
raise reCaptchaTimeout(
|
||||
f"9kw: reCaptcha solve took to long to execute 'captchaid' {jobID}, aborting."
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
|
||||
captchaSolver()
|
||||
@ -0,0 +1,47 @@
|
||||
import abc
|
||||
import logging
|
||||
import sys
|
||||
|
||||
if sys.version_info >= (3, 4):
|
||||
ABC = abc.ABC # noqa
|
||||
else:
|
||||
ABC = abc.ABCMeta('ABC', (), {})
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
captchaSolvers = {}
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
|
||||
class Captcha(ABC):
|
||||
@abc.abstractmethod
|
||||
def __init__(self, name):
|
||||
captchaSolvers[name] = self
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
@classmethod
|
||||
def dynamicImport(cls, name):
|
||||
if name not in captchaSolvers:
|
||||
try:
|
||||
__import__(f'{cls.__module__}.{name}')
|
||||
if not isinstance(captchaSolvers.get(name), Captcha):
|
||||
raise ImportError('The anti captcha provider was not initialized.')
|
||||
except ImportError as e:
|
||||
sys.tracebacklimit = 0
|
||||
logging.error(f'Unable to load {name} anti captcha provider -> {e}')
|
||||
raise
|
||||
|
||||
return captchaSolvers[name]
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
@abc.abstractmethod
|
||||
def getCaptchaAnswer(self, captchaType, url, siteKey, captchaParams):
|
||||
pass
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def solveCaptcha(self, captchaType, url, siteKey, captchaParams):
|
||||
return self.getCaptchaAnswer(captchaType, url, siteKey, captchaParams)
|
||||
@ -0,0 +1,109 @@
|
||||
from __future__ import absolute_import
|
||||
from ..exceptions import (
|
||||
CaptchaParameter,
|
||||
CaptchaTimeout,
|
||||
CaptchaAPIError
|
||||
)
|
||||
|
||||
try:
|
||||
from urlparse import urlparse
|
||||
except ImportError:
|
||||
from urllib.parse import urlparse
|
||||
|
||||
try:
|
||||
from python_anticaptcha import (
|
||||
AnticaptchaClient,
|
||||
NoCaptchaTaskProxylessTask,
|
||||
HCaptchaTaskProxyless,
|
||||
NoCaptchaTask,
|
||||
HCaptchaTask,
|
||||
AnticaptchaException
|
||||
)
|
||||
except ImportError:
|
||||
raise ImportError(
|
||||
"Please install/upgrade the python module 'python_anticaptcha' via "
|
||||
"pip install python-anticaptcha or https://github.com/ad-m/python-anticaptcha/"
|
||||
)
|
||||
|
||||
import sys
|
||||
|
||||
from . import Captcha
|
||||
|
||||
|
||||
class captchaSolver(Captcha):
|
||||
|
||||
def __init__(self):
|
||||
if sys.modules['python_anticaptcha'].__version__ < '0.6':
|
||||
raise ImportError(
|
||||
"Please upgrade the python module 'python_anticaptcha' via "
|
||||
"pip install -U python-anticaptcha or https://github.com/ad-m/python-anticaptcha/"
|
||||
)
|
||||
super(captchaSolver, self).__init__('anticaptcha')
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def parseProxy(self, url, user_agent):
|
||||
parsed = urlparse(url)
|
||||
|
||||
return dict(
|
||||
proxy_type=parsed.scheme,
|
||||
proxy_address=parsed.hostname,
|
||||
proxy_port=parsed.port,
|
||||
proxy_login=parsed.username,
|
||||
proxy_password=parsed.password,
|
||||
user_agent=user_agent
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def getCaptchaAnswer(self, captchaType, url, siteKey, captchaParams):
|
||||
if not captchaParams.get('api_key'):
|
||||
raise CaptchaParameter("anticaptcha: Missing api_key parameter.")
|
||||
|
||||
client = AnticaptchaClient(captchaParams.get('api_key'))
|
||||
|
||||
if captchaParams.get('proxy') and not captchaParams.get('no_proxy'):
|
||||
captchaMap = {
|
||||
'reCaptcha': NoCaptchaTask,
|
||||
'hCaptcha': HCaptchaTask
|
||||
}
|
||||
|
||||
proxy = self.parseProxy(
|
||||
captchaParams.get('proxy', {}).get('https'),
|
||||
captchaParams.get('User-Agent', '')
|
||||
)
|
||||
|
||||
task = captchaMap[captchaType](
|
||||
url,
|
||||
siteKey,
|
||||
**proxy
|
||||
)
|
||||
else:
|
||||
captchaMap = {
|
||||
'reCaptcha': NoCaptchaTaskProxylessTask,
|
||||
'hCaptcha': HCaptchaTaskProxyless
|
||||
}
|
||||
task = captchaMap[captchaType](url, siteKey)
|
||||
|
||||
if not hasattr(client, 'createTaskSmee'):
|
||||
raise NotImplementedError(
|
||||
"Please upgrade 'python_anticaptcha' via pip or download it from "
|
||||
"https://github.com/ad-m/python-anticaptcha/tree/hcaptcha"
|
||||
)
|
||||
|
||||
job = client.createTaskSmee(task, timeout=180)
|
||||
|
||||
try:
|
||||
job.join(maximum_time=180)
|
||||
except (AnticaptchaException) as e:
|
||||
raise CaptchaTimeout(f"{getattr(e, 'message', e)}")
|
||||
|
||||
if 'solution' in job._last_result:
|
||||
return job.get_solution_response()
|
||||
else:
|
||||
raise CaptchaAPIError('Job did not return `solution` key in payload.')
|
||||
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
captchaSolver()
|
||||
@ -0,0 +1,190 @@
|
||||
from __future__ import absolute_import
|
||||
|
||||
import requests
|
||||
|
||||
try:
|
||||
from urlparse import urlparse
|
||||
except ImportError:
|
||||
from urllib.parse import urlparse
|
||||
|
||||
from ..exceptions import (
|
||||
CaptchaServiceUnavailable,
|
||||
CaptchaAPIError,
|
||||
CaptchaTimeout,
|
||||
CaptchaParameter,
|
||||
CaptchaBadJobID
|
||||
)
|
||||
|
||||
try:
|
||||
import polling2
|
||||
except ImportError:
|
||||
raise ImportError("Please install the python module 'polling2' via pip")
|
||||
|
||||
from . import Captcha
|
||||
|
||||
|
||||
class captchaSolver(Captcha):
|
||||
|
||||
def __init__(self):
|
||||
super(captchaSolver, self).__init__('capmonster')
|
||||
self.host = 'https://api.capmonster.cloud'
|
||||
self.session = requests.Session()
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
@staticmethod
|
||||
def checkErrorStatus(response):
|
||||
if response.status_code in [500, 502]:
|
||||
raise CaptchaServiceUnavailable(
|
||||
f'CapMonster: Server Side Error {response.status_code}'
|
||||
)
|
||||
|
||||
payload = response.json()
|
||||
if payload['errorId'] == 1:
|
||||
if 'errorDescription' in payload:
|
||||
raise CaptchaAPIError(
|
||||
payload['errorDescription']
|
||||
)
|
||||
else:
|
||||
raise CaptchaAPIError(payload['errorCode'])
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def requestJob(self, taskID):
|
||||
if not taskID:
|
||||
raise CaptchaBadJobID(
|
||||
'CapMonster: Error bad task id to request Captcha.'
|
||||
)
|
||||
|
||||
def _checkRequest(response):
|
||||
self.checkErrorStatus(response)
|
||||
|
||||
if response.ok and response.json()['status'] == 'ready':
|
||||
return True
|
||||
|
||||
return None
|
||||
|
||||
response = polling2.poll(
|
||||
lambda: self.session.post(
|
||||
f'{self.host}/getTaskResult',
|
||||
json={
|
||||
'clientKey': self.clientKey,
|
||||
'taskId': taskID
|
||||
},
|
||||
timeout=30
|
||||
),
|
||||
check_success=_checkRequest,
|
||||
step=5,
|
||||
timeout=180
|
||||
)
|
||||
|
||||
if response:
|
||||
return response.json()['solution']['gRecaptchaResponse']
|
||||
else:
|
||||
raise CaptchaTimeout(
|
||||
"CapMonster: Error failed to solve Captcha."
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def requestSolve(self, captchaType, url, siteKey):
|
||||
def _checkRequest(response):
|
||||
self.checkErrorStatus(response)
|
||||
|
||||
if response.ok and response.json()['taskId']:
|
||||
return True
|
||||
|
||||
return None
|
||||
|
||||
data = {
|
||||
'clientKey': self.clientKey,
|
||||
'task': {
|
||||
'websiteURL': url,
|
||||
'websiteKey': siteKey,
|
||||
'softId': 37,
|
||||
'type': 'NoCaptchaTask' if captchaType == 'reCaptcha' else 'HCaptchaTask'
|
||||
}
|
||||
}
|
||||
|
||||
if self.proxy:
|
||||
data['task'].update(self.proxy)
|
||||
else:
|
||||
data['task']['type'] = f"{data['task']['type']}Proxyless"
|
||||
|
||||
response = polling2.poll(
|
||||
lambda: self.session.post(
|
||||
f'{self.host}/createTask',
|
||||
json=data,
|
||||
allow_redirects=False,
|
||||
timeout=30
|
||||
),
|
||||
check_success=_checkRequest,
|
||||
step=5,
|
||||
timeout=180
|
||||
)
|
||||
|
||||
if response:
|
||||
return response.json()['taskId']
|
||||
else:
|
||||
raise CaptchaBadJobID(
|
||||
'CapMonster: Error no task id was returned.'
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def getCaptchaAnswer(self, captchaType, url, siteKey, captchaParams):
|
||||
taskID = None
|
||||
|
||||
if not captchaParams.get('clientKey'):
|
||||
raise CaptchaParameter(
|
||||
"CapMonster: Missing clientKey parameter."
|
||||
)
|
||||
|
||||
self.clientKey = captchaParams.get('clientKey')
|
||||
|
||||
if captchaParams.get('proxy') and not captchaParams.get('no_proxy'):
|
||||
hostParsed = urlparse(captchaParams.get('proxy', {}).get('https'))
|
||||
|
||||
if not hostParsed.scheme:
|
||||
raise CaptchaParameter('Cannot parse proxy correctly, bad scheme')
|
||||
|
||||
if not hostParsed.netloc:
|
||||
raise CaptchaParameter('Cannot parse proxy correctly, bad netloc')
|
||||
|
||||
ports = {
|
||||
'http': 80,
|
||||
'https': 443
|
||||
}
|
||||
|
||||
self.proxy = {
|
||||
'proxyType': hostParsed.scheme,
|
||||
'proxyAddress': hostParsed.hostname,
|
||||
'proxyPort': hostParsed.port if hostParsed.port else ports[self.proxy['proxyType']],
|
||||
'proxyLogin': hostParsed.username,
|
||||
'proxyPassword': hostParsed.password,
|
||||
}
|
||||
else:
|
||||
self.proxy = None
|
||||
|
||||
try:
|
||||
taskID = self.requestSolve(captchaType, url, siteKey)
|
||||
return self.requestJob(taskID)
|
||||
except polling2.TimeoutException:
|
||||
try:
|
||||
if taskID:
|
||||
self.reportJob(taskID)
|
||||
except polling2.TimeoutException:
|
||||
raise CaptchaTimeout(
|
||||
"CapMonster: Captcha solve took to long and also failed "
|
||||
f"reporting the task with task id {taskID}."
|
||||
)
|
||||
|
||||
raise CaptchaTimeout(
|
||||
"CapMonster: Captcha solve took to long to execute "
|
||||
f"task id {taskID}, aborting."
|
||||
)
|
||||
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
captchaSolver()
|
||||
@ -0,0 +1,268 @@
|
||||
from __future__ import absolute_import
|
||||
|
||||
import json
|
||||
import requests
|
||||
try:
|
||||
from urlparse import urlparse
|
||||
except ImportError:
|
||||
from urllib.parse import urlparse
|
||||
|
||||
try:
|
||||
import polling2
|
||||
except ImportError:
|
||||
raise ImportError("Please install the python module 'polling2' via pip")
|
||||
|
||||
from ..exceptions import (
|
||||
CaptchaServiceUnavailable,
|
||||
CaptchaTimeout,
|
||||
CaptchaParameter,
|
||||
CaptchaBadJobID,
|
||||
CaptchaReportError
|
||||
)
|
||||
|
||||
from . import Captcha
|
||||
|
||||
|
||||
class captchaSolver(Captcha):
|
||||
|
||||
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 CaptchaServiceUnavailable(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 CaptchaServiceUnavailable('DeathByCaptcha: Your account is banned.')
|
||||
|
||||
if response.json().get('balanace') == 0:
|
||||
raise CaptchaServiceUnavailable('DeathByCaptcha: insufficient credits.')
|
||||
|
||||
return response
|
||||
|
||||
self.checkErrorStatus(response)
|
||||
|
||||
return None
|
||||
|
||||
response = polling2.poll(
|
||||
lambda: self.session.post(
|
||||
f'{self.host}/user',
|
||||
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 CaptchaBadJobID(
|
||||
"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 = polling2.poll(
|
||||
lambda: self.session.post(
|
||||
f'{self.host}/captcha/{jobID}/report',
|
||||
headers={'Accept': 'application/json'},
|
||||
data={
|
||||
'username': self.username,
|
||||
'password': self.password
|
||||
}
|
||||
),
|
||||
check_success=_checkRequest,
|
||||
step=10,
|
||||
timeout=180
|
||||
)
|
||||
|
||||
if response:
|
||||
return True
|
||||
else:
|
||||
raise CaptchaReportError(
|
||||
"DeathByCaptcha: Error report failed reCaptcha."
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def requestJob(self, jobID):
|
||||
if not jobID:
|
||||
raise CaptchaBadJobID(
|
||||
"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 = polling2.poll(
|
||||
lambda: self.session.get(
|
||||
f'{self.host}/captcha/{jobID}',
|
||||
headers={'Accept': 'application/json'}
|
||||
),
|
||||
check_success=_checkRequest,
|
||||
step=10,
|
||||
timeout=180
|
||||
)
|
||||
|
||||
if response:
|
||||
return response.json().get('text')
|
||||
else:
|
||||
raise CaptchaTimeout(
|
||||
"DeathByCaptcha: Error failed to solve reCaptcha."
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def requestSolve(self, captchaType, url, siteKey):
|
||||
def _checkRequest(response):
|
||||
if response.ok and response.json().get("is_correct") and response.json().get('captcha'):
|
||||
return response
|
||||
|
||||
self.checkErrorStatus(response)
|
||||
|
||||
return None
|
||||
|
||||
data = {
|
||||
'username': self.username,
|
||||
'password': self.password,
|
||||
}
|
||||
|
||||
if captchaType == 'reCaptcha':
|
||||
jPayload = {
|
||||
'googlekey': siteKey,
|
||||
'pageurl': url
|
||||
}
|
||||
|
||||
if self.proxy:
|
||||
jPayload.update({
|
||||
'proxy': self.proxy,
|
||||
'proxytype': self.proxyType
|
||||
})
|
||||
|
||||
data.update({
|
||||
'type': '4',
|
||||
'token_params': json.dumps(jPayload)
|
||||
})
|
||||
else:
|
||||
jPayload = {
|
||||
'sitekey': siteKey,
|
||||
'pageurl': url
|
||||
}
|
||||
|
||||
if self.proxy:
|
||||
jPayload.update({
|
||||
'proxy': self.proxy,
|
||||
'proxytype': self.proxyType
|
||||
})
|
||||
|
||||
data.update({
|
||||
'type': '7',
|
||||
'hcaptcha_params': json.dumps(jPayload)
|
||||
})
|
||||
|
||||
response = polling2.poll(
|
||||
lambda: self.session.post(
|
||||
f'{self.host}/captcha',
|
||||
headers={'Accept': 'application/json'},
|
||||
data=data,
|
||||
allow_redirects=False
|
||||
),
|
||||
check_success=_checkRequest,
|
||||
step=10,
|
||||
timeout=180
|
||||
)
|
||||
|
||||
if response:
|
||||
return response.json().get('captcha')
|
||||
else:
|
||||
raise CaptchaBadJobID(
|
||||
'DeathByCaptcha: Error no job id was returned.'
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def getCaptchaAnswer(self, captchaType, url, siteKey, captchaParams):
|
||||
jobID = None
|
||||
|
||||
for param in ['username', 'password']:
|
||||
if not captchaParams.get(param):
|
||||
raise CaptchaParameter(
|
||||
f"DeathByCaptcha: Missing '{param}' parameter."
|
||||
)
|
||||
setattr(self, param, captchaParams.get(param))
|
||||
|
||||
if captchaParams.get('proxy') and not captchaParams.get('no_proxy'):
|
||||
hostParsed = urlparse(captchaParams.get('proxy', {}).get('https'))
|
||||
|
||||
if not hostParsed.scheme:
|
||||
raise CaptchaParameter('Cannot parse proxy correctly, bad scheme')
|
||||
|
||||
if not hostParsed.netloc:
|
||||
raise CaptchaParameter('Cannot parse proxy correctly, bad netloc')
|
||||
|
||||
self.proxyType = hostParsed.scheme.upper()
|
||||
self.proxy = captchaParams.get('proxy', {}).get('https')
|
||||
else:
|
||||
self.proxy = None
|
||||
|
||||
try:
|
||||
jobID = self.requestSolve(captchaType, url, siteKey)
|
||||
return self.requestJob(jobID)
|
||||
except polling2.TimeoutException:
|
||||
try:
|
||||
if jobID:
|
||||
self.reportJob(jobID)
|
||||
except polling2.TimeoutException:
|
||||
raise CaptchaTimeout(
|
||||
f"DeathByCaptcha: Captcha solve took to long and also failed reporting the job id {jobID}."
|
||||
)
|
||||
|
||||
raise CaptchaTimeout(
|
||||
f"DeathByCaptcha: Captcha solve took to long to execute job id {jobID}, aborting."
|
||||
)
|
||||
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
captchaSolver()
|
||||
@ -0,0 +1,111 @@
|
||||
# -*- 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 CloudflareChallengeError(CloudflareException):
|
||||
"""
|
||||
Raise an error when detected new Cloudflare challenge
|
||||
"""
|
||||
|
||||
|
||||
class CloudflareSolveError(CloudflareException):
|
||||
"""
|
||||
Raise an error when issue with solving Cloudflare challenge
|
||||
"""
|
||||
|
||||
|
||||
class CloudflareCaptchaError(CloudflareException):
|
||||
"""
|
||||
Raise an error for problem extracting Captcha paramters
|
||||
from Cloudflare payload
|
||||
"""
|
||||
|
||||
|
||||
class CloudflareCaptchaProvider(CloudflareException):
|
||||
"""
|
||||
Raise an exception for no Captcha provider loaded for Cloudflare.
|
||||
"""
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
|
||||
class CaptchaException(Exception):
|
||||
"""
|
||||
Base exception class for cloudscraper captcha Providers
|
||||
"""
|
||||
|
||||
|
||||
class CaptchaServiceUnavailable(CaptchaException):
|
||||
"""
|
||||
Raise an exception for external services that cannot be reached
|
||||
"""
|
||||
|
||||
|
||||
class CaptchaAPIError(CaptchaException):
|
||||
"""
|
||||
Raise an error for error from API response.
|
||||
"""
|
||||
|
||||
|
||||
class CaptchaAccountError(CaptchaException):
|
||||
"""
|
||||
Raise an error for captcha provider account problem.
|
||||
"""
|
||||
|
||||
|
||||
class CaptchaTimeout(CaptchaException):
|
||||
"""
|
||||
Raise an exception for captcha provider taking too long.
|
||||
"""
|
||||
|
||||
|
||||
class CaptchaParameter(CaptchaException):
|
||||
"""
|
||||
Raise an exception for bad or missing Parameter.
|
||||
"""
|
||||
|
||||
|
||||
class CaptchaBadJobID(CaptchaException):
|
||||
"""
|
||||
Raise an exception for invalid job id.
|
||||
"""
|
||||
|
||||
|
||||
class CaptchaReportError(CaptchaException):
|
||||
"""
|
||||
Raise an error for captcha provider unable to report bad solve.
|
||||
"""
|
||||
@ -0,0 +1,72 @@
|
||||
import json
|
||||
import platform
|
||||
import requests
|
||||
import ssl
|
||||
import sys
|
||||
import urllib3
|
||||
|
||||
from collections import OrderedDict
|
||||
from . import __version__ as cloudscraper_version
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
|
||||
def getPossibleCiphers():
|
||||
try:
|
||||
context = ssl.create_default_context(ssl.Purpose.SERVER_AUTH)
|
||||
context.set_ciphers('ALL')
|
||||
return sorted([cipher['name'] for cipher in context.get_ciphers()])
|
||||
except AttributeError:
|
||||
return 'get_ciphers() is unsupported'
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
|
||||
def _pythonVersion():
|
||||
interpreter = platform.python_implementation()
|
||||
interpreter_version = platform.python_version()
|
||||
|
||||
if interpreter == 'PyPy':
|
||||
interpreter_version = \
|
||||
f'{sys.pypy_version_info.major}.{sys.pypy_version_info.minor}.{sys.pypy_version_info.micro}'
|
||||
if sys.pypy_version_info.releaselevel != 'final':
|
||||
interpreter_version = f'{interpreter_version}{sys.pypy_version_info.releaselevel}'
|
||||
return {
|
||||
'name': interpreter,
|
||||
'version': interpreter_version
|
||||
}
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
|
||||
def systemInfo():
|
||||
try:
|
||||
platform_info = {
|
||||
'system': platform.system(),
|
||||
'release': platform.release(),
|
||||
}
|
||||
except IOError:
|
||||
platform_info = {
|
||||
'system': 'Unknown',
|
||||
'release': 'Unknown',
|
||||
}
|
||||
|
||||
return OrderedDict([
|
||||
('platform', platform_info),
|
||||
('interpreter', _pythonVersion()),
|
||||
('cloudscraper', cloudscraper_version),
|
||||
('requests', requests.__version__),
|
||||
('urllib3', urllib3.__version__),
|
||||
('OpenSSL', OrderedDict(
|
||||
[
|
||||
('version', ssl.OPENSSL_VERSION),
|
||||
('ciphers', getPossibleCiphers())
|
||||
]
|
||||
))
|
||||
])
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
print(json.dumps(systemInfo(), indent=4))
|
||||
@ -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()
|
||||
@ -0,0 +1,62 @@
|
||||
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+(.*?a\.value\s*=\s*\S+toFixed\(10\);)',
|
||||
body,
|
||||
re.M | re.S
|
||||
).group(1)
|
||||
except Exception:
|
||||
raise ValueError('Unable to identify Cloudflare IUAM Javascript on website. {}'.format(BUG_REPORT))
|
||||
|
||||
jsEnv = '''String.prototype.italics=function(str) {{return "<i>" + this + "</i>";}};
|
||||
var subVars= {{{subVars}}};
|
||||
var document = {{
|
||||
createElement: function () {{
|
||||
return {{ firstChild: {{ href: "https://{domain}/" }} }}
|
||||
}},
|
||||
getElementById: function (str) {{
|
||||
return {{"innerHTML": subVars[str]}};
|
||||
}}
|
||||
}};
|
||||
'''
|
||||
|
||||
try:
|
||||
js = js.replace(
|
||||
r"(setInterval(function(){}, 100),t.match(/https?:\/\//)[0]);",
|
||||
r"t.match(/https?:\/\//)[0];"
|
||||
)
|
||||
|
||||
k = re.search(r" k\s*=\s*'(?P<k>\S+)';", body).group('k')
|
||||
r = re.compile(r'<div id="{}(?P<id>\d+)">\s*(?P<jsfuck>[^<>]*)</div>'.format(k))
|
||||
|
||||
subVars = ''
|
||||
for m in r.finditer(body):
|
||||
subVars = '{}\n\t\t{}{}: {},\n'.format(subVars, k, m.group('id'), m.group('jsfuck'))
|
||||
subVars = subVars[:-2]
|
||||
|
||||
except: # noqa
|
||||
logging.error('Error extracting Cloudflare IUAM Javascript. {}'.format(BUG_REPORT))
|
||||
raise
|
||||
|
||||
return '{}{}'.format(
|
||||
re.sub(
|
||||
r'\s{2,}',
|
||||
' ',
|
||||
jsEnv.format(
|
||||
domain=domain,
|
||||
subVars=subVars
|
||||
),
|
||||
re.MULTILINE | re.DOTALL
|
||||
),
|
||||
js
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
@ -0,0 +1,233 @@
|
||||
from __future__ import absolute_import
|
||||
|
||||
import ast
|
||||
import re
|
||||
import operator as op
|
||||
import pyparsing
|
||||
|
||||
from ..exceptions import CloudflareSolveError
|
||||
from . import JavaScriptInterpreter
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
_OP_MAP = {
|
||||
ast.Add: op.add,
|
||||
ast.Sub: op.sub,
|
||||
ast.Mult: op.mul,
|
||||
ast.Div: op.truediv,
|
||||
ast.Invert: op.neg,
|
||||
}
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
|
||||
class Calc(ast.NodeVisitor):
|
||||
|
||||
def visit_BinOp(self, node):
|
||||
return _OP_MAP[type(node.op)](self.visit(node.left), self.visit(node.right))
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def visit_Num(self, node):
|
||||
return node.n
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def visit_Expr(self, node):
|
||||
return self.visit(node.value)
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
@classmethod
|
||||
def doMath(cls, expression):
|
||||
tree = ast.parse(expression)
|
||||
calc = cls()
|
||||
return calc.visit(tree.body[0])
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
|
||||
class Parentheses(object):
|
||||
|
||||
def fix(self, s):
|
||||
res = []
|
||||
self.visited = set([s])
|
||||
self.dfs(s, self.invalid(s), res)
|
||||
return res
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def dfs(self, s, n, res):
|
||||
if n == 0:
|
||||
res.append(s)
|
||||
return
|
||||
for i in range(len(s)):
|
||||
if s[i] in ['(', ')']:
|
||||
s_new = s[:i] + s[i + 1:]
|
||||
if s_new not in self.visited and self.invalid(s_new) < n:
|
||||
self.visited.add(s_new)
|
||||
self.dfs(s_new, self.invalid(s_new), res)
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def invalid(self, s):
|
||||
plus = minus = 0
|
||||
memo = {"(": 1, ")": -1}
|
||||
for c in s:
|
||||
plus += memo.get(c, 0)
|
||||
minus += 1 if plus < 0 else 0
|
||||
plus = max(0, plus)
|
||||
return plus + minus
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
|
||||
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 flatten(lists):
|
||||
return sum(map(flatten, lists), []) if isinstance(lists, list) else [lists]
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def jsfuckToNumber(jsFuck):
|
||||
# "Clean Up" JSFuck
|
||||
jsFuck = jsFuck.replace('!+[]', '1').replace('!![]', '1').replace('[]', '0')
|
||||
jsFuck = jsFuck.lstrip('+').replace('(+', '(').replace(' ', '')
|
||||
jsFuck = Parentheses().fix(jsFuck)[0]
|
||||
|
||||
# Hackery Parser for Math
|
||||
stack = []
|
||||
bstack = []
|
||||
|
||||
for i in flatten(pyparsing.nestedExpr().parseString(jsFuck).asList()):
|
||||
if i == '+':
|
||||
stack.append(bstack)
|
||||
bstack = []
|
||||
continue
|
||||
bstack.append(i)
|
||||
stack.append(bstack)
|
||||
|
||||
return int(''.join([str(Calc.doMath(''.join(i))) for i in stack]))
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
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
|
||||
|
||||
try:
|
||||
jsfuckChallenge = re.search(
|
||||
r"setTimeout\(function\(\){\s+var.*?f,\s*(?P<variable>\w+).*?:(?P<init>\S+)};"
|
||||
r".*?\('challenge-form'\);.*?;(?P<challenge>.*?a\.value)\s*=\s*\S+\.toFixed\(10\);",
|
||||
body,
|
||||
re.DOTALL | re.MULTILINE
|
||||
).groupdict()
|
||||
except AttributeError:
|
||||
raise CloudflareSolveError('There was an issue extracting "jsfuckChallenge" from the Cloudflare challenge.')
|
||||
|
||||
kJSFUCK = re.search(r'(;|)\s*k.=(?P<kJSFUCK>\S+);', jsfuckChallenge['challenge'], re.S | re.M)
|
||||
if kJSFUCK:
|
||||
try:
|
||||
kJSFUCK = jsfuckToNumber(kJSFUCK.group('kJSFUCK'))
|
||||
except IndexError:
|
||||
raise CloudflareSolveError('There was an issue extracting "kJSFUCK" from the Cloudflare challenge.')
|
||||
|
||||
try:
|
||||
kID = re.search(r"\s*k\s*=\s*'(?P<kID>\S+)';", body).group('kID')
|
||||
except IndexError:
|
||||
raise CloudflareSolveError('There was an issue extracting "kID" from the Cloudflare challenge.')
|
||||
|
||||
try:
|
||||
r = re.compile(r'<div id="{}(?P<id>\d+)">\s*(?P<jsfuck>[^<>]*)</div>'.format(kID))
|
||||
|
||||
kValues = {}
|
||||
for m in r.finditer(body):
|
||||
kValues[int(m.group('id'))] = m.group('jsfuck')
|
||||
|
||||
jsfuckChallenge['k'] = kValues[kJSFUCK]
|
||||
except (AttributeError, IndexError):
|
||||
raise CloudflareSolveError('There was an issue extracting "kValues" from the Cloudflare challenge.')
|
||||
|
||||
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()
|
||||
@ -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()
|
||||
@ -1,38 +1,124 @@
|
||||
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 filterAgents(self, user_agents):
|
||||
filtered = {}
|
||||
|
||||
if self.mobile:
|
||||
if self.platform in user_agents['mobile'] and user_agents['mobile'][self.platform]:
|
||||
filtered.update(user_agents['mobile'][self.platform])
|
||||
|
||||
if self.desktop:
|
||||
if self.platform in user_agents['desktop'] and user_agents['desktop'][self.platform]:
|
||||
filtered.update(user_agents['desktop'][self.platform])
|
||||
|
||||
return filtered
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def tryMatchCustom(self, user_agents):
|
||||
for device_type in user_agents['user_agents']:
|
||||
for platform in user_agents['user_agents'][device_type]:
|
||||
for browser in user_agents['user_agents'][device_type][platform]:
|
||||
if re.search(re.escape(self.custom), ' '.join(user_agents['user_agents'][device_type][platform][browser])):
|
||||
self.headers = user_agents['headers'][browser]
|
||||
self.headers['User-Agent'] = self.custom
|
||||
self.cipherSuite = user_agents['cipherSuite'][browser]
|
||||
return True
|
||||
return False
|
||||
|
||||
# ------------------------------------------------------------------------------- #
|
||||
|
||||
def loadUserAgent(self, *args, **kwargs):
|
||||
browser = kwargs.pop('browser', 'chrome')
|
||||
self.browser = kwargs.pop('browser', None)
|
||||
|
||||
self.platforms = ['linux', 'windows', 'darwin', 'android', 'ios']
|
||||
self.browsers = ['chrome', 'firefox']
|
||||
|
||||
if isinstance(self.browser, dict):
|
||||
self.custom = self.browser.get('custom', None)
|
||||
self.platform = self.browser.get('platform', 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.platform = kwargs.pop('platform', None)
|
||||
self.desktop = kwargs.pop('desktop', True)
|
||||
self.mobile = kwargs.pop('mobile', True)
|
||||
|
||||
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.")
|
||||
|
||||
with open(os.path.join(os.path.dirname(__file__), 'browsers.json'), 'r') as fp:
|
||||
user_agents = json.load(
|
||||
fp,
|
||||
object_pairs_hook=OrderedDict
|
||||
)
|
||||
|
||||
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 self.browser not in self.browsers:
|
||||
sys.tracebacklimit = 0
|
||||
raise RuntimeError(f'Sorry "{self.browser}" browser is not valid, valid browsers are [{", ".join(self.browsers)}].')
|
||||
|
||||
if not self.platform:
|
||||
self.platform = random.SystemRandom().choice(self.platforms)
|
||||
|
||||
if self.platform not in self.platforms:
|
||||
sys.tracebacklimit = 0
|
||||
raise RuntimeError(f'Sorry the platform "{self.platform}" is not valid, valid platforms are [{", ".join(self.platforms)}]')
|
||||
|
||||
filteredAgents = self.filterAgents(user_agents['user_agents'])
|
||||
|
||||
with open(os.path.join(os.path.dirname(__file__), 'browsers.json'), 'r') as file:
|
||||
user_agents = json.load(file, object_pairs_hook=OrderedDict)
|
||||
if not self.browser:
|
||||
# has to be at least one in there...
|
||||
while not filteredAgents.get(self.browser):
|
||||
self.browser = random.SystemRandom().choice(list(filteredAgents.keys()))
|
||||
|
||||
if not user_agents.get(browser):
|
||||
logging.error('Sorry "{}" browser User-Agent was not found.'.format(browser))
|
||||
raise
|
||||
if not filteredAgents[self.browser]:
|
||||
sys.tracebacklimit = 0
|
||||
raise RuntimeError(f'Sorry "{self.browser}" browser was not found with a platform of "{self.platform}".')
|
||||
|
||||
user_agent = random.choice(user_agents.get(browser))
|
||||
self.cipherSuite = user_agents['cipherSuite'][self.browser]
|
||||
self.headers = user_agents['headers'][self.browser]
|
||||
|
||||
self.headers = user_agent.get('headers')
|
||||
self.headers['User-Agent'] = random.choice(user_agent.get('User-Agent'))
|
||||
self.headers['User-Agent'] = random.SystemRandom().choice(filteredAgents[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 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()
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Loading…
Reference in new issue