1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407
|
# ------------------------------------------------------------------------------- #
import logging
import requests
import sys
import ssl
from requests.adapters import HTTPAdapter
from requests.sessions import Session
from requests_toolbelt.utils import dump
# ------------------------------------------------------------------------------- #
try:
import brotli
except ImportError:
pass
try:
import copyreg
except ImportError:
import copy_reg as copyreg
try:
from urlparse import urlparse
except ImportError:
from urllib.parse import urlparse
# ------------------------------------------------------------------------------- #
from .exceptions import (
CloudflareLoopProtection,
CloudflareIUAMError
)
from .cloudflare import Cloudflare
from .user_agent import User_Agent
# ------------------------------------------------------------------------------- #
__version__ = '1.2.71'
# ------------------------------------------------------------------------------- #
class CipherSuiteAdapter(HTTPAdapter):
__attrs__ = [
'ssl_context',
'max_retries',
'config',
'_pool_connections',
'_pool_maxsize',
'_pool_block',
'source_address'
]
def __init__(self, *args, **kwargs):
self.ssl_context = kwargs.pop('ssl_context', None)
self.cipherSuite = kwargs.pop('cipherSuite', None)
self.source_address = kwargs.pop('source_address', None)
self.server_hostname = kwargs.pop('server_hostname', None)
self.ecdhCurve = kwargs.pop('ecdhCurve', 'prime256v1')
if self.source_address:
if isinstance(self.source_address, str):
self.source_address = (self.source_address, 0)
if not isinstance(self.source_address, tuple):
raise TypeError(
"source_address must be IP address string or (ip, port) tuple"
)
if not self.ssl_context:
self.ssl_context = ssl.create_default_context(ssl.Purpose.SERVER_AUTH)
self.ssl_context.orig_wrap_socket = self.ssl_context.wrap_socket
self.ssl_context.wrap_socket = self.wrap_socket
if self.server_hostname:
self.ssl_context.server_hostname = self.server_hostname
self.ssl_context.set_ciphers(self.cipherSuite)
self.ssl_context.set_ecdh_curve(self.ecdhCurve)
self.ssl_context.minimum_version = ssl.TLSVersion.TLSv1_2
self.ssl_context.maximum_version = ssl.TLSVersion.TLSv1_3
super(CipherSuiteAdapter, self).__init__(**kwargs)
# ------------------------------------------------------------------------------- #
def wrap_socket(self, *args, **kwargs):
if hasattr(self.ssl_context, 'server_hostname') and self.ssl_context.server_hostname:
kwargs['server_hostname'] = self.ssl_context.server_hostname
self.ssl_context.check_hostname = False
else:
self.ssl_context.check_hostname = True
return self.ssl_context.orig_wrap_socket(*args, **kwargs)
# ------------------------------------------------------------------------------- #
def init_poolmanager(self, *args, **kwargs):
kwargs['ssl_context'] = self.ssl_context
kwargs['source_address'] = self.source_address
return super(CipherSuiteAdapter, self).init_poolmanager(*args, **kwargs)
# ------------------------------------------------------------------------------- #
def proxy_manager_for(self, *args, **kwargs):
kwargs['ssl_context'] = self.ssl_context
kwargs['source_address'] = self.source_address
return super(CipherSuiteAdapter, self).proxy_manager_for(*args, **kwargs)
# ------------------------------------------------------------------------------- #
class CloudScraper(Session):
def __init__(self, *args, **kwargs):
self.debug = kwargs.pop('debug', False)
self.disableCloudflareV1 = kwargs.pop('disableCloudflareV1', False)
self.delay = kwargs.pop('delay', None)
self.captcha = kwargs.pop('captcha', {})
self.doubleDown = kwargs.pop('doubleDown', True)
self.interpreter = kwargs.pop('interpreter', 'native')
self.requestPreHook = kwargs.pop('requestPreHook', None)
self.requestPostHook = kwargs.pop('requestPostHook', None)
self.cipherSuite = kwargs.pop('cipherSuite', None)
self.ecdhCurve = kwargs.pop('ecdhCurve', 'prime256v1')
self.source_address = kwargs.pop('source_address', None)
self.server_hostname = kwargs.pop('server_hostname', None)
self.ssl_context = kwargs.pop('ssl_context', None)
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 = self.user_agent.headers
if not self.cipherSuite:
self.cipherSuite = self.user_agent.cipherSuite
if isinstance(self.cipherSuite, list):
self.cipherSuite = ':'.join(self.cipherSuite)
self.mount(
'https://',
CipherSuiteAdapter(
cipherSuite=self.cipherSuite,
ecdhCurve=self.ecdhCurve,
server_hostname=self.server_hostname,
source_address=self.source_address,
ssl_context=self.ssl_context
)
)
# 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__
# ------------------------------------------------------------------------------- #
# Allow replacing actual web request call via subclassing
# ------------------------------------------------------------------------------- #
def perform_request(self, method, url, *args, **kwargs):
return super(CloudScraper, self).request(method, url, *args, **kwargs)
# ------------------------------------------------------------------------------- #
# 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', errors='backslashreplace'))
except ValueError as e:
print(f"Debug Error: {getattr(e, 'message', e)}")
# ------------------------------------------------------------------------------- #
# Decode Brotli on older versions of urllib3 manually
# ------------------------------------------------------------------------------- #
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(
f'You\'re running urllib3 {requests.packages.urllib3.__version__}, Brotli content detected, '
'Which requires manual decompression, '
'But option allow_brotli is set to False, '
'We will not continue to decompress.'
)
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')
# ------------------------------------------------------------------------------- #
# Pre-Hook the request via user defined function.
# ------------------------------------------------------------------------------- #
if self.requestPreHook:
(method, url, args, kwargs) = self.requestPreHook(
self,
method,
url,
*args,
**kwargs
)
# ------------------------------------------------------------------------------- #
# Make the request via requests.
# ------------------------------------------------------------------------------- #
response = self.decodeBrotli(
self.perform_request(method, url, *args, **kwargs)
)
# ------------------------------------------------------------------------------- #
# Debug the request via the Response object.
# ------------------------------------------------------------------------------- #
if self.debug:
self.debugRequest(response)
# ------------------------------------------------------------------------------- #
# Post-Hook the request aka Post-Hook the response via user defined function.
# ------------------------------------------------------------------------------- #
if self.requestPostHook:
newResponse = self.requestPostHook(self, response)
if response != newResponse: # Give me walrus in 3.7!!!
response = newResponse
if self.debug:
print('==== requestPostHook Debug ====')
self.debugRequest(response)
# ------------------------------------------------------------------------------- #
if not self.disableCloudflareV1:
cloudflareV1 = Cloudflare(self)
# ------------------------------------------------------------------------------- #
# Check if Cloudflare v1 anti-bot is on
# ------------------------------------------------------------------------------- #
if cloudflareV1.is_Challenge_Request(response):
# ------------------------------------------------------------------------------- #
# Try to solve the challenge and send it back
# ------------------------------------------------------------------------------- #
if self._solveDepthCnt >= self.solveDepth:
_ = self._solveDepthCnt
self.simpleException(
CloudflareLoopProtection,
f"!!Loop Protection!! We have tried to solve {_} time(s) in a row."
)
self._solveDepthCnt += 1
response = cloudflareV1.Challenge_Response(response, **kwargs)
else:
if not response.is_redirect and response.status_code not in [429, 503]:
self._solveDepthCnt = 0
return response
# ------------------------------------------------------------------------------- #
@classmethod
def create_scraper(cls, sess=None, **kwargs):
"""
Convenience function for creating a ready-to-go CloudScraper object.
"""
scraper = cls(**kwargs)
if sess:
for attr in ['auth', 'cert', 'cookies', 'headers', 'hooks', 'params', 'proxies', 'data']:
val = getattr(sess, attr, None)
if val is not None:
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(
**{
field: kwargs.pop(field, None) for field in [
'allow_brotli',
'browser',
'debug',
'delay',
'doubleDown',
'captcha',
'interpreter',
'source_address',
'requestPreHook',
'requestPostHook'
] if field in kwargs
}
)
try:
resp = scraper.get(url, **kwargs)
resp.raise_for_status()
except Exception:
logging.error(f'"{url}" returned an error. Could not collect tokens.')
raise
domain = urlparse(resp.url).netloc
# noinspection PyUnusedLocal
cookie_domain = None
for d in scraper.cookies.list_domains():
if d.startswith('.') and d in (f'.{domain}'):
cookie_domain = d
break
else:
cls.simpleException(
cls,
CloudflareIUAMError,
"Unable to find Cloudflare cookies. Does the site actually "
"have Cloudflare IUAM (I'm Under Attack Mode) enabled?"
)
return (
{
'cf_clearance': scraper.cookies.get('cf_clearance', '', domain=cookie_domain)
},
scraper.headers['User-Agent']
)
# ------------------------------------------------------------------------------- #
@classmethod
def get_cookie_string(cls, url, **kwargs):
"""
Convenience function for building a Cookie HTTP header value.
"""
tokens, user_agent = cls.get_tokens(url, **kwargs)
return '; '.join('='.join(pair) for pair in tokens.items()), user_agent
# ------------------------------------------------------------------------------- #
if ssl.OPENSSL_VERSION_INFO < (1, 1, 1):
print(
f"DEPRECATION: The OpenSSL being used by this python install ({ssl.OPENSSL_VERSION}) 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 Captcha or cloudflare 1020 blocks."
)
# ------------------------------------------------------------------------------- #
create_scraper = CloudScraper.create_scraper
session = CloudScraper.create_scraper
get_tokens = CloudScraper.get_tokens
get_cookie_string = CloudScraper.get_cookie_string
|