break when the get_csrf is blocked

queue_message/appointmentrequestsender.py

@@ -127,9 +127,15 @@ class AppointmentRequestSender(threading.Thread):
                 for con in self.contact_list:
                     self.logger.info(con.mail)
                     if self.valid_csrf is None:
-                        self.valid_csrf = captchaResultGetter.get_csrf(
+                        csrf_result = captchaResultGetter.get_csrf(
                             proxy_to_use=_proxy_to_use, js_data=js_data,
                             cookie=_received_cookies)
+                        if isinstance(csrf_result, str):
+                            self.valid_csrf = csrf_result
+                        else:
+                            self.logger.info("csrf is {}".format(csrf_result))
+                            if csrf_result == RequestResult.BLOCKED:
+                                break
                     _new_cookies = captchaResultGetter.get_valid_ch_cookie(sender.proxy_to_use, js_data,
                                                                            old_valid_cookie=_received_cookies)
                     if _new_cookies is not None:
@@ -181,7 +187,7 @@ class AppointmentRequestSender(threading.Thread):
                     else:
                         can_continue = RequestResult.COOKIES_ERROR
                     if can_continue == RequestResult.BLOCKED:
-                        self.logger.info("cannot continue, valid_csrf is " + str(self.valid_csrf))
+                        self.logger.info("BLOCKED, valid_csrf is " + str(self.valid_csrf))
                         break
                     elif can_continue == RequestResult.PROXY_ERROR:
                         self.logger.info("PROXY_ERROR, will not reset valid_csrf")

workers/captcha_result_getter.py

@@ -6,6 +6,7 @@ import requests
 
 from models.jsdata_le_pojo import JsDataLeTypePojo
 from models.jsdata_pojo import JsDataPojo
+from models.result_pojo import RequestResult
 from utils.get_only_datadome_cookies import get_datadome_cookies, get_app_cookies, get_lang_cookies, \
     retain_only_dataome_cookies
 from workers.proxies_constants import PROXY_LIST_FR
@@ -24,7 +25,7 @@ class CaptchaResultGetter:
         self.cookie_str = 'datadome=5Nq~NEP_qQSHC0g_lZNnZmEv36J8gVV~rpZ329xmCkTq2~H3meIoXr4h_b988qB2XW5Te7iEGsvq8BzA5KeFupyrZFh4kgrDyl8hT2UymSByKHzAcDaNIBPDsRu2g_KG; Max-Age=31536000; Domain=.hermes.com; Path=/; Secure; SameSite=None'
         pass
 
-    def get_csrf(self, proxy_to_use, js_data: JsDataPojo, cookie: str = None) -> Union[str, None]:
+    def get_csrf(self, proxy_to_use, js_data: JsDataPojo, cookie: str = None) -> Union[str, RequestResult]:
         if cookie is not None:
             headers = {'Content-Type': 'application/x-www-form-urlencoded',
                        'User-Agent': js_data.ua,
@@ -49,13 +50,16 @@ class CaptchaResultGetter:
                                     timeout=15)
             print(response.status_code)
             if response.status_code == 200:
-                # print(response.text)
-                print(response.url)
+                print(response.text)
                 return self.extract_csrf_from_html(response.text)
+            elif response.status_code == 403:
+                return RequestResult.BLOCKED
             else:
-                return None
+                print(response.text)
+                return RequestResult.UNKNOWN
         except Exception as error:
             print(error)
+            return RequestResult.PROXY_ERROR
 
     def extract_csrf_from_html(self, html: str) -> Union[str, None]:
         result = re.findall(r'_csrf" value="[A-Za-z0-9-_]+', html)