fix for migration cached data

db/mongo_manager.py

@@ -1,6 +1,7 @@
 import datetime
 import logging
 import time
+import os
 
 from pymongo import MongoClient
 
@@ -11,7 +12,7 @@ from models.contact_pojo import ContactPojo
 from models.mail_pojo import MailAddress
 from models.regisered_user_pojo import RegisteredUserPojo
 
-MONGO_DB_URL = "mongodb://mongo.lpaconsulting.fr/?timeoutMS=100000"
+MONGO_DB_URL = "mongodb://mongo2.lpaconsulting.fr/?timeoutMS=100000"
 CAPTCHA_ERROR_COLLECTION_PREFIX = "CAPTCHA_ERROR_"
 BLACK_LIST = "BLACK_LIST"
 ACCEPTED_APPOINTMENT_LIST = "ACCEPTED_APPOINTMENT_LIST"
@@ -25,7 +26,22 @@ CONTACT_LIST_SERIAL_MAP = "CONTACT_LIST_SERIAL_MAP"
 
 class MongoDbManager:
     def __init__(self):
-        client = MongoClient(MONGO_DB_URL, username='appointment', password='Rdv@2022', authSource='appointment')
+        # Get username and password from environment variables
+        mongo_username = os.getenv("MONGO_USERNAME")
+        mongo_password = os.getenv("MONGO_PASSWORD")
+
+        # Validate that environment variables exist
+        if not mongo_username or not mongo_password:
+            raise ValueError(
+                "MONGO_USERNAME and MONGO_PASSWORD environment variables must be set"
+            )
+
+        client = MongoClient(
+            MONGO_DB_URL,
+            username=mongo_username,
+            password=mongo_password,
+            authSource="appointment",
+        )
         self.db = client.appointment
         self.logger = logging.getLogger("mongoDb")
 
@@ -36,8 +52,13 @@ class MongoDbManager:
     def insert_reserve_result(self, collection_name, reserve: ReserveResultPojo):
         try:
             collection_to_use = self.db[collection_name]
-            collection_to_use.replace_one(filter={'_id': reserve.id, }, replacement=reserve.to_firestore_dict(),
+            collection_to_use.replace_one(
-                                          upsert=True)
+                filter={
+                    "_id": reserve.id,
+                },
+                replacement=reserve.to_firestore_dict(),
+                upsert=True,
+            )
         except Exception as Error:
             self.logger.info(Error)
 
@@ -83,7 +104,14 @@ class MongoDbManager:
             result_list.append(ContactPojo.from_firestore_dict(document))
         return result_list
 
-    def save_links_to_validate(self, link: str, mail_address: str, model: str, _all_contact_list: list):
+    def save_links_to_validate(
+        self,
+        link: str,
+        mail_address: str,
+        model: str,
+        _all_contact_list: list,
+        _used_ip: str = "",
+    ):
         collection_to_use = self.db[LINKS_TO_VALIDATE]
         updated_at = time.strftime("%H:%M:%S", time.localtime())
         _ip_country = "FR"
@@ -94,30 +122,42 @@ class MongoDbManager:
                 _ip_country = _contact.ip_country
 
         if len(mail_address) > 0:
-            collection_to_use.replace_one(filter={'_id': mail_address, }, replacement={
+            collection_to_use.replace_one(
-                u'url': link,
+                filter={
-                u'email': mail_address,
+                    "_id": mail_address,
-                u'serial': serial,
-                u'model': model,
-                u'ip_country': _ip_country,
-                "updated_at": updated_at
                 },
-                                          upsert=True)
+                replacement={
+                    "url": link,
+                    "email": mail_address,
+                    "serial": serial,
+                    "model": model,
+                    "ip_country": _ip_country,
+                    "_used_ip": _used_ip,
+                    "updated_at": updated_at,
+                },
+                upsert=True,
+            )
         else:
-            collection_to_use.replace_one(filter={'_id': link, }, replacement={
+            collection_to_use.replace_one(
-                u'url': link,
+                filter={
-                u'serial': serial,
+                    "_id": link,
-                u'model': model,
-                u'ip_country': _ip_country,
-                "updated_at": updated_at
                 },
-                                          upsert=True)
+                replacement={
+                    "url": link,
+                    "serial": serial,
+                    "model": model,
+                    "ip_country": _ip_country,
+                    "_used_ip": _used_ip,
+                    "updated_at": updated_at,
+                },
+                upsert=True,
+            )
 
     def get_code_for_email(self, email: str):
         collection_name = DESTINATION_EMAIL_LIST
         try:
             collection_to_use = self.db[collection_name]
-            mailDocument = collection_to_use.find_one(filter={'_id': email})
+            mailDocument = collection_to_use.find_one(filter={"_id": email})
             if mailDocument is not None:
                 return MailAddress.from_firestore_dict(mailDocument).password
             else:
@@ -131,7 +171,9 @@ class MongoDbManager:
         _cursor = self.db[_collection_name]
         registered_user_list = []
         for document in _cursor.find():
-            registered_user_list.append(RegisteredUserPojo.from_firestore_dict(document))
+            registered_user_list.append(
+                RegisteredUserPojo.from_firestore_dict(document)
+            )
         return registered_user_list
 
     def get_destination_emails(self) -> list:
@@ -164,8 +206,20 @@ class MongoDbManager:
             self.logger.info(error)
         return link_list
 
-    def link_validated_for_result(self, link: str, linkPojo: LinkPojo, state=True, is_duplicated=False,
+    def link_validated_for_result(
-                                  is_invalid=False, segement_position=1, ua=""):
+        self,
+        link: str,
+        linkPojo: LinkPojo,
+        state=True,
+        is_duplicated=False,
+        is_invalid=False,
+        segement_position=1,
+        ua="",
+        model="",
+        timestamp_in_s: list = None,
+    ):
+        if timestamp_in_s is None:
+            timestamp_in_s = []
         print("link_validated_for_result() called with url = " + link)
         if is_duplicated:
             _id = link.split("/")[-2]
@@ -176,7 +230,10 @@ class MongoDbManager:
         print("link_validated_for_result() called with id = " + _id)
 
         collection_name = str(datetime.date.today())
-        print("link_validated_for_result() called with collection_name = " + collection_name)
+        print(
+            "link_validated_for_result() called with collection_name = "
+            + collection_name
+        )
 
         collection = self.db[collection_name]
         validated_at = time.strftime("%H:%M:%S", time.localtime())
@@ -185,17 +242,27 @@ class MongoDbManager:
             validated_by = "Invalid"
         if is_duplicated:
             validated_by = "Double"
-        collection.find_one_and_update({'_id': _id}, {
+        collection.find_one_and_update(
-            "$set": {"url_validated": state, "validated_at": validated_at, "id": _id, "email": linkPojo.email,
+            {"_id": _id},
+            {
+                "$set": {
+                    "url_validated": state,
+                    "validated_at": validated_at,
+                    "id": _id,
+                    "email": linkPojo.email,
                     "url": link,
-                     "source_from": linkPojo.model,
+                    "validated_by_model": model,
                     "serial": linkPojo.serial,
                     "validated_by_ua": ua,
-                     "validated_by": validated_by}},
+                    "timestamp_in_s": "-".join(str(x) for x in timestamp_in_s),
-                                       upsert=True)
+                    "validated_by": validated_by,
+                }
+            },
+            upsert=True,
+        )
         #     remove the link from db
         collection_to_use = self.db[LINKS_TO_VALIDATE]
-        collection_to_use.delete_one({'_id': linkPojo.email})
+        collection_to_use.delete_one({"_id": linkPojo.email})
 
 
 MONGO_STORE_MANAGER = MongoDbManager()

docs/mail_issue/jsdata_ch.json

@@ -1 +0,0 @@
-jsData={"ttst":26.700000002980232,"ifov":false,"hc":8,"br_oh":803,"br_ow":407,"ua":"Mozilla/5.0 (Linux; Android 10; K) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Mobile Safari/537.36","wbd":false,"tagpu":8.178524146392085,"wdif":false,"wdifrm":false,"npmtm":false,"br_h":803,"br_w":407,"isf":true,"nddc":1,"rs_h":904,"rs_w":407,"rs_cd":24,"phe":false,"nm":false,"jsf":false,"lg":"en-US","pr":3,"ars_h":904,"ars_w":407,"tz":-120,"str_ss":true,"str_ls":true,"str_idb":true,"str_odb":false,"plgod":false,"plg":0,"plgne":"NA","plgre":"NA","plgof":"NA","plggt":"NA","pltod":false,"hcovdr":false,"hcovdr2":false,"plovdr":false,"plovdr2":false,"ftsovdr":false,"ftsovdr2":false,"lb":false,"eva":33,"lo":false,"ts_mtp":5,"ts_tec":true,"ts_tsa":true,"vnd":"Google Inc.","bid":"NA","mmt":"empty","plu":"empty","hdn":false,"awe":false,"geb":false,"dat":false,"med":"defined","aco":"probably","acots":false,"acmp":"probably","acmpts":true,"acw":"probably","acwts":false,"acma":"maybe","acmats":false,"acaa":"probably","acaats":true,"ac3":"","ac3ts":false,"acf":"probably","acfts":false,"acmp4":"maybe","acmp4ts":false,"acmp3":"probably","acmp3ts":false,"acwm":"maybe","acwmts":false,"ocpt":false,"vco":"","vcots":false,"vch":"probably","vchts":true,"vcw":"probably","vcwts":true,"vc3":"maybe","vc3ts":false,"vcmp":"","vcmpts":false,"vcq":"","vcqts":false,"vc1":"probably","vc1ts":true,"dvm":8,"sqt":false,"so":"portrait-primary","wdw":true,"cokys":"bG9hZFRpbWVzY3NpL=","ecpc":false,"lgs":true,"lgsod":false,"psn":true,"edp":false,"addt":true,"wsdc":true,"ccsr":true,"nuad":true,"bcda":true,"idn":true,"capi":false,"svde":false,"vpbq":true,"ucdv":false,"spwn":false,"emt":false,"bfr":false,"dbov":false,"cfpfe":"ZnVuY3Rpb24oKXt2YXIgdD1kb2N1bWVudFsnXHg3MVx4NzVceDY1XHg3Mlx4NzlceDUzXHg2NVx4NmNceDY1XHg2M1x4NzRceDZmXHg3MiddKCdceDYyXHg3Mlx4NmZceDc3XHg3M1x4NjVceDcyXHg2Nlx4NmNceDZmXHg3N1x4MmRceDYzXHg2Zlx4NmVceDc0XHg2","stcfp":"Z2l0YWwuaGVybWVzL3RhZ3MuanM6Mjo4MjA4NykKICAgIGF0IDxjb21wdXRlZD4gW2FzIGRkX2FjXSAoaHR0cHM6Ly9kLmRpZ2l0YWwuaGVybWVzL3RhZ3MuanM6MjoxMDE4MjgpCiAgICBhdCBodHRwczovL2QuZGlnaXRhbC5oZXJtZXMvdGFncy5qczoyOjU2OTA5","ckwa":true,"glvd":"ARM","glrd":"Mali-G610 MC6","wwl":false,"jset":1727368033}&eventCounters=[]&jsType=ch&cid=_HVXtG_qYKC_7qVGzucgKRERQZKdu0OX2QWSHlhBY2mKRFTznVsiPH1avKpVyWC2xPjcEU6HpZUeVmohtzPmY8uyqnYVsxHP_HORmhr0xm3Z73h6A2j95cLo67lwH0Pj&ddk=789361B674144528D0B7EE76B35826&Referer=https%3A%2F%2Frendezvousparis.hermes.com%2Fclient%2Fregister%2F6GJ97H&request=%2Fclient%2Fregister%2F6GJ97H&responsePage=origin&ddv=4.35.1

excel_reader.py

@@ -12,7 +12,7 @@ chinnese_number_prefix = ['13', '15', '18']
 
 def read_contacts(file_name) -> list:
     print("read file " + file_name)
-    contact_list_in_json = pandas.read_excel(file_name).to_json(orient='records')
+    contact_list_in_json = pandas.read_excel(file_name, dtype={'passport': str}).to_json(orient='records')
     contact_dict_list = json.loads(contact_list_in_json)
     contact_list = []
     for contact_dict in contact_dict_list:

link_validator_executor.py

@@ -3,10 +3,14 @@ import time
 from workers.link_validator_with_provided_list import validate_all_links
 
 
-if __name__ == '__main__':
+def start_link_validation():
     # generate test data
     while True:
         print("call validate_all_links()")
         validate_all_links([])
         print("wait for 30 seconds")
         time.sleep(10)
+
+
+if __name__ == '__main__':
+    start_link_validation()

mail/imap_proxy_reader.py

@@ -0,0 +1,539 @@
+"""
+imap_proxy_reader.py
+====================
+Lire des emails via IMAPClient en passant par un proxy SOCKS5/SOCKS4/HTTP.
+
+Fonctionnement :
+  - ProxyIMAP4_TLS  : sous-classe de imaplib.IMAP4 qui ouvre la socket
+                      à travers un proxy SOCKS via PySocks.
+  - ProxyIMAPClient : sous-classe de IMAPClient qui injecte ProxyIMAP4_TLS
+                      au lieu de la connexion directe habituelle.
+
+Dépendances :
+  pip install imapclient PySocks
+"""
+
+import datetime
+import email
+import imaplib
+import io
+import logging
+import os
+import re
+import ssl
+import socket
+from dataclasses import dataclass, field
+from email.message import Message
+from typing import List, Optional, Tuple
+
+import socks
+from dotenv import load_dotenv
+from imapclient import IMAPClient
+
+load_dotenv()
+
+# ──────────────────────────────────────────────────────────────
+# Constantes
+# ──────────────────────────────────────────────────────────────
+
+VALIDATION_URL_SUBJECT_FR = "Validation de votre demande de rendez-vous"
+VALIDATION_URL_SUBJECT_EN = "Please confirm your appointment request"
+VALIDATION_URL_REGEX = (
+    r"https:\/\/rendezvousparis\.hermes\.com"
+    r"\/client\/register\/[A-Z0-9]+\/validate\.code=[A-Z0-9]+"
+)
+
+DATE_FORMAT = "%d-%b-%Y"
+
+# Correspondance domaine → serveur IMAP (identique à mail_constants.py)
+IMAP_SERVER_MAP: List[Tuple[str, str]] = [
+    ("163.com",           "imap.163.com"),
+    ("yahoo.com",         "imap.mail.yahoo.com"),
+    ("firemail.de",       "imap.firemail.de"),
+    ("gmail.com",         "imap.gmail.com"),
+    ("sina.com",          "imap.sina.com"),
+    ("hotmail.com",       "outlook.office365.com"),
+    ("outlook.com",       "outlook.office365.com"),
+    ("rambler.ru",        "imap.rambler.ru"),
+    ("btvm.ne.jp",        "imap.btvm.ne.jp"),
+    ("mars.dti.ne.jp",    "imap.cm.dream.jp"),
+    ("aurora.dti.ne.jp",  "imap.cm.dream.jp"),
+    ("naver.com",         "imap.naver.com"),
+    ("onet.pl",           "imap.poczta.onet.pl"),
+    ("gazeta.pl",         "imap.gazeta.pl"),
+    ("tim.it",            "imap.tim.it"),
+    ("alice.it",          "in.alice.it"),
+    ("gmx.com",           "imap.gmx.com"),
+    ("gmx.fr",            "imap.gmx.com"),
+    ("gmx.us",            "imap.gmx.com"),
+    ("gmx.ch",            "imap.gmx.com"),
+    ("gmx.pt",            "imap.gmx.com"),
+    ("gmx.sg",            "imap.gmx.com"),
+    ("gmx.net",           "imap.gmx.net"),
+    ("gmx.de",            "imap.gmx.net"),
+    ("gmx.at",            "imap.gmx.at"),
+    ("web.de",            "imap.web.de"),
+    ("inbox.lv",          "mail.inbox.lv"),
+    ("pissmail.com",      "mail.pissmail.com"),
+    ("incel.email",       "mail.pissmail.com"),
+    ("shitposting.expert","mail.pissmail.com"),
+    ("hatesje.ws",        "mail.pissmail.com"),
+    ("child.pizza",       "mail.pissmail.com"),
+    ("genocide.fun",      "mail.pissmail.com"),
+    ("dmc.chat",          "mail.pissmail.com"),
+    ("aol.com",           "imap.aol.com"),   # fallback AOL
+]
+
+PROXY_TYPE_MAP = {
+    "SOCKS5": socks.SOCKS5,
+    "SOCKS4": socks.SOCKS4,
+    "HTTP":   socks.HTTP,
+}
+
+logger = logging.getLogger(__name__)
+
+
+# ──────────────────────────────────────────────────────────────
+# Modèles de données
+# ──────────────────────────────────────────────────────────────
+
+@dataclass
+class ProxyConfig:
+    """Configuration du proxy."""
+    host: str
+    port: int
+    proxy_type: str = "SOCKS5"   # "SOCKS5" | "SOCKS4" | "HTTP"
+    username: Optional[str] = None
+    password: Optional[str] = None
+
+    @property
+    def socks_type(self) -> int:
+        t = self.proxy_type.upper()
+        if t not in PROXY_TYPE_MAP:
+            raise ValueError(f"proxy_type invalide : {self.proxy_type!r}. "
+                             f"Valeurs autorisées : {list(PROXY_TYPE_MAP)}")
+        return PROXY_TYPE_MAP[t]
+
+    def __repr__(self) -> str:
+        auth = f"{self.username}:***@" if self.username else ""
+        return f"{self.proxy_type}://{auth}{self.host}:{self.port}"
+
+
+@dataclass
+class MailAccount:
+    """Compte email à lire."""
+    login: str
+    password: str
+
+
+@dataclass
+class MailResult:
+    """Résultat d'une lecture d'email."""
+    account: str
+    subject: str
+    from_address: str
+    to_address: str
+    body: str
+    validation_urls: List[str] = field(default_factory=list)
+
+
+# ──────────────────────────────────────────────────────────────
+# Connexion IMAP via proxy (bas niveau)
+# ──────────────────────────────────────────────────────────────
+
+class ProxyIMAP4_TLS(imaplib.IMAP4):
+    """
+    Variante TLS de imaplib.IMAP4 qui route la connexion
+    à travers un proxy SOCKS5/SOCKS4/HTTP grâce à PySocks.
+    """
+
+    def __init__(
+        self,
+        host: str,
+        port: int,
+        ssl_context: Optional[ssl.SSLContext],
+        proxy: ProxyConfig,
+        timeout: Optional[float] = None,
+    ):
+        self._ssl_context = ssl_context
+        self._proxy = proxy
+        self._timeout = timeout
+        # imaplib.IMAP4.__init__ appelle self.open()
+        imaplib.IMAP4.__init__(self, host, port)
+        self.file: io.BufferedReader
+
+    def open(self, host: str = "", port: int = 993, timeout: Optional[float] = None) -> None:
+        self.host = host
+        self.port = port
+        effective_timeout = timeout if timeout is not None else self._timeout
+
+        # ── Créer la socket SOCKS ────────────────────────────
+        sock = socks.socksocket(socket.AF_INET, socket.SOCK_STREAM)
+        sock.set_proxy(
+            proxy_type=self._proxy.socks_type,
+            addr=self._proxy.host,
+            port=self._proxy.port,
+            username=self._proxy.username,
+            password=self._proxy.password,
+        )
+        if effective_timeout:
+            sock.settimeout(effective_timeout)
+        sock.connect((host, port))
+
+        # ── Envelopper avec SSL/TLS ──────────────────────────
+        ctx = self._ssl_context or ssl.create_default_context()
+        self.sock = ctx.wrap_socket(sock, server_hostname=host)
+        self.file = self.sock.makefile("rb")
+
+    # ── Méthodes requises par imaplib.IMAP4 ─────────────────
+    def read(self, size: int) -> bytes:
+        return self.file.read(size)  # type: ignore[return-value]
+
+    def readline(self) -> bytes:
+        return self.file.readline()  # type: ignore[return-value]
+
+    def send(self, data) -> None:
+        self.sock.sendall(data)
+
+    def shutdown(self) -> None:
+        imaplib.IMAP4.shutdown(self)
+
+
+# ──────────────────────────────────────────────────────────────
+# IMAPClient avec proxy
+# ──────────────────────────────────────────────────────────────
+
+class ProxyIMAPClient(IMAPClient):
+    """
+    Sous-classe d'IMAPClient qui utilise un proxy SOCKS/HTTP.
+
+    Usage :
+        proxy = ProxyConfig(host="127.0.0.1", port=1080, proxy_type="SOCKS5")
+        client = ProxyIMAPClient("imap.gmail.com", proxy=proxy, use_uid=True)
+        client.login("user@gmail.com", "password")
+    """
+
+    def __init__(self, host: str, proxy: ProxyConfig, **kwargs):
+        self._proxy = proxy
+        super().__init__(host, **kwargs)
+
+    def _create_IMAP4(self):
+        """Remplace la méthode d'IMAPClient pour injecter ProxyIMAP4_TLS."""
+        if self.ssl:
+            # self._timeout peut être un float (secondes) ou un objet avec
+            # un attribut 'connect' (ex : urllib3 Timeout).  On gère les deux.
+            _timeout = self._timeout
+            if _timeout is not None and not isinstance(_timeout, (int, float)):
+                _timeout = getattr(_timeout, "connect", None)
+            return ProxyIMAP4_TLS(
+                host=self.host,
+                port=self.port,
+                ssl_context=self.ssl_context,
+                proxy=self._proxy,
+                timeout=_timeout,
+            )
+        # Connexion non-SSL à travers le proxy (rare, mais supporté)
+        # On monkey-patch juste la connexion TCP
+        raise NotImplementedError(
+            "Connexion IMAP non-SSL via proxy non implémentée. "
+            "Utilisez ssl=True (port 993)."
+        )
+
+
+# ──────────────────────────────────────────────────────────────
+# Fonctions utilitaires
+# ──────────────────────────────────────────────────────────────
+
+def get_imap_server(login: str) -> str:
+    """Retourne le serveur IMAP correspondant au domaine du login."""
+    login_lower = login.lower()
+    for domain, server in IMAP_SERVER_MAP:
+        if domain in login_lower:
+            return server
+    return "imap.aol.com"  # fallback
+
+
+def extract_body(email_message: Message) -> str:
+    """Extrait le corps HTML ou texte d'un email."""
+    body = ""
+    for part in email_message.walk():
+        content_type = part.get_content_type()
+        try:
+            if content_type == "text/html":
+                payload = part.get_payload(decode=True)
+                if payload:
+                    body += payload.decode("utf-8", errors="ignore")
+            elif content_type == "text/plain":
+                payload = part.get_payload()
+                if payload:
+                    body += str(payload)
+        except Exception as exc:
+            logger.warning("Erreur extraction body : %s", exc)
+    return body
+
+
+def find_validation_urls(text: str) -> List[str]:
+    """Recherche toutes les URLs de validation Hermes dans un texte."""
+    return re.findall(VALIDATION_URL_REGEX, text)
+
+
+# ──────────────────────────────────────────────────────────────
+# Lecteur principal
+# ──────────────────────────────────────────────────────────────
+
+class ProxyMailReader:
+    """
+    Lit les emails d'un compte via IMAPClient en passant par un proxy.
+
+    Paramètres
+    ----------
+    account : MailAccount
+        Identifiants du compte email.
+    proxy   : ProxyConfig
+        Configuration du proxy.
+    timeout : float, optional
+        Timeout de connexion en secondes (défaut : 30 s).
+    """
+
+    def __init__(
+        self,
+        account: MailAccount,
+        proxy: ProxyConfig,
+        timeout: float = 30.0,
+    ):
+        self.account = account
+        self.proxy = proxy
+        self.timeout = timeout
+
+    # ── Connexion ────────────────────────────────────────────
+
+    def _connect(self) -> ProxyIMAPClient:
+        imap_server = get_imap_server(self.account.login)
+        logger.info(
+            "[%s] Connexion via %s → %s:993",
+            self.account.login, self.proxy, imap_server,
+        )
+        client = ProxyIMAPClient(
+            host=imap_server,
+            proxy=self.proxy,
+            use_uid=True,
+            ssl=True,
+            timeout=self.timeout,
+        )
+        client.login(self.account.login, self.account.password)
+        logger.info("[%s] Connecté.", self.account.login)
+        return client
+
+    # ── Lecture des dossiers ─────────────────────────────────
+
+    def _list_folders(self, client: ProxyIMAPClient) -> List[str]:
+        return [info[-1] for info in client.list_folders()]
+
+    # ── Lecture des messages ─────────────────────────────────
+
+    def _read_folder(
+        self,
+        client: ProxyIMAPClient,
+        folder: str,
+        since: Optional[datetime.datetime] = None,
+    ) -> List[MailResult]:
+        results: List[MailResult] = []
+        since = since or datetime.datetime.today()
+
+        try:
+            client.select_folder(folder, readonly=True)
+        except Exception as exc:
+            logger.warning("[%s] Impossible d'ouvrir '%s' : %s",
+                           self.account.login, folder, exc)
+            return results
+
+        try:
+            uids = client.search(["SINCE", since])
+        except Exception as exc:
+            logger.warning("[%s] Recherche échouée dans '%s' : %s",
+                           self.account.login, folder, exc)
+            return results
+
+        if not uids:
+            return results
+
+        logger.info("[%s] %d message(s) dans '%s'",
+                    self.account.login, len(uids), folder)
+
+        for uid, msg_data in client.fetch(uids, "RFC822").items():
+            try:
+                raw = msg_data.get(b"RFC822") or msg_data.get("RFC822")
+                if raw is None:
+                    continue
+                em = email.message_from_bytes(raw)
+
+                subject = em.get("Subject", "")
+                from_addr = em.get("From", "")
+                to_addr = em.get("To", self.account.login)
+
+                # Filtrer : on ne garde que les emails de validation Hermes
+                is_validation = (
+                    VALIDATION_URL_SUBJECT_FR in subject
+                    or VALIDATION_URL_SUBJECT_EN in subject
+                    or "no-reply@hermes.com" in from_addr.lower()
+                )
+                if not is_validation:
+                    continue
+
+                body = extract_body(em)
+                urls = find_validation_urls(body)
+
+                result = MailResult(
+                    account=self.account.login,
+                    subject=subject,
+                    from_address=from_addr,
+                    to_address=to_addr,
+                    body=body,
+                    validation_urls=urls,
+                )
+                results.append(result)
+                logger.info(
+                    "[%s] Email de validation trouvé (uid=%s) — URLs : %s",
+                    self.account.login, uid, urls or "aucune",
+                )
+            except Exception as exc:
+                logger.warning(
+                    "[%s] Erreur traitement uid=%s : %s",
+                    self.account.login, uid, exc,
+                )
+
+        return results
+
+    # ── Point d'entrée public ────────────────────────────────
+
+    def read(
+        self,
+        since: Optional[datetime.datetime] = None,
+        skip_folders: Optional[List[str]] = None,
+    ) -> List[MailResult]:
+        """
+        Se connecte au serveur IMAP via le proxy et retourne la liste
+        des emails de validation trouvés depuis `since` (aujourd'hui par défaut).
+
+        Paramètres
+        ----------
+        since        : datetime, optional  — date de début de recherche
+        skip_folders : list[str], optional — dossiers à ignorer
+                       (défaut : ["Sent", "Drafts", "Trash", "Junk", "Spam"])
+        """
+        if skip_folders is None:
+            skip_folders = ["Sent", "Drafts", "Trash", "Junk", "Spam"]
+
+        all_results: List[MailResult] = []
+        client = self._connect()
+
+        try:
+            folders = self._list_folders(client)
+            logger.info("[%s] Dossiers : %s", self.account.login, folders)
+
+            for folder in folders:
+                if folder in skip_folders:
+                    logger.debug("[%s] Dossier ignoré : %s",
+                                 self.account.login, folder)
+                    continue
+                all_results.extend(self._read_folder(client, folder, since))
+        finally:
+            try:
+                client.logout()
+            except Exception:
+                pass
+
+        return all_results
+
+
+# ──────────────────────────────────────────────────────────────
+# Lecture parallèle de plusieurs comptes
+# ──────────────────────────────────────────────────────────────
+
+from concurrent.futures import ThreadPoolExecutor, as_completed
+
+
+def read_multiple_accounts(
+    accounts: List[MailAccount],
+    proxy: ProxyConfig,
+    since: Optional[datetime.datetime] = None,
+    max_workers: int = 10,
+    timeout: float = 30.0,
+) -> List[MailResult]:
+    """
+    Lit plusieurs comptes email en parallèle via le même proxy.
+
+    Retourne la liste consolidée de tous les MailResult trouvés.
+    """
+    all_results: List[MailResult] = []
+
+    with ThreadPoolExecutor(max_workers=max_workers) as executor:
+        future_map = {
+            executor.submit(
+                ProxyMailReader(acc, proxy, timeout).read, since
+            ): acc.login
+            for acc in accounts
+        }
+        for future in as_completed(future_map):
+            login = future_map[future]
+            try:
+                results = future.result()
+                logger.info("[%s] %d email(s) de validation récupéré(s).",
+                            login, len(results))
+                all_results.extend(results)
+            except Exception as exc:
+                logger.error("[%s] Erreur : %s", login, exc)
+
+    return all_results
+
+
+# ──────────────────────────────────────────────────────────────
+# Point d'entrée — exemple d'utilisation
+# ──────────────────────────────────────────────────────────────
+
+if __name__ == "__main__":
+    logging.basicConfig(
+        level=logging.INFO,
+        format="%(asctime)s  %(levelname)-8s  %(message)s",
+        datefmt="%H:%M:%S",
+    )
+
+    # ── 1. Configurer le proxy ───────────────────────────────
+    proxy = ProxyConfig(
+        host=os.environ.get("GMX_PROXY_HOST", ""),
+        port=int(os.environ.get("GMX_PROXY_PORT", "443")),
+        proxy_type=os.environ.get("GMX_PROXY_TYPE", "SOCKS5"),
+        username=os.environ.get("GMX_PROXY_USERNAME"),
+        password=os.environ.get("GMX_PROXY_PASSWORD"),
+    )
+
+    # ── 2. Définir les comptes à lire ────────────────────────
+    accounts = [
+        MailAccount(login="birgitnaya@gmx.net",   password="XEeUF3Y1yaO"),
+        # MailAccount(login="user@gmail.com",      password="apppassword"),
+        # MailAccount(login="user@outlook.com",    password="password"),
+    ]
+
+    # ── 3. Lancer la lecture ─────────────────────────────────
+    results = read_multiple_accounts(
+        accounts=accounts,
+        proxy=proxy,
+        since=datetime.datetime.today(),
+        max_workers=5,
+        timeout=30.0,
+    )
+
+    # ── 4. Afficher les résultats ────────────────────────────
+    print(f"\n{'='*60}")
+    print(f"  {len(results)} email(s) de validation trouvé(s)")
+    print(f"{'='*60}\n")
+
+    for r in results:
+        print(f"  Compte     : {r.account}")
+        print(f"  De         : {r.from_address}")
+        print(f"  Sujet      : {r.subject}")
+        print(f"  URLs       : {r.validation_urls or 'aucune'}")
+        print(f"  {'-'*56}")
+
+
+

mail/lan_mail_helper.py

@@ -9,6 +9,7 @@ from mail.mail_reader_all_contacts import find_links_to_validate_from_mail_list
 from models.mail_pojo import MailAddress
 
 host = "https://authhk.bhdata.com:30015/bhmailer?uid=482391396&sign=32d7748da00047b9a1054c81a5750365"
+is_checking = False
 
 HERMES_EMAIL = "no-reply@hermes.com"
 
@@ -92,6 +93,9 @@ def check_confirmed_mails():
 
 
 def check_all_need_to_check_emails():
+    global is_checking
+    if not is_checking:
+        is_checking = True
         logger = logging.getLogger()
         _mail_list_before_filter = get_mail_list_to_check()
         _mails = filter_mail_with_links(_mail_list_before_filter)
@@ -100,8 +104,9 @@ def check_all_need_to_check_emails():
                 check_mail(_mail)
                 time.sleep(2)
 
-    _mail_list = [MailAddress("saigecong1990@pissmail.com", "cvExXKOP8oY1D@")]
+        # _mail_list = [MailAddress("saigecong1990@pissmail.com", "cvExXKOP8oY1D@")]
-    find_links_to_validate_from_mail_list(_mail_list, logger)
+        # find_links_to_validate_from_mail_list(_mail_list, logger)
+        is_checking = False
 
 
 def try_to_check_all_mails():
@@ -112,12 +117,12 @@ def try_to_check_all_mails():
         if "outlook.com" in _mail or "hotmail.com" in _mail:
             check_appointment_link_mail(_mail)
             time.sleep(2)
-    _mail_list = [MailAddress("saigecong1990@pissmail.com", "cvExXKOP8oY1D@")]
+    # _mail_list = [MailAddress("saigecong1990@pissmail.com", "cvExXKOP8oY1D@")]
-    find_links_to_validate_from_mail_list(_mail_list, logger)
+    # find_links_to_validate_from_mail_list(_mail_list, logger)
 
 
 if __name__ == '__main__':
-    # check_all_need_to_check_emails()
+    check_all_need_to_check_emails()
-    try_to_check_all_mails()
+    # try_to_check_all_mails()
     # check_confirmed_mails()
     # check_appointment_link_mail("hcunlvi533@outlook.com")

mail/mail_constants.py

@@ -2,6 +2,7 @@ import imaplib
 
 from imapclient import IMAPClient
 
+# 邮件域名常量
 DOMAIN_YAHOO = "yahoo.com"
 DOMAIN_SINA = "sina.com"
 DOMAIN_HOTMAIL = "hotmail.com"
@@ -10,9 +11,9 @@ DOMAIN_163 = "163.com"
 DOMAIN_RAMBLER_RU = "rambler.ru"
 DOMAIN_ALICE_IT = "alice.it"
 DOMAIN_MARS_DTI_NE_JP = "mars.dti.ne.jp"
-DOMAN_BTVM_NE_JP = "btvm.ne.jp"
+DOMAIN_BTVM_NE_JP = "btvm.ne.jp"
-DOMAN_AURORA_DTI_NE_JP = "aurora.dti.ne.jp"
+DOMAIN_AURORA_DTI_NE_JP = "aurora.dti.ne.jp"
-DOMAN_GMAIL = "gmail.com"
+DOMAIN_GMAIL = "gmail.com"
 DOMAIN_GMX = "gmx.com"
 DOMAIN_GMX_NET = "gmx.net"
 DOMAIN_GMX_AT = "gmx.at"
@@ -27,6 +28,7 @@ DOMAIN_NAVER = "naver.com"
 DOMAIN_INBOX_LV = "inbox.lv"
 DOMAIN_GMX_DE = "gmx.de"
 
+# 垃圾邮件域名
 DOMAIN_PISS_MAIL = "pissmail.com"
 DOMAIN_INCEL_EMAIL = "incel.email"
 DOMAIN_SHITPOSTING_EXPERT = "shitposting.expert"
@@ -38,6 +40,7 @@ DOMAIN_WEB_DE = "web.de"
 DOMAIN_OUTLOOK_COM = "outlook.com"
 DOMAIN_FIREMAIL_DE = "firemail.de"
 
+# IMAP服务器地址常量
 AOL_IMAP_SERVER = "imap.aol.com"
 IMAP_SERVER_163 = "imap.163.com"
 IMAP_SERVER_SINA = "imap.sina.com"
@@ -49,18 +52,17 @@ ALICE_IMAP_SERVER = "in.alice.it"
 TIME_IT_SERVER = "imap.tim.it"
 MARS_DTI_NE_JP_SERVER = "imap.cm.dream.jp"
 NAVER_SERVER = "imap.naver.com"
-BTVM_NE_JP = "imap.btvm.ne.jp"
+BTVM_NE_JP_SERVER = "imap.btvm.ne.jp"
-SEREVER_GMAIL = "imap.gmail.com"
+GMAIL_IMAP_SERVER = "imap.gmail.com"
-SERVER_IMAGE_ONET = "imap.poczta.onet.pl"
+ONET_IMAP_SERVER = "imap.poczta.onet.pl"
-SERVER_GMX = "imap.gmx.com"
+GMX_IMAP_SERVER = "imap.gmx.com"
-SERVER_GMX_NET = "imap.gmx.net"
+GMX_NET_IMAP_SERVER = "imap.gmx.net"
-SERVER_GMX_AT = "imap.gmx.at"
+GMX_AT_IMAP_SERVER = "imap.gmx.at"
-SERVER_FIREMAIL_DE = "imap.firemail.de"
+FIREMAIL_DE_IMAP_SERVER = "imap.firemail.de"
-SERVER_PISS_MAIL = "mail.pissmail.com"
+PISS_MAIL_IMAP_SERVER = "mail.pissmail.com"
-INBOX_LV = "mail.inbox.lv"
+INBOX_LV_IMAP_SERVER = "mail.inbox.lv"
-SERVER_WEB_DE = "imap.web.de"
+WEB_DE_IMAP_SERVER = "imap.web.de"
-IMAP_SERVER_DOMAIN_GAZETA_PL = "imap.gazeta.pl"
+GAZETA_PL_IMAP_SERVER = "imap.gazeta.pl"
-
 
 def show_folders(imap) -> list:
     folders = []
@@ -82,69 +84,49 @@ def show_folders(imap) -> list:
 
 
 def create_imap(login: str):
-    # create an IMAP4 class with SSL
+    # 创建一个IMAP4类实例
     if DOMAIN_163 in login:
         imap = IMAPClient(IMAP_SERVER_163, use_uid=True)
     elif DOMAIN_YAHOO in login:
-        # imap = imaplib.IMAP4_SSL(YAHOO_IMAP_SERVER)
         imap = IMAPClient(YAHOO_IMAP_SERVER, use_uid=True)
     elif DOMAIN_FIREMAIL_DE in login:
-        # imap = imaplib.IMAP4_SSL(SERVER_FIREMAIL_DE)
+        imap = IMAPClient(FIREMAIL_DE_IMAP_SERVER, use_uid=True)
-        imap = IMAPClient(SERVER_FIREMAIL_DE, use_uid=True)
     elif DOMAIN_GMX in login or DOMAIN_GMX_FR in login or DOMAIN_GMX_US in login or DOMAIN_GMX_CH in login or DOMAIN_GMX_PT in login or DOMAIN_GMX_SG in login:
-        # imap = imaplib.IMAP4_SSL(SERVER_GMX)
+        imap = IMAPClient(GMX_IMAP_SERVER, use_uid=True)
-        imap = IMAPClient(SERVER_GMX, use_uid=True)
     elif DOMAIN_SINA in login:
-        # imap = imaplib.IMAP4_SSL(IMAP_SERVER_SINA)
         imap = IMAPClient(IMAP_SERVER_SINA, use_uid=True)
     elif DOMAIN_HOTMAIL in login or DOMAIN_OUTLOOK_COM in login:
-        # imap = imaplib.IMAP4_SSL(HOTMAIL_IMAP_SERVER)
         imap = IMAPClient(HOTMAIL_IMAP_SERVER, use_uid=True)
     elif DOMAIN_RAMBLER_RU in login:
-        # imap = imaplib.IMAP4_SSL(RAMBLER_IMAP_SERVER)
         imap = IMAPClient(RAMBLER_IMAP_SERVER, use_uid=True)
-    elif DOMAN_BTVM_NE_JP in login:
+    elif DOMAIN_BTVM_NE_JP in login:
-        # imap = imaplib.IMAP4_SSL(BTVM_NE_JP)
+        imap = IMAPClient(BTVM_NE_JP_SERVER, use_uid=True)
-        imap = IMAPClient(BTVM_NE_JP, use_uid=True)
+    elif DOMAIN_GMAIL in login:
-    elif DOMAN_GMAIL in login:
+        imap = IMAPClient(GMAIL_IMAP_SERVER, use_uid=True)
-        # imap = imaplib.IMAP4_SSL(SEREVER_GMAIL, port=993)
-        imap = IMAPClient(SEREVER_GMAIL, use_uid=True)
     elif DOMAIN_ONET in login:
-        imap = IMAPClient(SERVER_IMAGE_ONET, use_uid=True)
+        imap = IMAPClient(ONET_IMAP_SERVER, use_uid=True)
     elif DOMAIN_TIM_IT in login:
-        # imap = imaplib.IMAP4(TIME_IT_SERVER)
         imap = IMAPClient(TIME_IT_SERVER, use_uid=True)
     elif DOMAIN_ALICE_IT in login:
-        # imap = imaplib.IMAP4(ALICE_IMAP_SERVER, port=143)
         imap = IMAPClient(ALICE_IMAP_SERVER, use_uid=True)
     elif DOMAIN_MARS_DTI_NE_JP in login:
-        # imap = imaplib.IMAP4(MARS_DTI_NE_JP_SERVER, port=143)
         imap = IMAPClient(MARS_DTI_NE_JP_SERVER, use_uid=True)
-    elif DOMAN_AURORA_DTI_NE_JP in login:
+    elif DOMAIN_AURORA_DTI_NE_JP in login:
-        # imap = imaplib.IMAP4(MARS_DTI_NE_JP_SERVER, port=143)
         imap = IMAPClient(MARS_DTI_NE_JP_SERVER, use_uid=True)
     elif DOMAIN_NAVER in login:
-        # imap = imaplib.IMAP4_SSL(NAVER_SERVER, port=993)
         imap = IMAPClient(NAVER_SERVER, use_uid=True)
     elif DOMAIN_GMX_DE in login or DOMAIN_GMX_NET in login:
-        # imap = imaplib.IMAP4_SSL(SERVER_GMX_NET, port=993)
+        imap = IMAPClient(GMX_NET_IMAP_SERVER, use_uid=True)
-        imap = IMAPClient(SERVER_GMX_NET, use_uid=True)
     elif DOMAIN_GMX_AT in login:
-        # imap = imaplib.IMAP4_SSL(SERVER_GMX_AT, port=993)
+        imap = IMAPClient(GMX_AT_IMAP_SERVER, use_uid=True)
-        imap = IMAPClient(SERVER_GMX_AT, use_uid=True)
     elif DOMAIN_GAZETA_PL in login:
-        # imap = imaplib.IMAP4_SSL(IMAP_SERVER_DOMAIN_GAZETA_PL, port=993)
+        imap = IMAPClient(GAZETA_PL_IMAP_SERVER, use_uid=True)
-        imap = IMAPClient(IMAP_SERVER_DOMAIN_GAZETA_PL, use_uid=True)
     elif DOMAIN_INBOX_LV in login:
-        # imap = imaplib.IMAP4_SSL(INBOX_LV, port=993)
+        imap = IMAPClient(INBOX_LV_IMAP_SERVER, use_uid=True)
-        imap = IMAPClient(INBOX_LV, use_uid=True)
     elif DOMAIN_WEB_DE in login:
-        # imap = imaplib.IMAP4_SSL(SERVER_WEB_DE, port=993)
+        imap = IMAPClient(WEB_DE_IMAP_SERVER, use_uid=True)
-        imap = IMAPClient(SERVER_WEB_DE, use_uid=True)
     elif DOMAIN_PISS_MAIL in login or DOMAIN_CHILD_PIZZA in login or DOMAIN_DMC_CHAT in login or DOMAIN_GENOCIDE_FUN in login or DOMAIN_HATESJE_WS in login or DOMAIN_INCEL_EMAIL in login or DOMAIN_SHITPOSTING_EXPERT in login:
-        # imap = imaplib.IMAP4_SSL(SERVER_PISS_MAIL, port=993)
+        imap = IMAPClient(PISS_MAIL_IMAP_SERVER, use_uid=True)
-        imap = IMAPClient(SERVER_PISS_MAIL, use_uid=True)
     else:
-        # imap = imaplib.IMAP4_SSL(AOL_IMAP_SERVER)
         imap = IMAPClient(AOL_IMAP_SERVER, use_uid=True)
     return imap

mail/mail_reader_all_contacts.py

@@ -1,88 +1,171 @@
 import datetime
 import email
 import logging
+import os
 import re
-from builtins import list
 from concurrent.futures import ThreadPoolExecutor
 from email.header import decode_header
 from email.message import Message
-from typing import Union
+from typing import Union, List, Optional
 
+from dotenv import load_dotenv
 from imapclient import IMAPClient
 from db.mongo_manager import MONGO_STORE_MANAGER
 from excel_reader import read_contacts
 from mail.mail_constants import DOMAIN_HOTMAIL, create_imap
+from mail.imap_proxy_reader import ProxyIMAPClient, ProxyConfig, get_imap_server
 from models.ReserveResultPojo import ReserveResultPojo
 from models.mail_pojo import MailPojo, MailAddress
 
-VALIDATION_URL_SUBJECT_fr = 'Validation de votre demande de rendez-vous'
+# Charger les variables d'environnement depuis .env
+load_dotenv()
+
+# 定义常量
+VALIDATION_URL_SUBJECT_FR = 'Validation de votre demande de rendez-vous'
 VALIDATION_URL_SUBJECT_EN = 'Please confirm your appointment request'
-VALIDATION_URL_REGEX = """https:\/\/rendezvousparis.hermes.com\/client\/register\/[A-Z0-9]+\/validate.code=[A-Z0-9]+"""
+VALIDATION_URL_REGEX = r"https:\/\/rendezvousparis.hermes.com\/client\/register\/[A-Z0-9]+\/validate.code=[A-Z0-9]+"
-PART_VALIDATION_URL_REGEX = """client\/register\/[A-Z0-9]+\/validate.code=[A-Z0-9]+"""
+PART_VALIDATION_URL_REGEX = r"client\/register\/[A-Z0-9]+\/validate.code=[A-Z0-9]+"
 HERMES_EMAIL = "no-reply@hermes.com"
 EMAIL_ADDRESS_REGEX = r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,7}\b'
 
-date_format = "%d-%b-%Y"  # DD-Mon-YYYY e.g., 3-Mar-2014
+# 日期格式
+DATE_FORMAT = "%d-%b-%Y"
+
+# Timeouts GMX (en secondes)
+IMAP_SOCKET_TIMEOUT = 300   # timeout socket pour chaque opération IMAP
+FUTURE_TIMEOUT = 600        # durée max allouée à la lecture d'une boîte mail
+
+# GMX域名列表（用于判断是否需要使用代理）
+GMX_DOMAINS = (
+    "gmx.com", "gmx.net", "gmx.de", "gmx.at",
+    "gmx.fr",  "gmx.us",  "gmx.sg", "gmx.ch", "gmx.pt",
+)
+
+# 需要通过代理读取的域名列表
+# PROXY_DOMAINS = GMX_DOMAINS + ("inbox.lv",)
+PROXY_DOMAINS = GMX_DOMAINS
+
+
+def is_gmx_account(login: str) -> bool:
+    """判断邮箱是否属于GMX域名"""
+    return any(d in login.lower() for d in GMX_DOMAINS)
+
+
+def is_proxy_account(login: str) -> bool:
+    """判断邮箱是否需要通过代理读取（GMX 或 inbox.lv）"""
+    return any(d in login.lower() for d in PROXY_DOMAINS)
+
+# 邮箱列表（简化为常量）
 REDIRECTION_MAILS = "appointment2022@aol.com, chenpeijun@aol.com,hongjiang176@aol.com,ciyuexie@aol.com,rutger.62@aol.com,ciccidaniel@aol.com,armasgoodman@aol.com,wknd.gemerine@aol.com,rafmail1981@aol.com,tonovichivanenaki@aol.com,hetland.ari@aol.com,mateusiversen@aol.com,lacerdaraffaello@aol.com,anasida76@aol.com,liamolinari@aol.com,sen70zib@aol.com,mezeiderrick@aol.com,stanisl49avchic@aol.com,damcvrobaneuron@aol.com,suyzanna_fleona@aol.com,dxealing.dissa@aol.com,hogg.karen@aol.com,obocharovamarina@aol.com,buchholzjohann@aol.com,orn.cecchini@aol.com,percivaltorgersen@aol.com,candalgudrun@aol.com,filimonis.76@aol.com,bengann_100@aol.com,axelhanne@aol.com,tiffanylarochelle@aol.com,nicoleta.r@aol.com,eichenbaum.1963@aol.com,kotensasharev@aol.com,samognat32@aol.com,edem_headshot@aol.com,kozmakuzmich1960@aol.com,damonsvensson@aol.com,anders.riva@aol.com,caiminwei123@gmail.com,yulingguo086@gmail.com,yingxiaolu086@gmail.com,lijiazhen0035@gmail.com,fangp370@gmail.com,huangyayu10086@gmail.com,fuziyuan110@gmail.com,xinyingdu886@gmail.com,yasiaforever.1971@aol.com,lukaszfidalgo@aol.com,zaichi29@aol.com,prostotakitak.1974@aol.com,mo90nroe@aol.com,blonde.87@aol.com,dimidrol.1969@aol.com"
 
 
-def check_email_address(email):
+# 邮件处理相关函数
-    # pass the regular expression
+def is_valid_email(email: str) -> bool:
-    # and the string into the fullmatch() method
+    """验证邮箱地址是否有效"""
-    if (re.fullmatch(EMAIL_ADDRESS_REGEX, email)):
+    return re.fullmatch(EMAIL_ADDRESS_REGEX, email) is not None
-        print("Valid Email")
-        return True
-    else:
-        print("Invalid Email:" + email)
-        return False
 
 
-def find_from_mail(param):
+def extract_email_from_from_address(content: str) -> str:
+    """从邮件地址中提取邮箱"""
+    match = re.search(r'[\w.+-]+@[\w-]+\.[\w.-]+', content)
+    return match.group(0) if match else ""
+
+
+def find_from_mail(param) -> str:
+    """解析邮件地址"""
     from_address, encoded_algo = param[0]
+
+    # 处理字节编码
     if isinstance(from_address, bytes):
         from_address = from_address.decode(encoded_algo)
-        if not check_email_address(from_address) and len(param) == 2:
+
+        # 如果邮箱地址无效，尝试另一种编码
+        if not is_valid_email(from_address) and len(param) == 2:
             from_address, new_encode = param[1]
             if new_encode is None:
                 new_encode = encoded_algo
             if isinstance(from_address, bytes):
                 from_address = from_address.decode(new_encode)
-                return from_address.strip(" ").strip(">").strip("<")
+
+    # 清理邮箱地址
     return from_address.strip(" ").strip(">").strip("<")
 
 
-def extract_email_from_from_address(content: str):
+class MailReader:
-    _match = re.search(r'[\w.+-]+@[\w-]+\.[\w.-]+', content)
+    """邮件读取器类"""
-    return _match.group(0)
 
-
+    def __init__(self, login: str, password: str, proxy: Optional[ProxyConfig] = None,
-class MailReader():
+                 failed_gmx_list: Optional[List[str]] = None):
-    def __init__(self, login, password):
         self.login = login
         self.password = password
+        self.proxy = proxy
+        self.failed_gmx_list = failed_gmx_list if failed_gmx_list is not None else []
 
     @staticmethod
-    def show_folders(imap) -> list:
+    def show_folders(imap) -> List[str]:
+        """获取邮箱文件夹列表"""
         folders = []
-        isImapClient = isinstance(imap, IMAPClient)
+        is_imap_client = isinstance(imap, IMAPClient)
-        if not isImapClient:
+
+        if not is_imap_client:
+            # 处理非IMAPClient对象
             for i in imap.list()[1]:
                 l = i.decode().split(' "/" ')
                 folders.append(l[1])
-            return folders
         else:
-            list = imap.list_folders()
+            # 处理IMAPClient对象
-            for i in list:
+            folder_list = imap.list_folders()
+            for i in folder_list:
                 name = i[-1]
                 folders.append(name)
+
         return folders
 
-    def read_emails(self, mails_messages: list) -> list:
+    def read_emails(self, mails_messages: List[MailPojo]) -> List[MailPojo]:
-        imap = create_imap(self.login)
+        """读取邮件"""
-        isImapClient = isinstance(imap, IMAPClient)
+        # ── GMX / inbox.lv 账户 → 使用代理连接（失败自动重试最多3次）──
-        print("isImapClient is " + str(isImapClient))
+        if is_proxy_account(self.login) and self.proxy is not None:
-        if isImapClient:
+            return self._read_emails_with_proxy_retry(mails_messages)
-            # authenticate
+        else:
+            return self._read_emails_internal(create_imap(self.login), mails_messages)
+
+    def _read_emails_with_proxy_retry(
+        self,
+        mails_messages: List[MailPojo],
+        max_retries: int = 8,
+    ) -> List[MailPojo]:
+        """通过 ProxyIMAPClient 读取邮件（GMX / inbox.lv），失败时最多重试 max_retries 次。"""
+        imap_server = get_imap_server(self.login)
+        last_error: Optional[Exception] = None
+
+        for attempt in range(1, max_retries + 1):
+            try:
+                print("[Proxy] {} → {} via {} (tentative {}/{})".format(
+                    self.login, imap_server, self.proxy, attempt, max_retries))
+                imap = ProxyIMAPClient(
+                    host=imap_server,
+                    proxy=self.proxy,
+                    use_uid=True,
+                    ssl=True,
+                    timeout=IMAP_SOCKET_TIMEOUT,
+                )
+                return self._read_emails_internal(imap, mails_messages)
+            except Exception as exc:
+                last_error = exc
+                print("[Proxy] Échec tentative {}/{} pour {} : {}".format(
+                    attempt, max_retries, self.login, exc))
+
+        print("[Proxy] Toutes les tentatives ont échoué pour {} : {}".format(
+            self.login, last_error))
+        self.failed_gmx_list.append(self.login)
+        return []
+
+    def _read_emails_internal(self, imap, mails_messages: List[MailPojo]) -> List[MailPojo]:
+        """Logique commune de lecture des emails (IMAPClient ou imaplib)."""
+        is_imap_client = isinstance(imap, IMAPClient)
+
+        # 登录邮箱
+        if is_imap_client:
             dat = imap.login(self.login, str(self.password))
             print("type is {} for {}".format(dat, self.login))
         else:
@@ -91,224 +174,352 @@ class MailReader():
 
         mail_list = []
         print("read mails from {}".format(self.login))
-        if not isImapClient:
+
+        # 获取文件夹列表
         folder_list = self.show_folders(imap)
+
+        # 处理每个文件夹
         for folder in folder_list:
             print("folder is {}".format(folder))
-                mail_list.extend(self._get_messages_from_folder(imap, subject=VALIDATION_URL_SUBJECT_fr,
+
-                                                                folder=folder))
+            # 跳过Sent和Drafts文件夹
-                mail_list.extend(self._get_messages_from_folder(imap, subject=VALIDATION_URL_SUBJECT_EN,
+            if folder in ["Sent", "Drafts"]:
-                                                                folder=folder))
+                continue
+
+            if is_imap_client:
+                # 使用IMAPClient处理
+                mail_list.extend(self._get_messages_from_folder_for_imapclient(imap, folder))
             else:
-            folder_list = self.show_folders(imap)
+                # 使用传统IMAP处理
-            for folder in folder_list:
+                mail_list.extend(self._get_messages_from_folder(imap, subject=VALIDATION_URL_SUBJECT_FR, folder=folder))
-                print("folder is " + folder)
+                mail_list.extend(self._get_messages_from_folder(imap, subject=VALIDATION_URL_SUBJECT_EN, folder=folder))
-                if folder == "Sent" or folder == "Drafts":
+
-                    pass
+        # 关闭连接
-                else:
+        if not is_imap_client:
-                    mail_list.extend(self._get_messages_from_folder_for_imapclient(imap, folder=folder))
-        if not isImapClient:
             imap.close()
         imap.logout()
+
+        # 添加邮件到结果列表
         mails_messages.extend(mail_list)
         return mail_list
 
-    def _get_messages_from_folder(self, imap, subject, folder="INBOX") -> list:
+    def _get_messages_from_folder(self, imap, subject: str, folder: str = "INBOX") -> List[MailPojo]:
+        """从指定文件夹获取邮件（传统IMAP方式）"""
         imap.select(folder)
         mail_messages = []
-        typ, data = imap.search(None, '(SUBJECT "{}" SINCE "{}")'.format(subject,
+
-                                                                         datetime.datetime.today().strftime(
+        # 搜索邮件
-                                                                             date_format)))
+        search_query = '(SUBJECT "{}" SINCE "{}")'.format(subject, datetime.datetime.today().strftime(DATE_FORMAT))
+        typ, data = imap.search(None, search_query)
+
         for i in data[0].split():
-            # fetch the email message by ID
+            try:
+                # 获取邮件内容
                 res, msg = imap.fetch(i.decode("utf-8"), "(RFC822)")
-            body = ''
+
+                # 解析邮件
                 for response in msg:
                     if isinstance(response, tuple):
-                    # parse a bytes email into a message object
+                        email_message = email.message_from_bytes(response[1])
-                    msg = email.message_from_bytes(response[1])
+
-                    # decode the email subject
+                        # 解码主题
-                    subject, subject_encoded = decode_header(msg["Subject"])[0]
+                        subject, subject_encoded = decode_header(email_message["Subject"])[0]
-                    received_date = msg["Date"]
                         if isinstance(subject, bytes):
-                        # if it's a bytes, decode to str
                             subject = subject.decode(subject_encoded)
-                    # decode email sender
+
-                    from_address = find_from_mail(decode_header(msg.get("From")))
+                        # 解码发件人地址
-                    to_email = find_from_mail(decode_header(msg.get("To")))
+                        from_address = find_from_mail(decode_header(email_message.get("From")))
+
+                        # 解码收件人地址
+                        to_email = find_from_mail(decode_header(email_message.get("To")))
+
                         print("Email:", self.login)
                         print("From:", from_address)
                         print("To:", to_email)
                         print("Subject:", subject)
-                    # if the email message is multipart
+
-                    if msg.is_multipart():
+                        # 获取邮件正文
-                        # iterate over email parts
+                        body = self._extract_body(email_message)
-                        for part in msg.walk():
+
-                            try:
+                        # 检查是否是预约验证邮件
-                                # get the email body
+                        if VALIDATION_URL_SUBJECT_FR in subject or VALIDATION_URL_SUBJECT_EN in subject:
-                                payloads = part.get_payload()
+                            mail = MailPojo(
-                                if isinstance(payloads, list):
+                                subject=subject,
-                                    for payload in payloads:
+                                body=body,
-                                        if isinstance(payload, Message):
+                                from_address=from_address
-                                            body = body + payload.get_payload(decode=True).decode("iso-8859-1")
+                            )
-                                # print(body)
+
-                            except Exception as Error:
+                            # 设置收件人地址
-                                print(Error)
-                    else:
-                        body = msg.get_payload(decode=True).decode()
-                        print(body)
-                    if VALIDATION_URL_SUBJECT_fr in subject or VALIDATION_URL_SUBJECT_EN in subject:
-                        mail = MailPojo(subject=subject, body=body, from_address=from_address)
                             if to_email is None:
                                 mail.to_address = self.login
                             else:
                                 mail.to_address = to_email
+
                             mail.mail_address = self.login
                             mail_messages.append(mail)
+            except Exception as error:
+                print("Error processing email: {}".format(error))
+
         return mail_messages
 
-    def _get_messages_from_folder_for_imapclient(self, imap, folder="INBOX") -> list:
+    def _extract_body(self, email_message: Message) -> str:
+        """提取邮件正文"""
+        body = ""
+
+        # 遍历邮件部分
+        for part in email_message.walk():
+            try:
+                content_type = part.get_content_type()
+
+                if content_type == "text/html":
+                    # 处理HTML内容
+                    payload = part.get_payload(decode=True)
+                    if payload:
+                        body += payload.decode("utf-8", errors="ignore")
+                elif content_type == "text/plain":
+                    # 处理纯文本内容
+                    payload = part.get_payload()
+                    if payload:
+                        body += payload
+            except Exception as error:
+                print("Error extracting body part: {}".format(error))
+
+        return body
+
+    def _get_messages_from_folder_for_imapclient(self, imap, folder: str = "INBOX") -> List[MailPojo]:
+        """从指定文件夹获取邮件（IMAPClient方式）"""
         mail_messages = []
+
+        # 搜索邮件
         search_terms = 'SINCE "{}"'.format(
-            datetime.datetime.today().strftime(
+            datetime.datetime.today().strftime(DATE_FORMAT))
-                date_format))
         print("{}: search terms is {}".format(self.login, search_terms))
+
         imap.select_folder(folder)
         messages = imap.search(['SINCE', datetime.datetime.today()])
         print("{}: {} messages from our best friend".format(self.login, len(messages)))
+
         if len(messages) == 0:
             return mail_messages
+
+        # 处理每封邮件
         for uid, message_data in imap.fetch(messages, 'RFC822').items():
             try:
                 email_message = email.message_from_bytes(message_data[b'RFC822'])
+
+                # 获取发件人和主题
                 from_address = email_message.get('FROM')
                 subject = email_message.get('subject')
-                body = ""
+
-                hermes_mail_adress = "no-reply@hermes.com"
+                # 检查是否是Hermes邮件
-                if hermes_mail_adress in from_address or "outlook.com" in from_address or "hotmail" in from_address:
+                hermes_mail_address = "no-reply@hermes.com"
-                    for part in email_message.walk():
+                if (hermes_mail_address in from_address or
-                        print(part.get_content_type())
+                        "outlook.com" in from_address or
-                        if part.get_content_type() == "text/html":
+                        "hotmail" in from_address):
-                            body = body + part.get_payload(decode=True).decode("utf-8")
+
-                        elif part.get_content_type() == "text/plain":
+                    # 提取邮件正文
-                            body = body + part.get_payload()
+                    body = self._extract_body_for_imapclient(email_message)
-                    if VALIDATION_URL_SUBJECT_fr in subject or VALIDATION_URL_SUBJECT_EN in subject or "Votre=20demande=20de=20rendez-vous" in subject or "Votre demande de rendez-vous" in body:
+
-                        mail = MailPojo(subject=subject, body=body, from_address=from_address)
+                    # 检查是否是预约验证邮件
+                    if (VALIDATION_URL_SUBJECT_FR in subject or
+                            VALIDATION_URL_SUBJECT_EN in subject or
+                            "Votre=20demande=20de=20rendez-vous" in subject or
+                            "Votre demande de rendez-vous" in body):
+
+                        mail = MailPojo(
+                            subject=subject,
+                            body=body,
+                            from_address=from_address
+                        )
                         mail.isImapClient = True
+
                         print("email is {}".format(self.login))
                         print("body is {}".format(body))
                         print("subject is {}".format(subject))
+
+                        # 设置收件人地址
                         if len(mail.to_address) == 0:
                             if "outlook.com" in from_address or "hotmail.com" in from_address:
-                                # it is a transferred email
+                                # 转发邮件
                                 mail.to_address = extract_email_from_from_address(from_address)
                             else:
                                 mail.to_address = self.login
+
                         mail_messages.append(mail)
             except Exception as error:
-                print(error)
+                print("Error trying to read email_Message for {}: {}".format(self.login, error))
-                print("error trying to read email_Message for {}".format(self.login))
+
         return mail_messages
 
+    def _extract_body_for_imapclient(self, email_message: Message) -> str:
+        """提取IMAPClient邮件正文"""
+        body = ""
 
-#
+        for part in email_message.walk():
-# Find the ReserveResultPojo object from persisted items of DB
+            content_type = part.get_content_type()
-#
+
+            if content_type == "text/html":
+                payload = part.get_payload(decode=True)
+                if payload:
+                    body += payload.decode("utf-8", errors="ignore")
+            elif content_type == "text/plain":
+                payload = part.get_payload()
+                if payload:
+                    body += payload
+
+        return body
+
+
+# 邮件处理相关函数
 def find_item_by_url(url: str, successful_items) -> Union[None, ReserveResultPojo]:
+    """根据URL查找预约结果对象"""
     print("url is :" + url)
     parts = url.split('/')
     _id = parts[5]
+
     if len(_id) == 6:
         for item in successful_items:
             if item.id == _id:
                 return item
+
     return None
 
 
 def need_to_valid_url(url: str, item: Union[ReserveResultPojo, None]) -> bool:
+    """判断是否需要验证URL"""
     print("url is :" + url)
     parts = url.split('/')
-    id = parts[5]
+    _id = parts[5]
-    if len(id) == 6:
+
+    if len(_id) == 6:
         if item:
             if item.url_validated is not None:
                 return not item.url_validated
             else:
-                # if url_validated is None
+                # 如果url_validated为None，需要验证
                 return True
         return True
-    else:
+
-        print("id not valid:{}".format(id))
+    print("id not valid:{}".format(_id))
     return False
 
 
 def need_to_check_email(mail: str, successful_items) -> bool:
+    """判断是否需要检查邮件"""
     print("successful_items size is " + str(len(successful_items)))
-    if mail =="saigecong1990@pissmail.com":
+
-        return True
+    # 过滤已验证的项目
-    filtered_items = list(filter(lambda item: item.email == mail, successful_items))
+    filtered_items = [item for item in successful_items if item.email == mail]
-    # has validated value
+
-    if len(filtered_items) > 0:
+    # 检查是否有已验证的项目
-        validated_items = list(filter(
+    validated_items = [item for item in filtered_items
-            lambda filtered_item: filtered_item.url_validated is not None and filtered_item.url_validated is True,
+                       if item.url_validated is not None and item.url_validated is True]
-            filtered_items))
+
-        if len(validated_items) > 0:
+    return len(validated_items) == 0
-            return False
-        else:
-            return True
-    else:
-        return True
 
 
-def find_links_to_validate_from_mail_list(mail_list: list, logger):
+def find_links_to_validate_from_mail_list(
+        mail_list: List[MailAddress],
+        logger,
+        proxy: Optional[ProxyConfig] = None,
+) -> List[str]:
+    """从邮件列表中查找需要验证的链接，返回读取失败的GMX账户列表"""
     if not mail_list:
-        return
+        return []
-    # check time before start checking emails
+
+    # 检查时间前开始检查邮件
     contact_to_book_list = MONGO_STORE_MANAGER.get_all_contact_to_book_list()
     successful_items = MONGO_STORE_MANAGER.get_all_successful_items_for_day()
+
     mails_messages = []
-    with ThreadPoolExecutor(max_workers=200) as executor:
+    failed_gmx: List[str] = []
+
+    # 使用线程池处理邮件
+    with ThreadPoolExecutor(max_workers=100) as executor:
+        futures = []
+
         for mail in mail_list:
-            # check whether we need to read mail
+            # 检查是否需要读取邮件
             if need_to_check_email(mail.mail, successful_items):
-                mail_reader = MailReader(mail.mail, mail.password)
+                mail_reader = MailReader(mail.mail, mail.password, proxy=proxy,
-                executor.submit(mail_reader.read_emails, mails_messages)
+                                        failed_gmx_list=failed_gmx)
+                future = executor.submit(mail_reader.read_emails, mails_messages)
+                futures.append(future)
+
+        # 等待所有任务完成
+        for future in futures:
+            try:
+                future.result(timeout=FUTURE_TIMEOUT)
+            except TimeoutError:
+                print("⏱️  Timeout ({} s) dépassé pour une boîte mail — lecture ignorée.".format(FUTURE_TIMEOUT))
+            except Exception as e:
+                print("Error processing mail: {},login: {}, password: {}".format(e,mail.mail, mail.password))
+
+    # ── Résumé des comptes proxy en échec ──────────────────────
+    if failed_gmx:
+        print("\n[Proxy] ⚠️  {} compte(s) non lus (GMX / inbox.lv) :".format(len(failed_gmx)))
+        for addr in failed_gmx:
+            print("  ✗ {}".format(addr))
+    else:
+        print("\n[Proxy] ✅ Tous les comptes GMX / inbox.lv ont été lus avec succès.")
+
+    # 刷新成功的项目
     _refreshed_successful_items = MONGO_STORE_MANAGER.get_all_successful_items_for_day()
+
+    # 处理邮件中的链接
     for mail in mails_messages:
         match = re.search(VALIDATION_URL_REGEX, mail.body)
         if match:
             url = match.group(0)
             _item = find_item_by_url(url, _refreshed_successful_items)
+
             if need_to_valid_url(url, _item):
                 logger.info("need to validate url: " + url)
                 _model = ""
+                _used_ip = ""
                 if _item:
                     _model = _item.model
-                MONGO_STORE_MANAGER.save_links_to_validate(url, mail.to_address, model=_model,
+                    _used_ip = _item.current_ip
-                                                           _all_contact_list=contact_to_book_list)
+
+                MONGO_STORE_MANAGER.save_links_to_validate(
+                    url,
+                    mail.to_address,
+                    model=_model,
+                    _all_contact_list=contact_to_book_list, _used_ip= _used_ip)
             else:
                 logger.info("do not need to click url --> {}".format(mail.mail_address))
 
+    return failed_gmx
 
+
+# 主函数
 if __name__ == '__main__':
-    # mail_address1 = MailAddress(mail="tinagonzales685585@aol.com", password="yhihvdkrbxnksema")
+    # 读取联系人列表
-    # mail_list = [mail_address1]
     contact_to_book_list = read_contacts(
-        # file_name="/Users/rdv/Desktop/contact_list_not_used_contacts.xlsx")
+        # file_name="~/Desktop/contact_list_inbox_lv_100.xlsx")
-        # file_name="/Users/lpan/Desktop/contact_list_not_used_contacts.xlsx")
+        # file_name="~/Desktop/contact_yahoo_5.xlsx")
-        # file_name="/Users/rdv/Desktop/real_name_contacts_100_hotmail.xlsx")
+        # file_name="~/Desktop/contact_list_2026-04-07.xlsx")
-    # file_name="~/Desktop/contact_list_2025-07-11.xlsx")
+        # file_name="~/Desktop/contact_list_2026-04-11.xlsx")
-    file_name="~/Desktop/contact_list_all_studio.xlsx")
+        file_name="~/Desktop/contact_list_2026-04-15.xlsx")
-    # file_name="/Users/rdv/Desktop/contact_list_all_studo_gmx_us.xlsx")
+        # file_name="~/Desktop/contact_list_inbox_100_14_04.xlsx")
-    # file_name="/Users/rdv/Desktop/contact_list_2025-05-24.xlsx")
+        # file_name="~/Desktop/yahooo_list.xlsx")
+
+    # 获取目标邮箱列表
     all_mail_list = MONGO_STORE_MANAGER.get_destination_emails()
+
+    # 筛选需要检查的邮件列表
     mail_list_to_check = []
     for contact in contact_to_book_list:
         for mail in all_mail_list:
             if contact.mail == mail.mail:
                 mail_list_to_check.append(mail)
+
+    # 设置日志记录器
     logger = logging.getLogger()
+    # 获取已验证的链接列表
     _all_links = MONGO_STORE_MANAGER.get_links_to_validate()
+
+    # 过滤掉已处理的邮件
     filter_mail = []
     for mail_pojo in mail_list_to_check:
         _to_add = True
@@ -317,6 +528,31 @@ if __name__ == '__main__':
                 _to_add = False
         if _to_add:
             filter_mail.append(mail_pojo)
-    filter_mail.append(MailAddress("saigecong1990@pissmail.com", "cvExXKOP8oY1D@"))
+    # filter_mail = [MailAddress("munozshawn1992@aol.com", "leivqvcwyacrgbzp")]
-    # filter_mail = [MailAddress("saigecong1990@pissmail.com", "cvExXKOP8oY1D@")]
+
-    find_links_to_validate_from_mail_list(filter_mail, logger)
+    # ── Mode de lecture : GMX_ONLY=true → uniquement les comptes GMX ──
+    gmx_only = os.environ.get("GMX_ONLY", "false").strip().lower() == "true"
+    if gmx_only:
+        filter_mail = [m for m in filter_mail if is_gmx_account(m.mail)]
+        print("[Mode] Lecture GMX uniquement ({} comptes)".format(len(filter_mail)))
+    else:
+        print("[Mode] Lecture de tous les comptes ({} comptes)".format(len(filter_mail)))
+
+    # 配置代理（GMX账号必须通过代理读取）
+    gmx_proxy = ProxyConfig(
+        host=os.environ.get("GMX_PROXY_HOST", ""),
+        port=int(os.environ.get("GMX_PROXY_PORT", "443")),
+        proxy_type=os.environ.get("GMX_PROXY_TYPE", "SOCKS5"),
+        username=os.environ.get("GMX_PROXY_USERNAME"),
+        password=os.environ.get("GMX_PROXY_PASSWORD"),
+    )
+    # 处理邮件
+    failed = find_links_to_validate_from_mail_list(filter_mail, logger, proxy=gmx_proxy)
+
+    # ── Afficher les comptes GMX non lus ─────────────────────
+    if failed:
+        print("\n===== Comptes GMX non lus ({}) =====".format(len(failed)))
+        for addr in failed:
+            print("  ✗ {}".format(addr))
+    else:
+        print("\n===== Tous les comptes GMX ont été lus avec succès =====")

migrate_cached_request_data.py

@@ -1,13 +1,14 @@
 from multiprocessing import Process
 
-from queue_message.CookiesPublisher import MORNING_DATA_CACHE_2, MORNING_DATA_CACHE, MORNING_DATA_CACHE_BAK
+from queue_message.CookiesPublisher import MORNING_DATA_CACHE_2, MORNING_DATA_CACHE, MORNING_DATA_CACHE_BAK, \
+    REGISTER_QUEUE
 from workers.MessagerTransporter import migrate_message_to_queue
 
 if __name__ == '__main__':
-    # p1 = Process(target=migrate_message_to_queue, args=(MORNING_DATA_CACHE_2, MORNING_DATA_CACHE_BAK))
+    p1 = Process(target=migrate_message_to_queue, args=(MORNING_DATA_CACHE, MORNING_DATA_CACHE_BAK))
-    # p1.start()
+    p1.start()
-    p2 = Process(target=migrate_message_to_queue, args=(MORNING_DATA_CACHE, MORNING_DATA_CACHE_BAK))
+    p2 = Process(target=migrate_message_to_queue, args=(MORNING_DATA_CACHE_2, MORNING_DATA_CACHE_BAK))
     p2.start()
-    # p2.join()
+    p2.join()
     # migrate_message_to_queue(from_queue=MORNING_DATA_CACHE_2)
     # migrate_message_to_queue(from_queue=MORNING_DATA_CACHE)

models/ReserveResultPojo.py

@@ -16,7 +16,6 @@ class PublishType(Enum):
 @dataclass_json
 @dataclass
 class ReserveResultPojo:
-    type: PublishType = PublishType.ERROR
     phone: str = ""
     message: str = ""
     url: str = ""
@@ -38,14 +37,10 @@ class ReserveResultPojo:
     proxy: str = None
     ua: str = None
     current_ip: str = ""
+    timestampInS: list = None
 
     @staticmethod
     def from_firestore_dict(source):
-        publish_type = PublishType.ERROR
-        if 'type' in source:
-            publish_type = source['type']
-            if publish_type:
-                publish_type = PublishType[publish_type]
         if 'phone' in source:
             phone = source['phone']
         else:
@@ -54,8 +49,6 @@ class ReserveResultPojo:
             url = source['url']
         else:
             url = ""
-        if 'id' in source:
-            id = source['id']
         if '_id' in source:
             id = source['_id']
         else:
@@ -74,7 +67,7 @@ class ReserveResultPojo:
         else:
             firstName = ""
 
-        result = ReserveResultPojo(type=publish_type, phone=phone,
+        result = ReserveResultPojo(phone=phone,
                                    url=url, email=email,
                                    firstName=firstName, lastName=lastName)
         if 'accepted' in source:
@@ -113,12 +106,14 @@ class ReserveResultPojo:
         if 'validated_at' in source:
             validated_at = source['validated_at']
             result.validated_at = validated_at
+        if 'current_ip' in source:
+            current_ip = source['current_ip']
+            result.current_ip = current_ip
         result.id = id
         return result
 
     def to_firestore_dict(self):
         dest = {
-            u'type': self.type.value,
             u'id': self.id,
             u'phone': self.phone,
             u'firstName': self.firstName,
@@ -135,6 +130,7 @@ class ReserveResultPojo:
             u'url_validated': self.url_validated,
             u'proxy': self.proxy,
             u'current_ip': self.current_ip,
+            u'timestamp_in_s': "-".join(str(x) for x in self.timestampInS),
             u'ua': self.ua,
         }
 

models/jsdata_le_pojo.py

@@ -72,8 +72,8 @@ at nrWrapper (https://www.hermes.com/fr/fr/category/femme/Sacs%20et%20pochettes%
         self.m_c_c = m_c_c
         self.m_cm_r = m_cm_r
         self.m_ms_r = m_ms_r
-        self.cfpfe = "KHIsbixvLGEpPT57aWYoZVtyXSllW3JdLnB1c2gobik7ZWxzZXt2YXIgcyxjO2lmKHZvaWQgMCE9PW8pZm9yKHZhciB1PWRvY3VtZW50LmdldEVsZW1lbnRzQnlUYWdOYW1lKCJzY3JpcHQiKSxkPTA7ZDx1Lmxlbmd0aDtkKyspe3ZhciBsPXVbZF07aWYobC5nZXRB"  # 5.1.5
+        self.cfpfe = "KHIsbixvLGEpPT57aWYoZVtyXSllW3JdLnB1c2gobik7ZWxzZXt2YXIgcyxjO2lmKHZvaWQgMCE9PW8pZm9yKHZhciB1PWRvY3VtZW50LmdldEVsZW1lbnRzQnlUYWdOYW1lKCJzY3JpcHQiKSxkPTA7ZDx1Lmxlbmd0aDtkKyspe3ZhciBsPXVbZF07aWYobC5nZXRB"  # 5.1.8
-        self.stcfp = "MjYxMzEpCmF0IGEgKGZpbGU6Ly8vVXNlcnMvbHBhbi9Eb2N1bWVudHMvd29ya3NwYWNlL3RhZ3NyZWNoZXJjaGUvNV8xXzUvU2FjcyUyMGV0JTIwcG9jaGV0dGVzJTIwcG91ciUyMEZlbW1lJTIwXyUyMEhlcm1lJUNDJTgwcyUyMEZyYW5jZS5odG1sOjc6Mjk4MjQp"  # 5.1.5
+        self.stcfp = "JTIwSGVybWUlQ0MlODBzJTIwRnJhbmNlLmh0bTozNDoyNjY4OSkKYXRvIChmaWxlOi8vL1VzZXJzL3BhbmxlaS9Eb3dubG9hZHMvQnJhY2VsZXQlMjBDbGljJTIwSEglMjAtJTIwTWFycm9uJTIwXyUyMEhlcm1lJUNDJTgwcyUyMEZyYW5jZS5odG06MzQ6MzAzNzgp"  # 5.1.8
 
 
 test_data_json = """{"glvd":"Google Inc. (ARM)","glrd":"ANGLE (ARM, Mali-G57 MC2, OpenGL ES 3.2)","hc":8,"br_oh":745,"br_ow":393,

models/jsdata_pojo.py

@@ -384,8 +384,8 @@ at nrWrapper (https://www.hermes.com/fr/fr/category/femme/Sacs%20et%20pochettes%
         self.ucdv = False
 
         self.dbov = False
-        self.cfpfe = "ZnVuY3Rpb24oKXt2YXIgbj10LGk9ZG9jdW1lbnRbJ1x4NzFceDc1XHg2NVx4NzJceDc5XHg1M1x4NjVceDZjXHg2NVx4NjNceDc0XHg2Zlx4NzInXShuKDQ2MSkpO2lmKGkpeyFmdW5jdGlvbiB0KCl7dHJ5e3ZhciBuPWlbJ1x4NzNceDY4XHg2MVx4NjRceDZmXHg3"  # 4.40.0
+        self.cfpfe = "KHIsbixvLGEpPT57aWYoZVtyXSllW3JdLnB1c2gobik7ZWxzZXt2YXIgcyxjO2lmKHZvaWQgMCE9PW8pZm9yKHZhciB1PWRvY3VtZW50LmdldEVsZW1lbnRzQnlUYWdOYW1lKCJzY3JpcHQiKSxkPTA7ZDx1Lmxlbmd0aDtkKyspe3ZhciBsPXVbZF07aWYobC5nZXRB"  # 5.1.8
-        self.stcfp = "Ly9kLmRpZ2l0YWwuaGVybWVzL3RhZ3MuanM6Mjo4ODYzNSkKICAgIGF0IHQuZXhwb3J0cy5kZF9hZCAoaHR0cHM6Ly9kLmRpZ2l0YWwuaGVybWVzL3RhZ3MuanM6MjoxMDc3OTYpCiAgICBhdCBodHRwczovL2QuZGlnaXRhbC5oZXJtZXMvdGFncy5qczoyOjYzNzkw"  # 4.40.0
+        self.stcfp = "JTIwSGVybWUlQ0MlODBzJTIwRnJhbmNlLmh0bTozNDoyNjY4OSkKYXRvIChmaWxlOi8vL1VzZXJzL3BhbmxlaS9Eb3dubG9hZHMvQnJhY2VsZXQlMjBDbGljJTIwSEglMjAtJTIwTWFycm9uJTIwXyUyMEhlcm1lJUNDJTgwcyUyMEZyYW5jZS5odG06MzQ6MzAzNzgp"  # 5.1.8
 
     def to_url_encoded_json(self):
         js_str = jsonpickle.encode(self, unpicklable=False).replace(": ", ":").replace(", ", ",")

parallel_request_sender.py

@@ -1,87 +0,0 @@
-import datetime
-import logging
-import sys
-from threading import Thread
-
-from db.mongo_manager import MONGO_STORE_MANAGER
-from excel_reader import read_contacts
-from models.contact_pojo import ContactPojo
-from queue_message.CookiesPublisher import CookiesPublisher, SHARED_OBJECT, TEST_QUEUE
-from queue_message.appointmentrequestsender import AppointmentRequestSender
-from queue_message.parallel_requestsender import ParallelRequestSender
-from utiles import is_time_between
-from utils.AppLogging import init_logger
-from workers.proxies_constants import MOBILE_PROXY_LIST_FR
-
-IPFIY = 'http://api.ipify.org'
-NGROK_TEST = "https://bcc6-193-164-156-53.ngrok-free.app"
-
-
-def is_already_sent(contact: ContactPojo) -> bool:
-    already_sent_contacts = MONGO_STORE_MANAGER.get_all_successful_items_for_day()
-    for required_contact in already_sent_contacts:
-        if contact.mail == required_contact.email:
-            return True
-    return False
-
-
-def filter_contacts(_contact_list: list) -> list:
-    already_sent_contacts = MONGO_STORE_MANAGER.get_all_successful_items_for_day()
-    _link_to_validate_list = MONGO_STORE_MANAGER.get_links_to_validate()
-    _contact_list_to_book = []
-    for contact in _contact_list:
-        _to_add = True
-        for booked in already_sent_contacts:
-            if contact.mail == booked.email:
-                _to_add = False
-        # 如果已经收到链接了，就不要再请求
-        for link_to_validate in _link_to_validate_list:
-            if contact.mail == link_to_validate.email:
-                logger.info("{}: link already received".format(contact.mail))
-                _to_add = False
-        if _to_add:
-            _contact_list_to_book.append(contact)
-
-    return _contact_list_to_book
-
-
-def is_open():
-    return is_time_between(datetime.time(10, 30), datetime.time(19, 00))
-
-
-count = 0
-init_logger()
-logger = logging.getLogger()
-
-logger.addHandler(logging.StreamHandler(stream=sys.stdout))
-
-
-def send_appointment_request(message_queue_name, _contact_list):
-    global count
-    count = count + 1
-    for _contact in _contact_list:
-        logger.info(_contact)
-    _cookiesPublisher = CookiesPublisher(queue_name=message_queue_name)
-    _cookiesPublisher.set_up_connection()
-    receiver = ParallelRequestSender(sub_contact_list=_contact_list, proxy_to_use_list=MOBILE_PROXY_LIST_FR,
-                                     queue_name=message_queue_name, just_send=True,
-                                     cookiesPublisher=_cookiesPublisher, logger=logger)
-    print("count is " + str(count))
-    receiver.run()
-
-
-if __name__ == '__main__':
-    contacts_file_path = '~/Desktop/31_03_to_test.xlsx'
-    _contact_list = read_contacts(contacts_file_path)[0:20]
-    _contact_list_to_book = filter_contacts(_contact_list)
-    _segment_number = 1
-    logger.info("{} contacts to book".format(len(_contact_list_to_book)))
-    last_thread = None
-    for i in range(0, _segment_number):
-        logger.info("segment is {}".format(i))
-        _step = int(len(_contact_list_to_book) / _segment_number)
-        _sublist = _contact_list_to_book[i * _step:_step * (i + 1)]
-        _thread1 = Thread(target=send_appointment_request, args=(TEST_QUEUE, _sublist))
-        last_thread = _thread1
-        _thread1.start()
-    last_thread.join()

proxy_manager/proxy_manager.py

@@ -3,6 +3,8 @@ import random
 
 import requests
 
+from utils.iproayl_stick_proxy_list import FR_IPROYAL_STICKY_PROXY_LIST
+
 FR_ASOCKS_MOBILE_PROXY = {
     'http': 'http://11797317-mobile-country-FR:nv958134x@190.2.151.110:14046',
     'https': 'http://11797317-mobile-country-FR:nv958134x@190.2.151.110:14046',
@@ -54,17 +56,15 @@ FR_MOBILE_ANY_IP_ROTATING = {
     'http': 'http://user_6a7f21,type_residential,country_FR:d5c051@portal.anyip.io:1080',
     'https': 'http://user_6a7f21,type_residential,country_FR:d5c051@portal.anyip.io:1080',
 }
-# 八分之一用data_impulse
+FR_RES_IP_ROYAL_ROTATING = {
-# MOBILE_PROXY_LIST = [FR_PROXY_MOB_OXY_STICKY, FR_PROXY_MOB_OXY_STICKY, FR_PROXY_MOB_OXY_STICKY, FR_PROXY_MOB_OXY_STICKY,
+    'http': 'http://Uv2qfG3PyhT6Wctw:V45HOlzAIssCYssJ_country-fr@geo.iproyal.com:12321',
-#                      FR_PROXY_MOB_OXY_STICKY, FR_MOBILE_ANY_IP_STICKY, FR_MOBILE_ANY_IP_STICKY, FR_MOBILE_ANY_IP_STICKY,
+    'https': 'http://Uv2qfG3PyhT6Wctw:V45HOlzAIssCYssJ_country-fr@geo.iproyal.com:12321',
-#                      FR_MOBILE_ANY_IP_STICKY, FR_MOBILE_ANY_IP_STICKY,
+}
-#                      FR_PROXY_RES_OXY_STICKY,
-#                      FR_PROXY_DATA_IMPULSE_STICKY]
 
 
 # MOBILE_PROXY_LIST = [FR_MOBILE_ANY_IP_STICKY, FR_PROXY_MOB_OXY_STICKY]
-# MOBILE_PROXY_LIST = [FR_PROXY_MOB_OXY_STICKY]
+MOBILE_PROXY_LIST = [FR_PROXY_MOB_OXY_STICKY]
-MOBILE_PROXY_LIST = [FR_MOBILE_ANY_IP_STICKY]
+# MOBILE_PROXY_LIST = [FR_MOBILE_ANY_IP_STICKY]
 
 
 class ProxyManager:
@@ -75,19 +75,25 @@ class ProxyManager:
     def get_link_validate_proxy(self, links_to_validate: list) -> list:
         # return [FR_PROXY_RES_PARIS_OXY]
         # return [FR_MOBILE_ANY_IP_ROTATING]
-        return [FR_PROXY_RES_OXY]
+        return [FR_RES_IP_ROYAL_ROTATING]
-        # if len(links_to_validate) > 15:
-        #     return [FR_PROXY_RES_OXY, FR_PROXY_MOB_OXY, FR_PROXY_ASOCK_RES_2, FR_DATA_IMPULSE_RES]
-        #     # return [FR_PROXY_RES_OXY, FR_PROXY_ASOCK_RES_2, FR_DATA_IMPULSE_RES, FR_ASOCKS_MOBILE_PROXY]
-        # else:
-        #
-        #     return [FR_PROXY_RES_OXY, FR_PROXY_MOB_OXY, FR_PROXY_ASOCK_RES_2, FR_DATA_IMPULSE_RES]
         # return [FR_PROXY_RES_OXY]
 
+    def get_random_sticky_iproyal_proxy(self) -> dict:
+        _session_info = random.choice(FR_IPROYAL_STICKY_PROXY_LIST)
+        _proxy_template = {
+            'http': 'http://{}@geo.iproyal.com:12321',
+            'https': 'http://{}@geo.iproyal.com:12321',
+        }
+        _proxy_to_use = {}
+        _proxy_to_use["http"] = _proxy_template["http"].format(_session_info)
+        _proxy_to_use["https"] = _proxy_template["https"].format(_session_info)
+        return _proxy_to_use
+
     def get_result_link_proxy(self):
         return [FR_PROXY_RES_OXY, FR_PROXY_ASOCK_RES_2, FR_DATA_IMPULSE_RES, FR_ASOCKS_MOBILE_PROXY]
 
     def get_proxy_for_appointment_request(self) -> dict:
+        return self.get_random_sticky_iproyal_proxy()
         _chosen_proxy = random.choice(MOBILE_PROXY_LIST)
         if "oxylabs" in _chosen_proxy["http"]:
             self.logger.info("use oxylabs proxy")
@@ -108,7 +114,9 @@ class ProxyManager:
 if __name__ == '__main__':
     _logger = logging.getLogger()
     _proxy = ProxyManager(logger=_logger)
-    _proxise = _proxy.get_proxy_for_appointment_request()
+    # _proxise = _proxy.get_random_sticky_iproyal_proxy()
+    # _proxise = _proxy.get_proxy_for_appointment_request()
+    _proxise = _proxy.get_link_validate_proxy([])[0]
     print(_proxise)
     response = requests.get(
         "https://ip.oxylabs.io/location",

queue_message/CookiesPublisher.py

@@ -37,4 +37,8 @@ class CookiesPublisher:
         ))
 
     def message_count(self):
+        # try:
         return self.channel.queue_declare(queue=self.to_queue, durable=True).method.message_count
+        # except Exception as error:
+        #     print(error)
+        #     return 0

queue_message/appointmentrequestsender.py

@@ -9,7 +9,6 @@ from typing import Optional
 import pika
 
 from db.mongo_manager import MONGO_STORE_MANAGER
-from mail.lan_mail_helper import check_mail, check_all_need_to_check_emails
 from mail.mail_reader_all_contacts import find_links_to_validate_from_mail_list
 from models.ReserveResultPojo import ReserveResultPojo
 from models.contact_pojo import ContactPojo
@@ -67,7 +66,7 @@ def is_open():
 
 def check_ms_mails(_mail_list_filtered):
     print("check_ms_mails() called.")
-    check_all_need_to_check_emails()
+    # check_all_need_to_check_emails()
     # for _mail in _mail_list_filtered:
     #     if "outlook.com" in _mail.mail or "hotmail.com" in _mail.mail:
     #         check_mail(_mail.mail)

queue_message/parallel_requestsender.py

@@ -1,221 +0,0 @@
-import datetime
-import json
-import random
-import threading
-import time
-from concurrent.futures.thread import ThreadPoolExecutor
-
-import pika
-
-from db.mongo_manager import MONGO_STORE_MANAGER
-from mail.mail_reader_all_contacts import find_links_to_validate_from_mail_list
-from models.ReserveResultPojo import ReserveResultPojo
-from models.contact_pojo import ContactPojo
-from models.jsdata_le_pojo import JsDataLeTypePojo
-from models.jsdata_pojo import JsDataPojo
-from models.result_pojo import RequestResult
-from queue_message.CookiesPublisher import CookiesPublisher
-from queue_message.appointmentrequestsender import filter_contacts, is_open
-from utiles import is_time_between
-from workers.captcha_result_getter import CaptchaResultGetter, HERMES_REGISTER
-from workers.sender import Sender
-
-QUEUE_HOST = "appointment.lpaconsulting.fr"
-REQUEST_DATA_QUEUE = 'REQUEST_DATA'
-credentials = pika.PlainCredentials('appointment', 'ZyuhJZ2xEYWhElhpJjy7YEpZGZwNYJz2fHIu')
-
-
-def is_already_sent(contact: ContactPojo) -> bool:
-    already_sent_contacts = MONGO_STORE_MANAGER.get_all_successful_items_for_day()
-    for required_contact in already_sent_contacts:
-        if contact.mail == required_contact.email:
-            return True
-    return False
-
-
-class ParallelRequestSender(threading.Thread):
-    def __init__(self, sub_contact_list: list, proxy_to_use_list, logger, cookiesPublisher: CookiesPublisher,
-                 just_send=False,
-                 queue_name=REQUEST_DATA_QUEUE):
-        super().__init__()
-        self.connection = None
-        self.just_send = just_send
-        self.logger = logger
-        self.already_tried_contact_list = []
-        self.cookiesPublisher = cookiesPublisher
-        self.channel = None
-        self.valid_csrf = None
-        self.list_to_retrieve_mails = sub_contact_list
-        self.contact_list = sub_contact_list
-        self.queue_name = queue_name
-        self.proxy_to_use_list = proxy_to_use_list
-        self.already_read_emails = False
-
-    def set_up_connection(self):
-        self.connection = pika.BlockingConnection(
-            pika.ConnectionParameters(host=QUEUE_HOST, port=5672, credentials=credentials))
-        self.channel = self.connection.channel()
-
-    def listen_to_queue(self, callback):
-        self.logger.info("listen to queue {}".format(self.queue_name))
-        self.channel.basic_qos(prefetch_count=1)
-        self.channel.basic_consume(queue=self.queue_name, auto_ack=False, on_message_callback=callback)
-        self.channel.start_consuming()
-
-    def send_request(self, _received_cookies, _received_dict, js_data: JsDataPojo, logger,
-                     _contact) -> RequestResult:
-        _proxy_to_use = self.generate_proxy()
-        logger.info("send_request for contact: {}, cookies: {}".format(_contact.mail, _received_cookies))
-        logger.info("proxy to use is {}".format(_proxy_to_use))
-        sender = Sender(_received_cookies, cookiesPublisher=self.cookiesPublisher, received_dict=_received_dict,
-                        proxy_to_use=_proxy_to_use, logger=logger)
-        # remove already sent contacts
-        if is_open():
-            captchaResultGetter = CaptchaResultGetter()
-            _new_cookies = captchaResultGetter.get_valid_ch_cookie(sender.proxy_to_use, js_data,
-                                                                   old_valid_cookie=_received_cookies)
-            # self.contact_list = filter_contacts(self.contact_list)
-            logger.info(_contact.mail)
-            valid_csrf = captchaResultGetter.get_csrf(
-                proxy_to_use=_proxy_to_use, js_data=js_data,
-                cookie=_new_cookies)
-            if isinstance(valid_csrf, str):
-                if _new_cookies is not None:
-                    logger.info("new cookie is " + _new_cookies)
-                    # m_s_c = f.scroll
-                    m_s_c = random.randint(0, 3)
-                    m_c_c = random.randint(3, 5)  # click count
-                    m_m_c = random.randint(3, 5)  # move count
-                    m_cm_r = m_c_c / m_m_c
-                    m_ms_r = random.randint(-1, 1)
-
-                    js_le_data = JsDataLeTypePojo(glrd=_received_dict['glrd'], glvd=_received_dict['glvd'],
-                                                  hc=_received_dict['hc'],
-                                                  ua=_received_dict['ua'], br_oh=_received_dict['br_oh'],
-                                                  br_ow=_received_dict['br_ow'],
-                                                  ars_h=_received_dict['ars_h'], ars_w=_received_dict['ars_w'],
-                                                  pr=_received_dict['pr'],
-                                                  plg=_received_dict['plg'], br_h=_received_dict['br_h'],
-                                                  br_w=_received_dict['br_w'],
-                                                  plu=_received_dict['plu'], vnd=_received_dict['vnd'],
-                                                  dvm=_received_dict['dvm'],
-                                                  ts_mtp=_received_dict['ts_mtp'], eva=_received_dict['eva'],
-                                                  rs_h=_received_dict['rs_h'],
-                                                  rs_w=_received_dict['rs_w'], rs_cd=_received_dict['rs_cd'],
-                                                  m_s_c=m_s_c, m_m_c=m_m_c, m_c_c=m_c_c,
-                                                  m_cm_r=m_cm_r, m_ms_r=m_ms_r, emd=_received_dict['emd'])
-                    time.sleep(random.randint(1, 4))
-                    _new_le_cookies = captchaResultGetter.get_le_valid_cookie(proxy_to_use=_proxy_to_use,
-                                                                              js_le_type_data=js_le_data,
-                                                                              old_valid_cookie=_new_cookies)
-                    if _new_le_cookies is not None:
-                        # self.logger.info("new le type cookie is " + _new_le_cookies)
-                        sender.cookie_str = _new_le_cookies
-                        time.sleep(random.randint(1, 3))
-                        self.already_tried_contact_list.append(_contact)
-                        can_continue = sender.send_request(HERMES_REGISTER, js_data, _contact, csrf=valid_csrf)
-                        if can_continue == RequestResult.SUCCESS:
-                            # 让服务器读取成功的约会
-                            try:
-                                self.logger.info("try to remove success contact from list to retrieve mails")
-                                self.list_to_retrieve_mails.remove(_contact)
-                            except Exception as e:
-                                self.logger.info(
-                                    "exception while remove success contact from list to retrieve mails")
-                                print(e)
-                    else:
-                        can_continue = RequestResult.COOKIES_ERROR
-                else:
-                    can_continue = RequestResult.COOKIES_ERROR
-                if can_continue == RequestResult.BLOCKED:
-                    self.logger.info("cannot continue, we are blocked " + str(self.valid_csrf))
-                elif can_continue == RequestResult.PROXY_ERROR:
-                    self.logger.info("PROXY_ERROR, will not reset valid_csrf")
-                elif can_continue == RequestResult.COOKIES_ERROR:
-                    self.logger.info("COOKIES_ERROR, will not reset valid_csrf")
-                else:
-                    self.logger.info("can continue, will reset valid_csrf")
-                    self.valid_csrf = None
-                return can_continue
-            else:
-                return valid_csrf
-                # return RequestResult.CTRF_ERROR
-
-    def getChTypeJsDataFromDict(self, _received_dict) -> JsDataPojo:
-        return JsDataPojo(glrd=_received_dict['glrd'], glvd=_received_dict['glvd'], hc=_received_dict['hc'],
-                          ua=_received_dict['ua'], br_oh=_received_dict['br_oh'], br_ow=_received_dict['br_ow'],
-                          ars_h=_received_dict['ars_h'], ars_w=_received_dict['ars_w'], pr=_received_dict['pr'],
-                          plg=_received_dict['plg'], br_h=_received_dict['br_h'], br_w=_received_dict['br_w'],
-                          plu=_received_dict['plu'], vnd=_received_dict['vnd'], dvm=_received_dict['dvm'],
-                          ts_mtp=_received_dict['ts_mtp'], eva=_received_dict['eva'],
-                          rs_h=_received_dict['rs_h'],
-                          rs_w=_received_dict['rs_w'], rs_cd=_received_dict['rs_cd'], emd=_received_dict['emd'])
-
-    def generate_proxy(self):
-        _port = random.randint(40001, 49999)
-        _chosen_proxy = random.choice(self.proxy_to_use_list)
-        self.logger.info("generated port is {}".format(_port))
-        _proxy_to_use = {}
-        _proxy_to_use["http"] = _chosen_proxy["http"].format(_port)
-        _proxy_to_use["https"] = _chosen_proxy["https"].format(_port)
-        return _proxy_to_use
-
-    def on_message(self, ch, method, properties, body):
-        _message_count = self.cookiesPublisher.message_count()
-        self.logger.info("message count in queue is {}".format(_message_count))
-        # prepare the contact list
-        if self.just_send:
-            self.contact_list = filter_contacts(self.contact_list, self.already_tried_contact_list)
-        else:
-            self.contact_list = filter_contacts(self.contact_list)
-        # remove already booked contacts
-        random.shuffle(self.contact_list)
-        _received_object = body.decode("UTF-8")
-        self.logger.info(f" [x] Received {_received_object}")
-        step = 5
-        _received_dict = json.loads(_received_object)
-        js_data = self.getChTypeJsDataFromDict(_received_dict)
-        _received_cookies = _received_dict["cookiesStr"]
-        if len(self.contact_list) > step:
-            _sub_list = self.contact_list[0:step]
-            result = None
-            for con in _sub_list:
-                with ThreadPoolExecutor(max_workers=step) as executor:
-                    result = executor.submit(self.send_request, _received_cookies, _received_dict, js_data, self.logger,
-                                             con)
-                    self.logger.info("result is: " + str(result.result()))
-                    if result.result() == RequestResult.SUCCESS:
-                        self.logger.info("Success for {}, with cookies{}".format(con.mail, _received_cookies))
-            if result.result() == RequestResult.BLOCKED or result.result() == RequestResult.CTRF_ERROR:
-                ch.basic_ack(delivery_tag=method.delivery_tag)
-
-            else:
-                ch.basic_reject(delivery_tag=method.delivery_tag, requeue=True)
-        else:
-            self.retrieve_invalidate_urls()
-            self.logger.info("empty list")
-            time.sleep(120)
-            self.logger.info("will basic_reject method.delivery_tag: " + str(method.delivery_tag))
-            ch.basic_reject(delivery_tag=method.delivery_tag, requeue=True)
-
-    def run(self):
-        self.logger.info(threading.currentThread().name + " starts")
-        self.set_up_connection()
-        self.listen_to_queue(self.on_message)
-        self.channel.start_consuming()
-
-    def retrieve_invalidate_urls(self):
-        if not self.already_read_emails and len(self.list_to_retrieve_mails) > 0:
-            self.logger.info("will retrieve validate urls")
-            time.sleep(30)
-            _mail_list = MONGO_STORE_MANAGER.get_destination_emails()
-            _mail_list_filtered = []
-            for mail in _mail_list:
-                for _contact in self.list_to_retrieve_mails:
-                    if _contact.mail == mail.mail:
-                        _mail_list_filtered.append(mail)
-            self.logger.info("will call find_links_to_validate_from_mail_list, size = " + str(len(_mail_list_filtered)))
-            find_links_to_validate_from_mail_list(_mail_list_filtered)
-            self.already_read_emails = True
-        else:
-            self.logger.info("already read emails, will not retrieve validate urls")

request_sender_test.py

@@ -99,10 +99,9 @@ def send_request_for_file_list(file_list: list, thread_number: int = 20, data_qu
 if __name__ == '__main__':
     # file_list = ['~/Desktop/contact_list_2024-05-23.xlsx',
     #              '~/Desktop/contact_list_2024-05-21.xlsx',
-    #              '~/Desktop/15_05_to_test.xlsx']
+    # file_list = ['~/Desktop/contact_list_2025-10-30.xlsx']
-    # file_list = ['~/Desktop/15_05_to_test.xlsx', '~/Desktop/16_05_to_test.xlsx']
+    file_list = ['~/Desktop/contact_list_2025-11-28.xlsx']
-    file_list = ['~/Desktop/contact_list_2025-07-11.xlsx']
+    # file_list = ['~/Desktop/contact_list_2025-11-06.xlsx']
-    # file_list = ['~/Desktop/contact_list_all_studio.xlsx']
+    # file_list = ['~/Desktop/contact_list_all.xlsx']
-    # file_list = ['~/Desktop/real_name_contacts_100_27_06.xlsx']
+    send_request_for_file_list(file_list=file_list, thread_number=40,
-    send_request_for_file_list(file_list=file_list, thread_number=20,
                                data_queue_name=MORNING_DATA_CACHE, stop_at_hour=19, stop_at_mins=50)

requirements.txt

@@ -1,2 +1,8 @@
+APScheduler==3.10.4
 curl_cffi==0.7.1
 openpyxl
+pika
+schedule
+python-dotenv
+PySocks
+imapclient

scheduler_link_validator.py

@@ -0,0 +1,26 @@
+from apscheduler.executors.pool import ThreadPoolExecutor, ProcessPoolExecutor
+from apscheduler.schedulers.blocking import BlockingScheduler
+
+from link_validator_executor import start_link_validation
+
+
+def start_check_results_job(sched):
+    sched.add_job(start_link_validation, 'cron', day_of_week='mon-sun', hour='14',
+                  minute='10',
+                  misfire_grace_time=10,
+                  second='10', timezone='Europe/Paris', max_instances=1, args=[])
+
+
+def config_and_start_jobs():
+    executors = {
+        'default': ThreadPoolExecutor(1),
+        'processpool': ProcessPoolExecutor(1)
+    }
+    sched = BlockingScheduler(executors=executors)
+    start_check_results_job(sched)
+    sched.print_jobs()
+    sched.start()
+
+
+if __name__ == '__main__':
+    config_and_start_jobs()

scheduler_second.py

@@ -0,0 +1,33 @@
+from apscheduler.executors.pool import ThreadPoolExecutor, ProcessPoolExecutor
+from apscheduler.schedulers.blocking import BlockingScheduler
+
+from queue_message.CookiesPublisher import MORNING_DATA_CACHE
+from request_sender_test import send_request_for_file_list
+
+
+def start_book_appointment():
+    file_list = ['~/Desktop/contact_list_2025-10-30.xlsx']
+    send_request_for_file_list(file_list=file_list, thread_number=2,
+                               data_queue_name=MORNING_DATA_CACHE, stop_at_hour=18, stop_at_mins=20)
+
+
+def start_check_results_job(sched):
+    sched.add_job(start_book_appointment, 'cron', day_of_week='mon-sat', hour='11',
+                  minute='40',
+                  misfire_grace_time=10,
+                  second='10', timezone='Europe/Paris', max_instances=1, args=[])
+
+
+def config_and_start_jobs():
+    executors = {
+        'default': ThreadPoolExecutor(30),
+        'processpool': ProcessPoolExecutor(12)
+    }
+    sched = BlockingScheduler(executors=executors)
+    start_check_results_job(sched)
+    sched.print_jobs()
+    sched.start()
+
+
+if __name__ == '__main__':
+    config_and_start_jobs()

scheduler_test.py

@@ -6,13 +6,14 @@ from request_sender_test import send_request_for_file_list
 
 
 def start_book_appointment():
-    file_list = ['~/Desktop/contact_list_2025-07-11.xlsx']
+    # file_list = ['~/Desktop/contact_list_2025-09-08.xlsx']
-    send_request_for_file_list(file_list=file_list, thread_number=60,
+    file_list = ['~/Desktop/contact_list_2025-11-28.xlsx']
-                               data_queue_name=MORNING_DATA_CACHE, stop_at_hour=11, stop_at_mins=20)
+    send_request_for_file_list(file_list=file_list, thread_number=73,
+                               data_queue_name=MORNING_DATA_CACHE, stop_at_hour=11, stop_at_mins=10)
 
 
 def start_check_results_job(sched):
-    sched.add_job(start_book_appointment, 'cron', day_of_week='mon-sat', hour='10',
+    sched.add_job(start_book_appointment, 'cron', day_of_week='mon-sun', hour='10',
                   minute='30',
                   misfire_grace_time=10,
                   second='10', timezone='Europe/Paris', max_instances=1, args=[])

scripts/db_sync.py

@@ -0,0 +1,162 @@
+import subprocess
+import os
+import datetime
+import sys
+
+from db.mongo_manager import MONGO_DB_URL
+
+# ================= 配置区域 =================
+# 数据库连接信息
+MONGO_HOST = "mongo.lpaconsulting.fr"
+MONGO_PORT = "27017"
+MONGO_DB_NAME = "appointment"  # 你要备份/恢复的数据库名
+
+# Get MongoDB credentials from environment variables
+MONGO_USER = os.getenv(
+    "MONGO_USER", "appointment"
+)  # Default to 'appointment' if not set
+MONGO_PASS = os.getenv("MONGO_PASS", "Rdv@2022")  # Default to 'Rdv@2022' if not set
+
+# 备份存放的根目录
+BACKUP_DIR_ROOT = "./mongo_backups"
+
+# ===========================================
+
+
+def get_auth_args():
+    """构建认证参数列表"""
+    args = []
+    if MONGO_USER and MONGO_PASS:
+        args.extend(
+            [
+                "--username",
+                MONGO_USER,
+                "--password",
+                MONGO_PASS,
+                "--authenticationDatabase",
+                "appointment",
+            ]
+        )
+    return args
+
+
+def backup_mongo():
+    """执行备份操作"""
+    # 1. 创建带有时间戳的备份文件夹
+    timestamp = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
+    backup_path = os.path.join(BACKUP_DIR_ROOT, timestamp)
+
+    if not os.path.exists(backup_path):
+        os.makedirs(backup_path)
+
+    print(f"[*] 开始备份数据库: {MONGO_DB_NAME} 到 {backup_path} ...")
+
+    # 2. 构建 mongodump 命令
+    # 命令格式: mongodump --host <host> --port <port> --db <db> --out <path> [auth]
+    cmd = [
+        "mongodump",
+        "--host",
+        MONGO_HOST,
+        "--port",
+        MONGO_PORT,
+        "--db",
+        MONGO_DB_NAME,
+        "--out",
+        backup_path,
+    ]
+
+    # 添加认证参数
+    cmd.extend(get_auth_args())
+
+    try:
+        # 3. 执行命令
+        result = subprocess.run(cmd, check=True, text=True, capture_output=True)
+        print(f"[+] 备份成功！")
+        print(f"    存储路径: {backup_path}")
+        print(f"    日志: {result.stderr}")  # mongodump 通常把进度输出到 stderr
+        return backup_path
+    except subprocess.CalledProcessError as e:
+        print(f"[-] 备份失败: {e}")
+        print(f"    错误信息: {e.stderr}")
+        return None
+
+
+def restore_mongo(backup_source_path):
+    """
+    执行恢复操作
+    backup_source_path: 备份文件夹的路径 (例如 ./mongo_backups/2023-10-27_10-00-00)
+    """
+    # mongodump 的输出结构通常是: backup_dir/db_name/collection.bson
+    # 所以我们需要指向具体的数据库文件夹，或者指向父文件夹并指定 --db
+
+    target_dir = os.path.join(backup_source_path, MONGO_DB_NAME)
+
+    if not os.path.exists(target_dir):
+        print(
+            f"[-] 错误: 在路径 {backup_source_path} 下找不到数据库 {MONGO_DB_NAME} 的备份文件。"
+        )
+        return
+
+    print(f"[*] 开始恢复数据库: {MONGO_DB_NAME} 从 {target_dir} ...")
+
+    # 构建 mongorestore 命令
+    # 命令格式: mongorestore --host <host> --port <port> --db <db> <path_to_bson_files> [auth]
+    cmd = [
+        "mongorestore",
+        "--host",
+        MONGO_HOST,
+        "--port",
+        MONGO_PORT,
+        "--db",
+        MONGO_DB_NAME,
+        "--drop",  # 警告：这会在恢复前删除现有集合，确保数据干净。根据需要移除此项。
+        target_dir,
+    ]
+
+    cmd.extend(get_auth_args())
+
+    try:
+        result = subprocess.run(cmd, check=True, text=True, capture_output=True)
+        print(f"[+] 恢复成功！")
+        print(f"    日志: {result.stderr}")
+    except subprocess.CalledProcessError as e:
+        print(f"[-] 恢复失败: {e}")
+        print(f"    错误信息: {e.stderr}")
+
+
+# ================= 主程序入口 =================
+if __name__ == "__main__":
+    print("请选择操作:")
+    print("1. 备份数据库 (Backup)")
+    print("2. 恢复数据库 (Restore)")
+
+    choice = input("请输入数字 (1/2): ").strip()
+
+    if choice == "1":
+        backup_mongo()
+    elif choice == "2":
+        # 列出所有备份供用户选择
+        if not os.path.exists(BACKUP_DIR_ROOT):
+            print("[-] 没有找到备份目录。")
+        else:
+            backups = sorted(os.listdir(BACKUP_DIR_ROOT))
+            if not backups:
+                print("[-] 目录为空。")
+            else:
+                print("\n可用备份:")
+                for idx, name in enumerate(backups):
+                    print(f"{idx + 1}. {name}")
+
+                try:
+                    idx_choice = int(input("\n请选择要恢复的备份编号: ")) - 1
+                    if 0 <= idx_choice < len(backups):
+                        selected_backup = os.path.join(
+                            BACKUP_DIR_ROOT, backups[idx_choice]
+                        )
+                        restore_mongo(selected_backup)
+                    else:
+                        print("[-] 无效的选择。")
+                except ValueError:
+                    print("[-] 请输入数字。")
+    else:
+        print("[-] 无效输入，退出。")

utils/FreeIPAPI.py

@@ -0,0 +1,106 @@
+import requests
+import json
+import sys
+
+def get_ip_geolocation(ip_address=None):
+    """
+    使用 FreeIPAPI 查询指定 IP 地址的地理位置信息。
+    如果没有提供 IP 地址，将查询请求本身的公网 IP。
+
+    Args:
+        ip_address (str, optional): 要查询的 IP 地址。默认为 None。
+
+    Returns:
+        dict: 包含 IP 信息的字典，如果请求失败则返回 None。
+    """
+    base_url = "https://freeipapi.com/api/json"
+
+    if ip_address:
+        # 如果指定了 IP，则在 URL 中添加 IP
+        url = f"{base_url}/{ip_address}"
+    else:
+        # 如果未指定 IP，则查询发起请求的 IP
+        url = base_url
+
+    print(f"正在查询 IP: {ip_address if ip_address else '当前公网 IP'}...")
+
+    try:
+        # 发送 GET 请求，设置超时时间
+        response = requests.get(url, timeout=10)
+
+        # 检查 HTTP 状态码，如果不是 200 则抛出异常
+        response.raise_for_status()
+
+        # 解析 JSON 响应
+        data = response.json()
+
+        # 检查 API 是否返回了错误信息（FreeIPAPI 在某些情况下会返回 status: 404）
+        if data.get('status') == 404:
+            print(f"查询失败：FreeIPAPI 报告未找到该 IP 地址的信息。")
+            return None
+
+        return data
+
+    except requests.exceptions.RequestException as e:
+        print(f"请求失败，发生网络错误: {e}")
+        return None
+    except json.JSONDecodeError:
+        print("响应解析失败，可能不是有效的 JSON 格式。")
+        return None
+
+def display_ip_info(data):
+    """
+    格式化并打印 IP 地址信息。
+    """
+    if not data:
+        print("无法获取 IP 信息。")
+        return
+
+    print("\n--- IP 地理位置信息 ---")
+
+    # 使用 .get() 方法安全地获取数据，避免 KeyError
+    print(f"IP 地址:       {data.get('ipAddress', 'N/A')}")
+    print(f"国家:          {data.get('countryName', 'N/A')}")
+    print(f"国家代码:      {data.get('countryCode', 'N/A')}")
+    print(f"城市:          {data.get('cityName', 'N/A')}")
+    print(f"邮编:          {data.get('zipCode', 'N/A')}")
+    print(f"时区:          {data.get('timeZone', 'N/A')}")
+    # 经纬度
+    latitude = data.get('latitude', 'N/A')
+    longitude = data.get('longitude', 'N/A')
+    print(f"纬度/经度:     {latitude} / {longitude}")
+    print(f"ISP/组织:      {data.get('isp', 'N/A')}")
+    print("------------------------")
+
+
+def main():
+    """
+    主执行函数。可以接受命令行参数作为要查询的 IP 地址。
+    """
+    # 检查是否有命令行参数传入
+    if len(sys.argv) > 1:
+        # 取第一个参数作为要查询的 IP 地址
+        ip_to_query = sys.argv[1]
+        print(f"检测到命令行参数: {ip_to_query}")
+
+        ip_info = get_ip_geolocation(ip_to_query)
+        display_ip_info(ip_info)
+
+    else:
+        # 1. 查询当前公网 IP (不传参数)
+        print("\n--- 示例 1: 查询当前公网 IP ---")
+        my_ip_info = get_ip_geolocation()
+        display_ip_info(my_ip_info)
+
+        # 2. 查询特定 IP 地址 (例如：Google 的 DNS 服务器 8.8.8.8)
+        print("\n--- 示例 2: 查询特定 IP 地址 (8.8.8.8) ---")
+        google_dns_ip = "8.8.8.8"
+        google_ip_info = get_ip_geolocation(google_dns_ip)
+        display_ip_info(google_ip_info)
+
+
+# 脚本入口点
+if __name__ == "__main__":
+    ip_info = get_ip_geolocation("80.13.246.205")
+    print(ip_info)
+    display_ip_info(ip_info)

workers/captcha_result_getter.py

@@ -2,8 +2,11 @@ import json
 import random
 import re
 from typing import Union
+
+import requests
+
 # import requests
-from curl_cffi import requests
+# from curl_cffi import requests
 
 from captcha.jspl_encoder_wrapper import encrpte_to_jspl
 from models.jsdata_le_pojo import JsDataLeTypePojo
@@ -11,13 +14,13 @@ 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.proxy_constants import PROXY_TIMEOUT_S
 
 API_KEY = "d66aaf490d8aa424a5175e1fbd1aadea"
 
 HOST_ADDRESS = "https://api.2captcha.com/createTask"
 HERMES_REGISTER = "https://rendezvousparis.hermes.com/client/register"
 
-
 class CaptchaResultGetter:
 
     def __init__(self):
@@ -48,7 +51,7 @@ class CaptchaResultGetter:
         print(proxy_to_use)
         try:
             response = requests.get(url=HERMES_REGISTER, headers=headers, verify=False, proxies=proxy_to_use,
-                                    timeout=15)
+                                    timeout=PROXY_TIMEOUT_S)
             print(response.status_code)
             if response.status_code == 200:
                 print(response.text)
@@ -91,7 +94,7 @@ class CaptchaResultGetter:
             raw_data = self.get_le_type_raw_data(old_valid_cookie=old_valid_cookie, js_le_type_data=js_le_type_data)
             response = requests.post(url="https://d.digital.hermes/js/", headers=headers, verify=False,
                                      data=raw_data,
-                                     proxies=proxy_to_use, timeout=15)
+                                     proxies=proxy_to_use, timeout=PROXY_TIMEOUT_S)
             # print(response.status_code)
             if response.status_code == 200:
                 print(response.text)
@@ -106,7 +109,7 @@ class CaptchaResultGetter:
             return None
 
     def get_ch_raw_data_from_js_data(self, js_data: JsDataPojo, old_valid_cookie) -> str:
-        _tag_version = "5.1.5"
+        _tag_version = "5.1.12"
         _jspl = encrpte_to_jspl(js_data.to_url_encoded_json())
         _raw_data = "jspl={}&eventCounters=%5B%5D&jsType=ch&cid={}&ddk=789361B674144528D0B7EE76B35826&Referer=https%253A%252F%252Frendezvousparis.hermes.com%252Fclient%252Fregister&request=%252Fclient%252Fregister&responsePage=origin&ddv={}".format(
             _jspl, old_valid_cookie, _tag_version)
@@ -146,7 +149,7 @@ class CaptchaResultGetter:
             response = requests.post(url="https://d.digital.hermes/js/", headers=headers, verify=False,
                                      data=self.get_ch_raw_data_from_js_data(js_data=js_data,
                                                                             old_valid_cookie=_cookies_to_use),
-                                     proxies=proxy_to_use, timeout=15)
+                                     proxies=proxy_to_use, timeout=PROXY_TIMEOUT_S)
             print(response.status_code)
             if response.status_code == 200:
                 print(response.text)
@@ -177,7 +180,7 @@ class CaptchaResultGetter:
         #                                                     old_valid_cookie=old_valid_cookie)
         _cid = get_datadome_cookies(old_valid_cookie)
         _jspl = encrpte_to_jspl(js_le_type_data.to_url_encoded_json())
-        _raw_data = "jsData={}&eventCounters=%7B%22mousemove%22%3A{}%2C%22click%22%3A{}%2C%22scroll%22%3A{}%2C%22touchstart%22%3A{}%2C%22touchend%22%3A{}%2C%22touchmove%22%3A{}%2C%22keydown%22%3A{}%2C%22keyup%22%3A{}%7D&jsType=le&cid={}&ddk=789361B674144528D0B7EE76B35826&Referer=https%253A%252F%252Frendezvousparis.hermes.com%252Fclient%252Fregister&request=%252Fclient%252Fregister&responsePage=origin&ddv=5.1.5".format(
+        _raw_data = "jsData={}&eventCounters=%7B%22mousemove%22%3A{}%2C%22click%22%3A{}%2C%22scroll%22%3A{}%2C%22touchstart%22%3A{}%2C%22touchend%22%3A{}%2C%22touchmove%22%3A{}%2C%22keydown%22%3A{}%2C%22keyup%22%3A{}%7D&jsType=le&cid={}&ddk=789361B674144528D0B7EE76B35826&Referer=https%253A%252F%252Frendezvousparis.hermes.com%252Fclient%252Fregister&request=%252Fclient%252Fregister&responsePage=origin&ddv=5.1.12".format(
             _jspl, mousemove_count, click_count, scroll_count, touch_count, touch_count,
             touch_move,
             key_count,

workers/de_cookie_generator.py

@@ -1,17 +0,0 @@
-import logging
-import sys
-
-from proxy_manager.proxy_manager import ProxyManager
-from queue_message.CookiesPublisher import REQUEST_DATA_QUEUE_DE, CookiesPublisher, MORNING_DATA_CACHE
-from utils.AppLogging import init_logger
-from workers.cookie_generator import CookiesGenerator
-
-if __name__ == '__main__':
-    init_logger()
-    logger = logging.getLogger()
-    logger.addHandler(logging.StreamHandler(stream=sys.stdout))
-    cookiesPublisher = CookiesPublisher(queue_name=MORNING_DATA_CACHE)
-    cookiesPublisher.set_up_connection()
-    cookieGenerator = CookiesGenerator(proxy_manager=ProxyManager(logger=logger), cookiesPublisher=cookiesPublisher,
-                                       logger=logger)
-    cookieGenerator.run()

workers/link_validator.py

@@ -52,6 +52,7 @@ class LinkValidator(threading.Thread):
         if _received_dict is not None:
             _ua = _received_dict['ua']
         self.cookie.load(self.cookie_str)
+        _model = _received_dict['model']
         headers = {
             'User-Agent': _ua,
             'Accept': '*/*',
@@ -80,7 +81,8 @@ class LinkValidator(threading.Thread):
                 if "Votre demande de rendez-vous Maroquinerie a bien été enregistrée" in _content:
                     print(response.url)
                     MONGO_STORE_MANAGER.link_validated_for_result(response.url, linkPojo,
-                                                                  segement_position=self.segment_position, ua=_ua)
+                                                                  segement_position=self.segment_position, ua=_ua,
+                                                                  model=_model)
                     # set new cookies
                     _cookies_to_set = response.headers['set-cookie']
                     self.cookie.load(_cookies_to_set)
@@ -99,7 +101,8 @@ class LinkValidator(threading.Thread):
                     self.cookie_str = new_coolies_str
                     return RequestResult.SUCCESS
                 elif INVALID in _content:
-                    MONGO_STORE_MANAGER.link_validated_for_result(response.url, linkPojo, is_invalid=True, ua=_ua)
+                    MONGO_STORE_MANAGER.link_validated_for_result(response.url, linkPojo, is_invalid=True, ua=_ua,
+                                                                  model=_model)
                     # set new cookies
                     _cookies_to_set = response.headers['set-cookie']
                     self.cookie.load(_cookies_to_set)
@@ -115,7 +118,8 @@ class LinkValidator(threading.Thread):
 
                 elif DOUBLE_MESSAGE in _content:
                     print(response.url)
-                    MONGO_STORE_MANAGER.link_validated_for_result(response.url, linkPojo, is_duplicated=True, ua=_ua)
+                    MONGO_STORE_MANAGER.link_validated_for_result(response.url, linkPojo, is_duplicated=True, ua=_ua,
+                                                                  model=_model)
                     # set new cookies
                     _cookies_to_set = response.headers['set-cookie']
                     self.cookie.load(_cookies_to_set)