(20241210) EMail filter added for listing emails.

utils_v2/mail/mail_parser_v2.py

@@ -60,6 +60,8 @@ from typing import Any, Dict
 import base64
 import quopri
 
+import time
+
 
 #   *****************************************************************************************************************
 #  *****                                                                                                          ****
@@ -88,6 +90,31 @@ import quopri
 #   *****************************************************************************************************************
 
 
+def parse_part(
+        # part: email.message.Message
+        part
+) -> Dict[str, Any]:
+
+    part_json = {
+        "contentType": part.get_content_type(),
+        "contentMainType": part.get_content_maintype(),
+        "contentSubType": part.get_content_subtype(),
+        "contentCharset": part.get_content_charset(),
+        "contentDisposition": part.get_content_disposition(),
+        "filename": part.get_filename(),
+        "payload": part.get_payload(decode = True)
+    }
+    if part_json["contentCharset"] is not None:
+        part_json["payload"] = part_json["payload"].decode(part_json["contentCharset"])
+
+    print("PARSED PART:", json.to_string(part_json, default = str))
+
+    return part_json
+
+
+# ---------------------------------------------------------------------------------------------------------------------
+
+
 def parse(raw_mail: str | bytes) -> Dict[str, Any]:
 
     """
@@ -106,11 +133,40 @@ def parse(raw_mail: str | bytes) -> Dict[str, Any]:
 
     # Make variables:
     parts = []
+    attachments = []
 
     # Iterate through each part of the mail for multipart mails:
     if parsed_mail.is_multipart():
         for part in parsed_mail.walk():
-            print("MULTIPART PART:", part)
+            parse_part(part)
+
+            # # Start by extracting basic details about the part:
+            # part_json = {
+            #     "contentType": part.get("Content-Type"),
+            #     "contentDisposition": part.get("Content-Disposition"),
+            #     "contentTransferEncoding": part.get("Content-Transfer-Encoding"),
+            #     "contentId": part.get("Content-ID"),
+            #     # "part": part.get_payload(decode=True)
+            # }
+            #
+            # # Now check if this part is either plain or HTML text:
+            # content_type = part_json["contentType"].lower()
+            # if (
+            #         content_type.find("text/html") >= 0 or
+            #         content_type.find("text/plain") >= 0
+            # ): parts.append(parse_part(part))
+            #
+            # # print("MULTIPART PART:", json.to_string(part_json, default = str))
+            # # if (
+            # #         isinstance(part_json["part"], bytes) and
+            # #         part_json[""].find()
+            # # ):
+            # #     time.sleep(1.0)
+            # #     try: part_json["part"] = part_json["part"].decode()
+            # #     except: pass
+            # # print("MULTIPART PART:", json.to_string(part_json))
+            # print("\n\n---\n\n")
+            # # if part_json[]
 
     # When the mails are not multipart, just plaintext:
     else: print("PLAINTEXT PART:", parsed_mail.get_payload())
@@ -127,7 +183,7 @@ if __name__ == "__main__":
 
     from utils_v2.system import files
 
-    mail_string_raw = files.read_file(r"/home/developer/Downloads/raw_mail.txt")
+    mail_string_raw = files.read_file(r"/home/developer/Downloads/raw_mail_test.txt")
     parse_results = parse(mail_string_raw)
 
-    print(json.to_string(parse_results, default = str))
+    # print(json.to_string(parse_results, default = str))