(20241210) Bug fix for retrieval of one full mail.

utils_v2/mail/mail_parser_v2.py

@@ -100,15 +100,36 @@ def parse_part(
         "contentMainType": part.get_content_maintype(),
         "contentSubType": part.get_content_subtype(),
         "contentCharset": part.get_content_charset(),
+        "contentTransferEncoding": part.get("Content-Transfer-Encoding"),
         "contentDisposition": part.get_content_disposition(),
         "filename": part.get_filename(),
-        "payload": part.get_payload(decode = True)
+        "contentId": part.get("Content-ID"),
+        "payload": part.get_payload(decode = False)
     }
-    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))
+    # We decode various kinds of parts:
+    match part_json["contentTransferEncoding"]:
 
+        # This is just unencoded plaintext:
+        case None: pass
+
+        # Typically see with attachments:
+        case "base64":
+            charset = part_json["contentCharset"] or "utf-8"
+            payload = part_json["payload"]
+            payload = base64.b64decode(payload)
+            part_json["payload"] = payload
+
+        # Typically seen with HTML parts:
+        case "quoted-printable":
+            charset = part_json["contentCharset"] or "utf-8"
+            payload = part_json["payload"].encode(charset)
+            payload = quopri.decodestring(payload)
+            part_json["payload"] = payload.decode(charset)
+
+    # print("PARSED PART:", json.to_string(part_json, default = str))
+
+    # Done here;
     return part_json
 
 
@@ -138,35 +159,8 @@ def parse(raw_mail: str | bytes) -> Dict[str, Any]:
     # Iterate through each part of the mail for multipart mails:
     if parsed_mail.is_multipart():
         for part in parsed_mail.walk():
-            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[]
+            part_json = parse_part(part)
+            if part_json["contentDisposition"] in ["inline", "attachment"]: attachments.append()
 
     # When the mails are not multipart, just plaintext:
     else: print("PLAINTEXT PART:", parsed_mail.get_payload())