(20241127) Google API OAuth2.0 support ready!

utils_v2/mail/mail_parser.py

@@ -24,8 +24,7 @@
         N/A
 
 """
-
-
+import base64
 #   *****************************************************************************************************************
 #  *****                                                                                                          ****
 # ***                                                   IMPORT                                                      ***
@@ -49,6 +48,9 @@ from utils_v2.date_time import date_time
 # To work with mails:
 import mailparser
 
+# To parse the HTML content in the mail:
+from bs4 import BeautifulSoup
+
 # To work with datatypes:
 from typing import Any, Dict
 
@@ -111,6 +113,42 @@ def parse(raw_mail: str | bytes) -> Dict[str, Any]:
         } for attachment in parsed_mail.attachments
     ]
 
+    # Figure out which entity (text and HTML) came in which sequence.
+    # The library doesn't give us any sequence info so we do some custom string processing here to figure out the order
+    # in which to render the contents of the page.
+    parts = [
+        {
+            "no": None,
+            "offset": max(
+                parsed_mail.message_as_string.find(t),
+                parsed_mail.message_as_string.find(base64.b64encode(t.encode()).decode())
+            ),
+            "type": "text/plain",
+            "data": t
+        } for t in parsed_mail.text_plain
+    ]
+    parts = parts + [
+        {
+            "partNo": None,
+            "offset": max(
+                parsed_mail.message_as_string.find(h),
+                parsed_mail.message_as_string.find(base64.b64encode(h.encode()).decode())
+            ),
+            "type": "text/html",
+            "data": h
+        } for h in parsed_mail.text_html
+    ]
+    parts = sorted(parts, key = lambda x: x["offset"])
+    for i, p in enumerate(parts): p["no"] = i
+
+    # Get the unformatted text from everything in the mail:
+    unformatted_text = []
+    for p in parts:
+        if p["type"] == "text/html":
+            html_parser = BeautifulSoup(p["data"], "html.parser")
+            unformatted_text.append(html_parser.get_text())
+        else: unformatted_text.append(p["data"])
+
     # Put everything together:
     return {
         "ts": date_time.to_timezone(parsed_mail.date, timezone = date_time.TIMEZONE_UTC),
@@ -121,6 +159,8 @@ def parse(raw_mail: str | bytes) -> Dict[str, Any]:
         "bcc": [{"name": _[0] or _[1], "email": _[1]} for _ in parsed_mail.headers.get("Bcc", [])],
         "text": parsed_mail.text_plain,
         "html": parsed_mail.text_html,
+        "parts": parts,
+        "unformattedText": "\n".join(unformatted_text),
         "attachments": message_attachments,
     }