fix bmo parser for new format / lints

.pre-commit-config.yaml

@@ -1,14 +1,14 @@
 # .pre-commit-config.yaml
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.1.5  # Check for the latest version
+    rev: v0.15.12  # Check for the latest version
     hooks:
       - id: ruff
         args: ["check", "--select", "I", "--fix"]
       - id: ruff-format
 
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0  # Check for the latest version
+    rev: v6.0.0  # Check for the latest version
     hooks:
       - id: check-yaml
       - id: end-of-file-fixer
@@ -16,6 +16,6 @@ repos:
       - id: requirements-txt-fixer
 
   - repo: https://github.com/PyCQA/flake8
-    rev: 6.0.0  # Check for the latest version
+    rev: 7.3.0  # Check for the latest version
     hooks:
       - id: flake8

actual_imap_poll/model.py

@@ -1,5 +1,5 @@
+import datetime
 from dataclasses import dataclass
-from datetime import date
 from decimal import Decimal
 from uuid import UUID
 
@@ -12,7 +12,7 @@ class Transaction:
     """
 
     account: UUID
-    date: date
+    date: datetime.date
     amount: Decimal  # Note: decimal dollars, JS shim will convert to cents as described in the API
     payee: str  # imported_payee in API
     notes: str

actual_imap_poll/parsers.py

@@ -58,6 +58,18 @@ class TransactionParser(ABC):
             raise TransactionParsingFailed("No content of message found")
         return content
 
+    @staticmethod
+    def strip_html(msg: EmailMessage) -> str:
+        body = msg.get_body(preferencelist=("html", "plain"))
+        if body is None:
+            raise TransactionParsingFailed("No HTML body of message found")
+        content = body.get_content()
+        if content is None:
+            raise TransactionParsingFailed("No content of message found")
+
+        soup = BeautifulSoup(content, "html.parser")
+        return soup.get_text()
+
 
 class TransactionParsingFailed(Exception):
     pass
@@ -136,8 +148,8 @@ class MBNAParser(TransactionParser):
 
 class BMOParser(TransactionParser):
     EXTRACT_RE = re.compile(
-        r"We want to let you know that a (withdrawal|deposit) of\s+\$([0-9,]+\.\d{2})\s+has been made (?:to|from) your account ending\s+in\s+(\d{3})",  # noqa: E501
+        r"There was a (withdrawal|deposit).*Amount:\s*\$([0-9,]+\.\d{2}).*Account:\s*Ending in ([0-9]+)",  # noqa: E501
-        flags=re.MULTILINE,
+        flags=re.DOTALL,
     )
 
     def __init__(self, account_map: dict[int, UUID]):
@@ -147,9 +159,8 @@ class BMOParser(TransactionParser):
         return msg["From"] == "bmoalerts@bmo.com"
 
     def extract(self, msg: EmailMessage) -> Optional[Transaction]:
-        content = self.get_content(msg)
+        content = self.strip_html(msg)
-        soup = BeautifulSoup(content, "html.parser")
+        matches = self.EXTRACT_RE.search(content)
-        matches = self.EXTRACT_RE.search(soup.get_text())
         if matches is None:
             raise TransactionParsingFailed("No matches for extraction RE")