Merge pull request #289 from TeamMsgExtractor/next-release

v0.36.3

Author: TheElementalOfDestruction

.github/FUNDING.yml

@@ -1 +1 @@
-custom: ['https://www.buymeacoffee.com/DestructionE']
+custom: ['https://www.buymeacoffee.com/DestructionE', 'https://www.patreon.com/DestructionE']

2022-06-20_1617 Team Msg Extractor I/ContactPicture.jpg

@@ -1,3 +1,7 @@
+**v0.36.3**
+* Added an option to skip the body if it could not be found, rather than throwing an error. This will cause no file to be made for it in the event no valid body exists. For the save functions, this option is `skipBodyNotFound` and from the command line the option is `--skip-body-not-found`.
+* Fixed a bug that caused contacts to save the business phone with two colons instead of 1.
+
 **v0.36.2**
 * [[TeamMsgExtractor #286](https://github.com/TeamMsgExtractor/msg-extractor/issues/286)] Fix missing import.
 

2022-06-20_1617 Team Msg Extractor I/message.txt

@@ -87,6 +87,7 @@ refer to the usage information provided from the program's help dialog:
       --raw                 Sets whether the output should be raw. If this is not possible, will error.
       --rtf                 Sets whether the output should be RTF. If this is not possible, will error.
       --allow-fallback      Tells the program to fallback to a different save type if the selected one is not possible.
+      --skip-body-not-found Skips saving the body if the body cannot be found, rather than throwing an error.
       --zip ZIP             Path to use for saving to a zip file.
       --attachments-only    Specify to only save attachments from an msg file.
       --no-folders          When used with --attachments-only, stores everything in the location specified by --out. Incompatible with --out-name.
@@ -226,8 +227,8 @@ your access to the newest major version of extract-msg.
 .. |License: GPL v3| image:: https://img.shields.io/badge/License-GPLv3-blue.svg
    :target: LICENSE.txt
 
-.. |PyPI3| image:: https://img.shields.io/badge/pypi-0.36.2-blue.svg
-   :target: https://pypi.org/project/extract-msg/0.36.2/
+.. |PyPI3| image:: https://img.shields.io/badge/pypi-0.36.3-blue.svg
+   :target: https://pypi.org/project/extract-msg/0.36.3/
 
 .. |PyPI2| image:: https://img.shields.io/badge/python-3.6+-brightgreen.svg
    :target: https://www.python.org/downloads/release/python-367/

CHANGELOG.md

@@ -27,8 +27,8 @@
 #    along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
 __author__ = 'Destiny Peterson & Matthew Walker'
-__date__ = '2022-08-12'
-__version__ = '0.36.2'
+__date__ = '2022-08-29'
+__version__ = '0.36.3'
 
 import logging
 

README.rst

@@ -67,6 +67,7 @@ def main() -> None:
             'pdf': args.pdf,
             'preparedHtml': args.preparedHtml,
             'rtf': args.rtf,
+            'skipBodyNotFound': args.skipBodyNotFound,
             'skipEmbedded': args.skipEmbedded,
             'skipNotImplemented': args.skipNotImplemented,
             'useMsgFilename': args.useFilename,

extract_msg/__init__.py

@@ -714,7 +714,7 @@ def strListToStr(inp : Union[str, List[str]]):
                 'IM Address': self.instantMessagingAddress,
             },
             '-phone numbers-': {
-                'Business:': self.businessTelephoneNumber,
+                'Business': self.businessTelephoneNumber,
                 'Business 2': strListToStr(self.businessTelephone2Number),
                 'Assistant': self.assistantTelephoneNumber,
                 'Company Main Phone': self.companyMainTelephoneNumber,

extract_msg/__main__.py

@@ -659,6 +659,8 @@ def save(self, **kwargs):
         :param attachmentsOnly: Turns off saving the body and only saves the
             attachments when set.
         :param skipAttachments: Turns off saving attachments.
+        :param skipBodyNotFound: Suppresses errors if no valid body could be
+            found, simply skipping the step of saving the body.
         :param charset: If the html is being prepared, the charset to use for
             the Content-Type meta tag to insert. This exists to ensure that
             something parsing the html can properly determine the encoding (as
@@ -697,6 +699,9 @@ def save(self, **kwargs):
         attachOnly = kwargs.get('attachmentsOnly', False)
         # Track if we are skipping attachments.
         skipAttachments = kwargs.get('skipAttachments', False)
+        # Track if we should skip the body if no valid body is found instead of
+        # raising an exception.
+        skipBodyNotFound = kwargs.get('skipBodyNotFound', False)
 
         if pdf:
             kwargs['preparedHtml'] = True
@@ -810,21 +815,30 @@ def save(self, **kwargs):
                         useHtml = True
                         fext = 'html'
                     elif not allowFallback:
-                        raise DataNotFoundError('Could not find the htmlBody.')
+                        if skipBodyNotFound:
+                            fext = None
+                        else:
+                            raise DataNotFoundError('Could not find the htmlBody.')
 
                 if pdf:
                     if self.htmlBody:
                         usePdf = True
                         fext = 'pdf'
                     elif not allowFallback:
-                        raise DataNotFoundError('Count not find the htmlBody to convert to pdf.')
+                        if skipBodyNotFound:
+                            fext = None
+                        else:
+                            raise DataNotFoundError('Count not find the htmlBody to convert to pdf.')
 
                 if rtf or (html and not useHtml) or (pdf and not usePdf):
                     if self.rtfBody:
                         useRtf = True
                         fext = 'rtf'
                     elif not allowFallback:
-                        raise DataNotFoundError('Could not find the rtfBody.')
+                        if skipBodyNotFound:
+                            fext = None
+                        else:
+                            raise DataNotFoundError('Could not find the rtfBody.')
                     else:
                         # This was the last resort before plain text, so fall
                         # back to that.
@@ -837,10 +851,13 @@ def save(self, **kwargs):
                     # was found but was empty that is considered valid, so we
                     # specifically check against None.
                     if self.body is None:
-                        if allowFallback:
-                            raise DataNotFoundError('Could not find a valid body using current options.')
+                        if skipBodyNotFound:
+                            fext = None
                         else:
-                            raise DataNotFoundError('Plain text body could not be found.')
+                            if allowFallback:
+                                raise DataNotFoundError('Could not find a valid body using current options.')
+                            else:
+                                raise DataNotFoundError('Plain text body could not be found.')
 
 
             if not skipAttachments:
@@ -849,7 +866,7 @@ def save(self, **kwargs):
                 # Remove skipped attachments.
                 attachmentNames = [x for x in attachmentNames if x]
 
-            if not attachOnly:
+            if not attachOnly and fext:
                 with _open(str(path / ('message.' + fext)), mode) as f:
                     if _json:
                         emailObj = json.loads(self.getJson())

extract_msg/contact.py

@@ -8,7 +8,7 @@
 from .exceptions import StandardViolationError
 from .message_base import MessageBase
 from .signed_attachment import SignedAttachment
-from .utils import inputToBytes, inputToString, unwrapMultipart
+from .utils import inputToString, unwrapMultipart
 
 
 logger = logging.getLogger(__name__)