def get_main_content(self, msg: email.message.EmailMessage):
'''
メール本文、フォーマット、キャラクターセットを取得する。
'''
try:
body_part = msg.get_body()
main_content = body_part.get_content()
format_ = body_part.get_content_type()
charset = body_part.get_content_charset()
except Exception as error:
print(error)
main_content = '解析失敗'
format_ = '不明'
charset = '不明'
# get_bodyでエラーになるのは文字コード設定がおかしいメールを受信した場合なので、
# decodeせずにテキスト部分をそのまま返す。
for part in msg.walk():
if part.get_content_type() == 'text/plain':
format_ = part.get_content_type()
main_content = str(part.get_payload())
charset = part.get_content_charset()
return main_content, format_, charset
async def handle_message(self, message: email.message.EmailMessage):
transactional_mail = False
if message.get("Remove-List-Unsubscribe", None):
del message["List-Unsubscribe"]
del message["Remove-List-Unsubscribe"]
transactional_mail = True
del message['X-Peer']
del message['X-MailFrom']
del message['X-RcptTo']
await aiosmtplib.send(message, hostname=SMTP_HOST, port=SMTP_PORT)
if transactional_mail:
log.info(
f'Transactional Mail has been sent to {",".join(message.get_all("to", []))}'
)
else:
log.info(
f'Non-Transactional Mail has been sent to {",".join(message.get_all("to", []))}'
)
if LOG_CONTENT:
for part in message.walk():
# each part is a either non-multipart, or another multipart message
# that contains further parts... Message is organized like a tree
if part.get_content_type() == 'text/plain':
log.info(part.get_payload())
if part.get_content_type() == 'text/html':
log.info(part.get_payload())
def _convert_message_part_to_str(message_part: email.message.EmailMessage) -> Tuple[str, bool]:
content: Union[str, bytes] = message_part.get_content()
content_type = message_part.get_content_type()
content_transfer_encoding = message_part['Content-Transfer-Encoding']
logger_dict = {'ContentType': content_type, 'ContentTransferEncoding': content_transfer_encoding}
if isinstance(content, str):
logger.info('Successfully decoded message part with {ContentType} {ContentTransferEncoding} as string',
fparams=logger_dict)
return content, False
try:
if content_type == 'application/xml':
decoded_content = content.decode()
logger.info('Successfully decoded message part with {ContentType} {ContentTransferEncoding} '
'as a string', fparams=logger_dict)
return decoded_content, False
decoded_content = base64.b64encode(content).decode()
logger.info('Successfully encoded binary message part with {ContentType} {ContentTransferEncoding} as '
'a base64 string', fparams=logger_dict)
return decoded_content, True
except UnicodeDecodeError as e:
logger.error('Failed to decode ebXML message part with {ContentType} {ContentTransferEncoding}.',
fparams=logger_dict)
raise ebxml_envelope.EbXmlParsingError(f'Failed to decode ebXML message part with '
f'Content-Type: {content_type} and '
f'Content-Transfer-Encoding: {content_transfer_encoding}') from e
def _extract_message_parts(msg: email.message.EmailMessage) -> Tuple[str, str, List[Dict[str, Union[str, bool]]]]:
"""Extract the ebXML and payload parts of the message and return them as a tuple.
:param msg: The message to extract parts from.
:return: A tuple containing the ebXML and payload (if present, otherwise None) parts of the message provided.
"""
# EIS section 2.5.4 defines that the first MIME part must contain the ebML SOAP message and the message payload
# (if present) must be the first additional attachment.
if not msg.is_multipart():
logger.error('Non-multipart message received')
raise ebxml_envelope.EbXmlParsingError("Non-multipart message received")
message_parts: Sequence[email.message.EmailMessage] = tuple(msg.iter_parts())
EbxmlRequestEnvelope._report_any_defects_in_message_parts(message_parts)
# ebXML part is the first part of the message
ebxml_part = EbxmlRequestEnvelope._extract_ebxml_part(message_parts[0])
payload_part = None
attachments = []
if len(message_parts) > 1:
# HL7 payload part is the second part of the message
payload_part = EbxmlRequestEnvelope._extract_hl7_payload_part(message_parts[1])
# Any additional attachments are from the third part of the message onwards
attachments.extend(EbxmlRequestEnvelope._extract_additional_attachments_parts(message_parts[2:]))
return ebxml_part, payload_part, attachments
def _get_payload(self, message: email.message.EmailMessage) -> str:
"""
Get the body of the email.
Note: MODIFIES message fetched to be seen.
"""
if message.is_multipart():
return message.get_payload(0).get_payload()
else:
return message.get_payload(0)
def get_attachments(self, msg: email.message.EmailMessage, b_num: bytes):
'''
添付ファイルが存在する場合はファイルに出力し、ファイルパスとファイル名を返す。
ファイルはメール番号のディレクトリに格納する。
'''
files = []
for part in msg.iter_attachments():
try:
filename = part.get_filename()
if not filename:
continue
# メール番号でディレクトリを作成
new_dir = os.path.join('./tmp/{}/'.format(
b_num.decode('utf-8')))
os.makedirs(new_dir, exist_ok=True)
# 添付ファイルを出力
file_path = os.path.join(new_dir, filename)
with open(file_path, 'wb') as fp:
fp.write(part.get_payload(decode=True))
# ファイルパス（絶対パス）とファイル名を保存
abs_path = os.path.abspath(file_path)
files.append({'file_path': abs_path, 'file_name': filename})
except Exception as error:
print(error)
return files
def filter_email(eml: email.message.EmailMessage) -> str:
# Get plaintext part
body = eml.get_body("plain")
if body == None:
raise EmailParseException()
# Find a link in the body
link_re = r"(?i)\b((?:https?://|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’]))"
urls = re.findall(link_re, body.get_content())
if len(urls) == 0:
raise LinkNotFoundException()
url: str = urls[0][0]
# Some sites require this header
headers = {
'Accept' : 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.7) Gecko/2009021910 Firefox/3.0.7'
}
# Download the contents at that URL with urllib
request = urllib.request.Request(url, headers=headers)
with urllib.request.urlopen(request) as response:
webpage = response.read()
# Parse with BeautifulSoup
bs = BeautifulSoup(webpage, features='lxml')
content = bs.prettify()
return content
return url
def get_header_text(self, msg: email.message.EmailMessage):
'''
ヘッダー部をまとめて文字列として返す。
'''
text = ''
for key, value in msg.items():
text = text + '{}: {}\n'.format(key, value)
return text
def _get_body(msg: email.message.EmailMessage) -> Optional[str]:
candidate = None
for part in msg.walk():
if part.get_content_type() == "text/plain" and not part.is_multipart() and part.get(
"Content-Disposition") is None:
if not candidate:
candidate = part.get_payload(decode=True).decode("utf-8")
else:
raise Exception("two possible candidates!")
return candidate
def _store_fault(item: Item, number: int,
mail: email.message.EmailMessage) -> str:
filename = "{0:s}/{1:s}_{2:d}.eml".format(pmlib.config.target_path,
item.name, number)
filename = os.path.abspath(os.path.normpath(filename))
error_text = "Unable to decode mail {0:d} in {1:s}".format(
number, item.name)
f = open(filename, mode="w", encoding='utf-8')
f.write(mail.as_string())
f.close()
return error_text
def process_message(uid, msg: email.message.EmailMessage):
try:
raw_date = msg.get('Date')
local_date = None
# Now convert to local date-time
date_tuple = email.utils.parsedate_tz(raw_date)
if date_tuple:
local_date = datetime.datetime.fromtimestamp(
email.utils.mktime_tz(date_tuple))
except:
raw_date = None
local_date = None
links = []
try:
body = msg.get_body(('html', 'plain'))
if body:
if body.get_content_type() == 'text/plain':
links = links_from_plaintext(body.get_content())
elif body.get_content_type() == 'text/html':
links = links_from_html(body.get_content())
except:
pass
try:
msg_to = msg.get('To')
except:
msg_to = None
try:
msg_from = msg.get('From')
except:
msg_from = None
try:
msg_sub = msg.get('Subject')
except:
msg_sub = None
try:
msg_id = msg.get('Message-ID')
except:
msg_id = None
info = {
'uid': uid,
'to': msg_to,
'from': msg_from,
'subject': msg_sub,
'raw_date': raw_date,
'local_date': local_date,
'message-id': msg_id,
'links': links,
'num-links': len(links)
}
return info
def email_message_to_plain(em: email.message.EmailMessage) -> str:
"""
获取EmailMessage对象中的简单文本
@ param em: EmailMessage对象
@ return: 给定对象中的简单文本
"""
for part in em.walk():
part_content_type = part.get_content_type()
if part_content_type not in ['text/plain','text/html']:
continue
try:
part_content = part.get_content()
except Exception:
part_content = str(part.get_payload())
if part_content_type == 'text/plain':
return part_content if part_content is not None else "empty"
else:
return Formatter.html_to_plain(part_content)
