def parse1(request_text=None, file_path=None):
# TODO: 如果提供了file_path, 优先filepath
if file_path:
request_text = ParseReqHeader().get_request_text_by_file(file_path)
request_line, headers_alone = request_text.split(b'\r\n', 1)
headers = BytesParser().parsebytes(headers_alone)
return {k: v for k, v in headers.items()}
def _get_parts_regular(self, data):
msg = BytesParser().parsebytes(data)
yield from self._get_headparts(msg.items())
for part in msg.walk():
path = part.get_filename()
data = part.get_payload(decode=True)
if data is None:
continue
if path is None:
path = F'BODY.{file_extension(part.get_content_subtype(), "TXT").upper()}'
yield UnpackResult(path, data)
def _get_parts_regular(self, data):
if not re.match(BR'^[\s!-~]+$', data):
raise ValueError('This is not a plaintext email message.')
msg = BytesParser().parsebytes(data)
yield from self._get_headparts(msg.items())
for k, part in enumerate(msg.walk()):
path = part.get_filename()
elog = None
if path is None:
extension = file_extension(part.get_content_type(), 'txt')
path = F'body.{extension}'
else:
path = F'attachments/{path}'
try:
data = part.get_payload(decode=True)
except Exception as E:
try:
data = part.get_payload(decode=False)
except Exception as E:
elog = str(E)
data = None
else:
from refinery import carve
self.log_warn(F'manually decoding part {k}, data might be corrupted: {path}')
if isinstance(data, str):
data = data.encode('latin1')
if isbuffer(data):
data = next(data | carve('b64', stripspace=True, single=True, decode=True))
else:
elog = str(E)
data = None
if not data:
if elog is not None:
self.log_warn(F'could not get content of message part {k}: {elog!s}')
continue
yield UnpackResult(path, data)
def extractMetaData(self,obj): headers = BytesParser().parse(obj) h = dict(headers.items()) return self.convertMetaDataToSwiftFormat(h)
def extractMetaData(self, obj): headers = BytesParser().parse(obj) metadata = dict(headers.items()) return self.cleanupMetaDataDict(metadata)
def extractMetaData(self, obj):
headers = BytesParser().parse(obj)
metadata = dict(headers.items())
return self.cleanupMetaDataDict(metadata)
