I am trying to use Python 3 to extract the body of email messages from a thunderbird mbox file. It is an IMAP account.
I would like to have the text part of the body of the email available to process as a unicode string. It should 'look like' the email does in Thunderbird, and not contain escaped characters such as \r\n =20 etc.
I think that it is the Content Transfer Encodings that I don't know how to decode or remove. I receive emails with a variety of different Content Types, and different Content Transfer Encodings. This is my current attempt :
import mailbox
import quopri,base64
def myconvert(encoded,ContentTransferEncoding):
if ContentTransferEncoding == 'quoted-printable':
result = quopri.decodestring(encoded)
elif ContentTransferEncoding == 'base64':
result = base64.b64decode(encoded)
mboxfile = 'C:/Users/Username/Documents/Thunderbird/Data/profile/ImapMail/server.name/INBOX'
for msg in mailbox.mbox(mboxfile):
if msg.is_multipart(): #Walk through the parts of the email to find the text body.
for part in msg.walk():
if part.is_multipart(): # If part is multipart, walk through the subparts.
for subpart in part.walk():
if subpart.get_content_type() == 'text/plain':
body = subpart.get_payload() # Get the subpart payload (i.e the message body)
for k,v in subpart.items():
if k == 'Content-Transfer-Encoding':
cte = v # Keep the Content Transfer Encoding
elif subpart.get_content_type() == 'text/plain':
body = part.get_payload() # part isn't multipart Get the payload
for k,v in part.items():
if k == 'Content-Transfer-Encoding':
cte = v # Keep the Content Transfer Encoding
print(body)
print('Body is of type:',type(body))
body = myconvert(body,cte)
print(body)
But this fails with :
Body is of type: <class 'str'>
Traceback (most recent call last):
File "C:/Users/David/Documents/Python/test2.py", line 31, in <module>
body = myconvert(body,cte)
File "C:/Users/David/Documents/Python/test2.py", line 6, in myconvert
result = quopri.decodestring(encoded)
File "C:\Python32\lib\quopri.py", line 164, in decodestring
return a2b_qp(s, header=header)
TypeError: 'str' does not support the buffer interface
Here is some code that does the job, it prints errors instead of crashing for those messages where it would fail. I hope that it may be useful. Note that if there is a bug in Python 3, and that is fixed, then the lines .get_payload(decode=True) may then return a str object instead of a bytes object. I ran this code today on 2.7.2 and on Python 3.2.1.
import mailbox
def getcharsets(msg):
charsets = set({})
for c in msg.get_charsets():
if c is not None:
charsets.update([c])
return charsets
def handleerror(errmsg, emailmsg,cs):
print()
print(errmsg)
print("This error occurred while decoding with ",cs," charset.")
print("These charsets were found in the one email.",getcharsets(emailmsg))
print("This is the subject:",emailmsg['subject'])
print("This is the sender:",emailmsg['From'])
def getbodyfromemail(msg):
body = None
#Walk through the parts of the email to find the text body.
if msg.is_multipart():
for part in msg.walk():
# If part is multipart, walk through the subparts.
if part.is_multipart():
for subpart in part.walk():
if subpart.get_content_type() == 'text/plain':
# Get the subpart payload (i.e the message body)
body = subpart.get_payload(decode=True)
#charset = subpart.get_charset()
# Part isn't multipart so get the email body
elif part.get_content_type() == 'text/plain':
body = part.get_payload(decode=True)
#charset = part.get_charset()
# If this isn't a multi-part message then get the payload (i.e the message body)
elif msg.get_content_type() == 'text/plain':
body = msg.get_payload(decode=True)
# No checking done to match the charset with the correct part.
for charset in getcharsets(msg):
try:
body = body.decode(charset)
except UnicodeDecodeError:
handleerror("UnicodeDecodeError: encountered.",msg,charset)
except AttributeError:
handleerror("AttributeError: encountered" ,msg,charset)
return body
#mboxfile = 'C:/Users/Username/Documents/Thunderbird/Data/profile/ImapMail/server.name/INBOX'
print(mboxfile)
for thisemail in mailbox.mbox(mboxfile):
body = getbodyfromemail(thisemail)
print(body[0:1000])