def email_parser(email_file):
html_flag = 0
with open(email_file, 'rb') as fp:
msg = BytesParser(policy=policy.default).parse(fp)
# print('Subject:', msg['subject'])
if not msg.is_multipart():
# print("Singular email")
if msg.get_content_maintype() == "text":
if msg.get_content_subtype() == "plain":
# print(msg.get_content_type())
body = msg.get_body(preferencelist='text/plain')
# print(body)
elif msg.get_content_subtype() == "html":
# print(msg.get_content_type())
body = msg.get_body(preferencelist='html')
# print("----Body from get_body()-------")
# print(body)
html_body = str(body).split("\n")[3:]
html_body = '\n'.join(html_body)
# print("----Parsed text through beautiful soup-------")
body = html_parse(html_body)
# print(body)
else:
print("Don't know if html or text {}".format(
msg.get_content_subtype()))
else:
print("Email is multipart")
i = 0
for part in msg.walk():
i = i + 1
print("part " + str(i))
cdispo = str(part.get('Content-Disposition'))
print(cdispo)
print(part.get_content_type())
print(part.get_content_subtype())
if part.get_content_type(
) == 'multipart/alternative' or part.get_content_type(
) == 'multipart/related':
body = part.get_body(preferencelist='html')
print("----Body from get_body()-------")
print(body)
html_body = str(body).split("\n")[3:]
html_body = '\n'.join(html_body)
print("----Parsed text through beautiful soup-------")
body = html_parse(html_body)
print(body)
if part.get_content_type() == 'text/plain':
body = part.get_payload(decode=True) # decode
print(body)
break
return body
def display_eml(eml_filepath): ## -> treba vyladit!!!
with open(eml_filepath, 'rb') as eml_file:
msg = BytesParser(policy=policy.default).parse(eml_file)
text = msg.get_body(preferencelist=('plain')).get_content()
# sk = get_info_from_mail_field(msg['from'])
# eml_output = eml_file.read()
eml_output = msg
# eml_output = msg #get_all('Content-Dispositio
found = []
for part in msg.walk():
if 'content-disposition' not in part:
continue
cdisp = part['content-disposition'].split(';')
cdisp = [x.strip() for x in cdisp]
if cdisp[0].lower() != 'attachment':
continue
parsed = {}
for kv in cdisp[1:]:
key, val = kv.split('=')
if val.startswith('"'):
val = val.strip('"')
elif val.startswith("'"):
val = val.strip("'")
parsed[key] = val
found.append((parsed, part))
eml_output = {
"Odesílatel": msg.get('From'),
"Příjemce": msg.get('To'),
"Datum": msg.get('Date'),
"Předmět": msg.get('Subject'),
"Text zprávy": msg.get_body(preferencelist=('plain')).get_content(),
"Přílohy": found #[0]
}
#print('eml_output',eml_output, msg.get('Cc'))
if msg.get_content_maintype() == 'multipart': # <--zjisti zda potrebujes - jinak smaz
# loop on the parts of the mail
for part in msg.walk():
# find the attachment part - so skip all the other parts
if part.get_content_maintype() == 'multipart': continue
if part.get_content_maintype() == 'text':
content = part.get_body(preferencelist=('plain'))
if content:
output = part.get_body(preferencelist=('plain')).get_content()
else:
output = None
continue
if part.get('Content-Disposition') == 'inline': continue
if part.get('Content-Disposition') is None: continue
# save the attachment in the program directory
result_dict = {
"Odesílatel": msg.get('From'),
"Příjemce": msg.get('To'),
"Datum": msg.get('Date'),
"Předmět": msg.get('Subject'),
"Text zprávy": output, #msg.get_body(preferencelist=('plain')).get_content(),
"Přílohy": part.get_all('Content-Disposition')
}
#eml_output = result_dict
#print('result_dict',result_dict)
return eml_output
]
template = {key: '' for key in keys}
# Now the header items can be accessed as a dictionary:
# print('To: {}'.format(eml['to']))
# print('From: {}'.format(eml['from']))
template['from'] = eml['from']
# print('Subject: {}'.format(eml['subject']))
template['subject'] = eml['subject']
# You can also access the parts of the addresses:
# print('Recipient username: {}'.format(eml['to'].addresses[0].username))
# print('Sender name: {}'.format(eml['from'].addresses[0].display_name))
template['from_display_name'] = eml['from'].addresses[0].display_name
ctype = eml.get_content_maintype()
if ctype == 'multipart':
for part in eml.get_payload():
subctype = part.get_content_maintype()
if subctype == 'text':
if part.get_content_subtype() == 'plain':
template['content_text'] = part.get_payload()
elif part.get_content_subtype() == 'html':
template['content_html'] = part.get_payload()
elif ctype == 'text':
if eml.get_content_subtype() == 'plain':
template['content_text'] = eml.get_payload()
elif eml.get_content_subtype == 'html':
template['content_html'] = eml.get_payload()
else:
print('nope...')
