在我的Python代码中,我想获取Gmail电子邮件的正文。我希望它可以与任何电子邮件一起使用,与格式(纯文本,Mime等)和文本编码无关。
从我所看到的,唯一的方法就是编写一个能够处理任何场景的解码器。在进入之前,我有几个问题:
1-我对此是正确的,还是有更简单的方法,从API或Python模块,获取任何类型的电子邮件的正文? (我是Python和Gmail API的新手)
2-有没有人写过这样的解码器,我可以导入我的代码?
谢谢你, 埃里克
答案 0 :(得分:0)
是一个简单的&快速沙盒情况下,你必须重构一些部分
import re
import sys
import imaplib
import getpass
import email
import datetime
import string
import get_mail_search
from sys import stdout
M = imaplib.IMAP4_SSL('imap.gmail.com')
class Get_mail(object):
"""docstring for Get_mail"""
def __init__(self, *args):
super(Get_mail, self).__init__()
c=1
self.login(c)
self.toast_msg()
raw_input()
def toast_msg(self, *args):
"""docstring for Get_mail"""
M = self.mailbox()
stdout.write("\n{}\n".format(get_mail_search.search_help_info))
serach_input = raw_input()
rv, data = M.search(None, serach_input)
if rv != 'OK':
print "No messages found!"
id_ls = data[0].split()
rev_id_ls = [i for i in reversed(id_ls)]
if rev_id_ls:
for o in rev_id_ls:
try:
msg_content = self.process_mailbox(M, o)
_date_ = msg_content[0]
_from_ = msg_content[1]
_to_ = msg_content[2]
_subject_ = msg_content[3]
_msg_ = msg_content[4]
stdout.write("$$$$$$$$$$$\nDate: {}\nFrom: {}\nTo: {}\nSubject: {}\nMSG: {}\n".format(_date_,_from_,_to_,_subject_,_msg_))
except Exception, e:
pass
else:
stdout.write("No {} Mail Found!".format(serach_input))
raw_input()
self.toast_msg()
def login(self, try_c, *args):
"""docstring for Get_mail"""
try:
stdout.write("\nMail:\n")
mail = raw_input()
if mail:
M.login(str(mail), getpass.getpass())
else:
sys.exit(1)
except imaplib.IMAP4.error:
if try_c<=3:
stdout.write("Versuch: {}/3\n".format(try_c))
stdout.write("Die eingegebene E-Mail-Adresse und das Passwort stimmen nicht uberein. Nochmal versuchen")
try_c+=1
self.login(try_c)
else:
sys.exit(1)
def mailbox(self, *args):
"""docstring for Get_mail"""
rv, mailboxes = M.list()
if rv == 'OK':
for menu in mailboxes:
print('{}'.format(menu))
rv, data = M.select("inbox")
if rv == 'OK':
return M
def eval_decode(self, header, *args):
"""docstring for Get_mail"""
return email.Header.decode_header(header)[0]
def process_mailbox(self, M, num, *args):
"""docstring for Get_mail"""
rv, header = M.fetch(num, '(RFC822)')
if rv != 'OK':
print "ERROR getting message", num
header_msg = email.message_from_string(header[0][1])
if header_msg.is_multipart():
body=[payload.get_payload(decode=True) for payload in header_msg.get_payload()]
else:
body=payload.get_payload(decode=True)
from_decode = self.eval_decode(header_msg['From'])
subject_decode = self.eval_decode(header_msg['Subject'])
date_decode = self.eval_decode(header_msg['Date'])
to_decode = self.eval_decode(header_msg['To'])
return (date_decode[0], from_decode[0], to_decode[0], subject_decode[0], str(body[0]))
def run():
try:
Get_mail()
except KeyboardInterrupt:
M.close()
M.logout()
sys.exit(1)
run()