现在我在这里
import imaplib
mail = imaplib.IMAP4_SSL('imap.gmail.com')
mail.login('login@gmail.com', 'password')
mail.list()
# Out: list of "folders" aka labels in gmail.
mail.select("inbox") # connect to inbox.
#Get an email
result, data = mail.uid('fetch', b'1', '(RFC822)')
raw_email = data[0][1]
email_message = email.message_from_bytes(raw_email)
maintype = email_message.get_content_maintype()
#HERE COMES TROUBLES - if hmtl will be base64 string
if maintype == 'multipart':
for part in email_message.get_payload():
print(part.get_content_maintype())
if part.get_content_maintype() == 'text':
html = str(part.get_payload())
elif maintype == 'text':
html = str(email_message.get_payload())
#Now I Can parse HTML
if html is not None:
soup = BeautifulSoup(html, 'html.parser')
一些字母带有base64编码。怎么解码呢? base64.b64encode(some_string) - 没有帮助
答案 0 :(得分:1)
import email
raw_email = data[0][1]
email_message = email.message_from_string(raw_email)
print email_message['To']
print email.utils.parseaddr(email_message['From']) # for parsing "Yuji Tomita" <yuji@grovemade.com>
print email_message.items() # print all headers
def get_first_text_block(self, email_message_instance):
maintype = email_message_instance.get_content_maintype()
if maintype == 'multipart':
for part in email_message_instance.get_payload():
if part.get_content_maintype() == 'text':
return part.get_payload()
elif maintype == 'text':
return email_message_instance.get_payload()
**我没有写这个来自https://yuji.wordpress.com/2011/06/22/python-imaplib-imap-example-with-gmail/