使用python獲取郵箱郵件

首先我們要在郵箱的設置中開通那個POP3

然後我們要導入這些包

import poplib
from datetime import datetime
import jieba
import re
from email.parser import Parser
from email.header import decode_header
from email.utils import parseaddr
from lxml import etree

然後進行鏈接

name_list = []
email = '[email protected]'
password = 'xxxxxx'
pop3_server = 'imap.exmail.qq.com'

# 連接到POP3服務器:
server = poplib.POP3(pop3_server)
# 可以打開或關閉調試信息:
server.set_debuglevel(1)
# 可選:打印POP3服務器的歡迎文字:
print(server.getwelcome().decode('utf-8'))

# 身份認證:
server.user(email)
server.pass_(password)

# stat()返回郵件數量和佔用空間:
print('Messages: %s. Size: %s' % server.stat())
# list()返回所有郵件的編號:
resp, mails, octets = server.list()
# 可以查看返回的列表類似[b'1 82923', b'2 2184', ...]
print(mails)

# 獲取最新一封郵件, 注意索引號從1開始:
index = len(mails)
print(index,'2222')
resp, lines, octets = server.retr(284)

# lines存儲了郵件的原始文本的每一行,
# 可以獲得整個郵件的原始文本:
msg_content = b'\r\n'.join(lines).decode('utf-8')
# 稍後解析出郵件:
msg = Parser().parsestr(msg_content)
# print(msg)

messageObject = Parser().parsestr(msg_content)
msgDate = messageObject["date"]
print(678,msgDate)
# 可以根據郵件索引號直接從服務器刪除郵件:
# server.dele(index)
# 關閉連接:

這裏的index是全部的郵件數量，server.retr(284)，從最新的開始，retr裏面傳你要讀取的第幾個，

try:
    GMT_FORMAT = '%a, %d %b %Y %H:%M:%S +0800 (CST)'
    new_date = datetime.strptime(msgDate, GMT_FORMAT)
except:
    GMT_FORMAT = '%a, %d %b %Y %H:%M:%S +0800'
    new_date = datetime.strptime(msgDate, GMT_FORMAT)
name_list.append(str(new_date))
print(datetime.strptime(msgDate, GMT_FORMAT))

直接讀取出來的時間是Tue, 17 Sep 2019 16:21:25 +0800(CST) 這種形式，這裏是轉爲爲2019-09-17 16:21:25這種亞子。哈哈
繼續

def print_info(msg, indent=0):

    if indent == 0:
        for header in ['From', 'To', 'Subject']:
            value = msg.get(header, '')
            if value:
                if header == 'Subject':
                    value = decode_str(value)

                else:
                    hdr, addr = parseaddr(value)
                    name = decode_str(hdr)
                    value = u'%s <%s>' % (name, addr)

                    print('7777',name)
            print('%s%s: %s' % ('  ' * indent, header, value))
    if (msg.is_multipart()):
        parts = msg.get_payload()
        for n, part in enumerate(parts):
            print('%spart %s' % ('  ' * indent, n))
            print('%s--------------------' % ('  ' * indent))
            print_info(part, indent + 1)
    else:
        content_type = msg.get_content_type()
        if content_type == 'text/plain' or content_type == 'text/html':
            content = msg.get_payload(decode=True)
            charset = guess_charset(msg)
            if charset:
                content = content.decode(charset)
            print('%sText: %s' % ('  ' * indent, content + '...'))
    else:
       print('%sAttachment: %s' % ('  ' * indent, content_type))

這裏就是讀取郵件內容了

繼續還有兩個函數

def decode_str(s):
    value, charset = decode_header(s)[0]
    if charset:
        value = value.decode(charset)
    return value


def guess_charset(msg):
    charset = msg.get_charset()
    if charset is None:
        content_type = msg.get('Content-Type', '').lower()
        pos = content_type.find('charset=')
        if pos >= 0:
            charset = content_type[pos + 8:].strip()
    return charset


print_info(msg = msg)
print(name_list)

server.quit()

就這樣了