email 邮箱接收,带附件,中文解码!

介绍

1.Python邮件解码真的是很痛苦的事情.
2.搞了很久,记录一下,接收邮件编码问题.

demo

class EmailReceive:

    def loging_email(self):
        '''
        邮箱登录
        '''
        host = ''
        user = ''
        pass_ = ''
        print(f'邮箱地址:{host}, user:{user}, pass_={pass_}')
        try:
            server = poplib.POP3_SSL(host)  # 连接到POP3服务器，带SSL的:
            # server = poplib.POP3(host)
            server.user(user)
            server.pass_(pass_)
            return server
        except BaseException as e:
            print(f'邮件登录报错 {e}')
            raise Exception('连接邮箱报错')

    def decode_str(self, s):
        value, charset = decode_header(s)[0]
        if charset:
            if charset == 'gb2312':
                charset = 'gb18030'
            value = value.decode(charset)
        return value

    def get_email_headers(self, msg):
        '''头部信息解析函数'''
        headers = {}
        for header in ['From', 'Subject', 'Date']:
            value = msg.get(header, '')
            if value:
                if header == 'Date':
                    headers['Date'] = value
                if header == 'Subject':
                    subject = self.decode_str(value)
                    headers['Subject'] = subject
                if header == 'From':
                    hdr, addr = parseaddr(value)
                    name = decode_str(hdr)
                    from_addr = u'%s <%s>' % (name, addr)
                    headers['From'] = from_addr
        return headers

    def decode_e_mail(self, data):
        '''解析转码邮件内容'''
        try:
            return data.decode('utf-8')
        except:
            try:
                return data.decode('gbk')
            except Exception as e:
                try:
                    return data.decode('gb18030', 'ignore')
                except:
                    print(chardet.detect(data))
                    print(f'解析转码错误类型是 {e.__class__.__name__}')
                    print(f'解析转码错误明细是 {e}')
                    print(e.__traceback__.tb_lineno)
        return None

    def get_email_content(self, message, savepath):  # 下载附件函数
        '''邮件附件下载'''
        file_name_list = []
        for part in message.walk():
            download_filename = part.get_filename()
            if download_filename:
                download_filename = decode_str(download_filename)
                print(f'附件名称:{download_filename}', savepath)
                data = part.get_payload(decode=True)
                abs_filename = os.path.join(savepath, download_filename)
                try:
                    print(f'邮件附件解压地址: {abs_filename}')
                    attach = open(abs_filename, 'wb')
                    attach.write(data)
                    attach.close()
                    file_name_list.append(download_filename)
                except BaseException as e:
                    print(f'附件下载错误 {abs_filename}')
                    print(e)
        return str(file_name_list)

    def guess_charset(self, 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

    def get_mail_content(self, msg):
        '''邮件正文解码'''
        if msg == None:
            return None
        for part in msg.walk():
            content_type = part.get_content_type()
            charset = guess_charset(part)
            # 如果有附件，则直接跳过
            if part.get_filename() != None: continue
            email_content_type = ''
            content = ''
            if content_type == 'text/plain':
                email_content_type = 'text'
            elif content_type == 'text/html':
                # print('html 格式 跳过')
                email_content_type = 'html'
                # continue  # 不要html格式的邮件
            if charset:
                try:
                    content = part.get_payload(decode=True).decode(charset)
                # 这里遇到了几种由广告等不满足需求的邮件遇到的错误，直接跳过了
                except AttributeError:
                    print('type error')
                except LookupError:
                    print("unknown encoding: utf-8")
            if email_content_type == '':
                continue
                # 如果内容为空，也跳过
            print(email_content_type + ' ----->  ' + content)

    def run(self):
        # 确定邮件遍历起始点
        server = loging_email()
        msg_count, msg_size = server.stat()  # stat()返回邮件数量和占用空间:
        print(f'邮件数量:{msg_count}, 占用空间:{msg_size}')

        for i in range(int(msg_count) - 10, int(msg_count) + 1):  # 遍历邮件索引
            resp, byte_lines, octets = server.retr(i)
            # 拼接邮件内容
            msg_content = b'\r\n'.join(byte_lines).decode('utf-8', 'ignore')
            # 把邮件内容解析为Message对象
            msg = Parser().parsestr(msg_content)
            # 解码邮件正文
            content = self.get_mail_content(msg)
            if content: print(content)
            # 解码头部信息
            headers = self.get_email_headers(msg)
            print(f'第 {i} 封邮件,邮件头部信息:{headers}')
            # 下载邮件附件
            self.get_email_content(msg, r'C:\Users\axzq\Desktop\新建文件夹\qwer')
        server.quit()

赏

谢谢你请我吃糖果