|
|
@@ -1,608 +1,608 @@
|
|
|
-import imaplib
|
|
|
-import shutil
|
|
|
-import smtplib
|
|
|
-from email.mime.multipart import MIMEMultipart
|
|
|
-from email.mime.text import MIMEText
|
|
|
-
|
|
|
-import boto3
|
|
|
-from boto3 import Session
|
|
|
-from django.views import View
|
|
|
-
|
|
|
-from model.models import EmailSortModel, EmailConfigModel
|
|
|
-from Utils.NeteaseMail import NeteaseMail
|
|
|
-from django.views.generic import TemplateView
|
|
|
-
|
|
|
-from object.ResponseObject import ResponseObject
|
|
|
-import os
|
|
|
-import csv
|
|
|
-
|
|
|
-
|
|
|
-class ComprehendView(TemplateView):
|
|
|
-
|
|
|
- def get(self, request, *args, **kwargs):
|
|
|
- request.encoding = 'utf-8'
|
|
|
- operation = kwargs.get('operation')
|
|
|
- return self.validation(request.GET, request, operation)
|
|
|
-
|
|
|
- def post(self, request, *args, **kwargs):
|
|
|
- request.encoding = 'utf-8'
|
|
|
- operation = kwargs.get('operation')
|
|
|
- return self.validation(request.POST, request, operation)
|
|
|
-
|
|
|
- def validation(self, request_dict, request, operation):
|
|
|
- response = ResponseObject()
|
|
|
- if operation is None:
|
|
|
- return response.json(444, 'error path')
|
|
|
- else:
|
|
|
- if operation == 'createSort':
|
|
|
- return self.createSort(request_dict, response)
|
|
|
- elif operation == 'doStartSortWord':
|
|
|
- return self.doStartSortWord(request_dict, response)
|
|
|
- elif operation == 'write_csv':
|
|
|
- return self.write_csv(request_dict, response)
|
|
|
- elif operation == 'upload_csv':
|
|
|
- return self.upload_csv(request_dict, response)
|
|
|
- elif operation == 'create_document_classifier':
|
|
|
- return self.create_document_classifier(request_dict, response)
|
|
|
- elif operation == 'create_endpoint':
|
|
|
- return self.create_endpoint(request_dict, response)
|
|
|
- elif operation == 'describe_document_classifier':
|
|
|
- return self.describe_document_classifier(request_dict, response)
|
|
|
- elif operation == 'describe_endpoint':
|
|
|
- return self.describe_endpoint(request_dict, response)
|
|
|
- elif operation == 'delete_endpoint':
|
|
|
- return self.delete_endpoint(request_dict, response)
|
|
|
- elif operation == 'delete_document_classifier':
|
|
|
- return self.delete_document_classifier(request_dict, response)
|
|
|
- elif operation == 'getDocumentClassifier':
|
|
|
- return self.get_document_classifier(request_dict, response)
|
|
|
- elif operation == 'email':
|
|
|
- return self.email(request_dict, response)
|
|
|
-
|
|
|
- def createSort(self, request_dict, response):
|
|
|
- client = boto3.client('comprehend', region_name='region')
|
|
|
-
|
|
|
- # Create a document classifier
|
|
|
- create_response = client.create_document_classifier(
|
|
|
- InputDataConfig={
|
|
|
- 'S3Uri': 's3://S3Bucket/docclass/file name'
|
|
|
- },
|
|
|
- DataAccessRoleArn='arn:aws:iam::account number:role/resource name',
|
|
|
- DocumentClassifierName='SampleCodeClassifier1',
|
|
|
- LanguageCode='en'
|
|
|
- )
|
|
|
- print("Create response: %s\n", create_response)
|
|
|
-
|
|
|
- # Check the status of the classifier
|
|
|
- describe_response = client.describe_document_classifier(
|
|
|
- DocumentClassifierArn=create_response['DocumentClassifierArn'])
|
|
|
- print("Describe response: %s\n", describe_response)
|
|
|
-
|
|
|
- # List all classifiers in account
|
|
|
- list_response = client.list_document_classifiers()
|
|
|
- print("List response: %s\n", list_response)
|
|
|
-
|
|
|
- def doStartSortWord(self, request_dict, response):
|
|
|
- client = boto3.client('comprehend', region_name='region')
|
|
|
-
|
|
|
- start_response = client.start_document_classification_job(
|
|
|
- InputDataConfig={
|
|
|
- 'S3Uri': 's3://srikad-us-west-2-input/docclass/file name',
|
|
|
- 'InputFormat': 'ONE_DOC_PER_LINE'
|
|
|
- },
|
|
|
- OutputDataConfig={
|
|
|
- 'S3Uri': 's3://S3Bucket/output'
|
|
|
- },
|
|
|
- DataAccessRoleArn='arn:aws:iam::account number:role/resource name',
|
|
|
- DocumentClassifierArn=
|
|
|
- 'arn:aws:comprehend:region:account number:document-classifier/SampleCodeClassifier1'
|
|
|
- )
|
|
|
-
|
|
|
- print("Start response: %s\n", start_response)
|
|
|
-
|
|
|
- # Check the status of the job
|
|
|
- describe_response = client.describe_document_classification_job(JobId=start_response['JobId'])
|
|
|
- print("Describe response: %s\n", describe_response)
|
|
|
-
|
|
|
- # List all classification jobs in account
|
|
|
- list_response = client.list_document_classification_jobs()
|
|
|
- print("List response: %s\n", list_response)
|
|
|
-
|
|
|
- def write_csv(self, request_dict, response):
|
|
|
- file_path = os.path.join(os.path.dirname(__file__) + '/../emailtrainfile/emailtrain.csv')
|
|
|
- with open(file_path, "w", newline='') as f:
|
|
|
- sort = EmailSortModel.objects.values('sort', 'clientquestion')
|
|
|
- for a in sort:
|
|
|
- text = [a['sort'], a['clientquestion']]
|
|
|
- csv_writer = csv.writer(f)
|
|
|
- for i in range(50):
|
|
|
- csv_writer.writerow(text)
|
|
|
- return response.json(0)
|
|
|
-
|
|
|
- def upload_csv(self, request_dict, response):
|
|
|
- file_path = os.path.join(os.path.dirname(__file__) + '/../emailtrainfile/emailtrain.csv')
|
|
|
- bucket_name = "asj-amazon-comprehend"
|
|
|
- upload_key = "location/emailtrain.csv"
|
|
|
- with open(file_path, "rb") as f:
|
|
|
- NeteaseMail().s3_login().upload_fileobj(f, bucket_name, Key=upload_key)
|
|
|
- return response.json(0)
|
|
|
-
|
|
|
- def create_document_classifier(self, request_dict, response):
|
|
|
- try:
|
|
|
- response1 = NeteaseMail().aws_login().create_document_classifier(
|
|
|
- DocumentClassifierName='lhq',
|
|
|
- DataAccessRoleArn='arn:aws:iam::697864307463:role/service-role/AmazonComprehendServiceRoleS3FullAccess-admin',
|
|
|
- # Tags=[{'Key': 'string','Value': 'string'},],
|
|
|
- InputDataConfig={
|
|
|
- 'DataFormat': 'COMPREHEND_CSV',
|
|
|
- # | 'AUGMENTED_MANIFEST',
|
|
|
- 'S3Uri': 's3://asj-amazon-comprehend/location/emailtrain.csv',
|
|
|
- # 'LabelDelimiter': 'string',
|
|
|
- # 'AugmentedManifests': [
|
|
|
- # {
|
|
|
- # 'S3Uri': 'string',
|
|
|
- # 'AttributeNames': ['string', ]
|
|
|
- # },
|
|
|
- # ]
|
|
|
- },
|
|
|
- OutputDataConfig={
|
|
|
- 'S3Uri': 's3://asj-amazon-comprehend/output/lhq/'},
|
|
|
- # 'KmsKeyId': 'string'},
|
|
|
- # ClientRequestToken='string',
|
|
|
- LanguageCode='en',
|
|
|
- # | 'es' | 'fr' | 'de' | 'it' | 'pt' | 'ar'
|
|
|
- # | 'hi' | 'ja' | 'ko' | 'zh' | 'zh-TW',
|
|
|
- # VolumeKmsKeyId='string',
|
|
|
- # VpcConfig={
|
|
|
- # 'SecurityGroupIds': ['string', ],
|
|
|
- # 'Subnets': ['string', ]
|
|
|
- # },
|
|
|
- Mode='MULTI_CLASS' # 'MULTI_LABEL'
|
|
|
- )
|
|
|
- except Exception as e:
|
|
|
- return response.json(404, repr('模型正在训练或已存在'))
|
|
|
- else:
|
|
|
- print(response1)
|
|
|
- return response.json(0)
|
|
|
-
|
|
|
- def create_endpoint(self, request_dict, response):
|
|
|
- try:
|
|
|
- response1 = NeteaseMail().aws_login().create_endpoint(
|
|
|
- EndpointName='lhq',
|
|
|
- ModelArn='arn:aws:comprehend:us-east-1:697864307463:document-classifier/lhq',
|
|
|
- # Document classifier arn
|
|
|
- DesiredInferenceUnits=1,
|
|
|
- # ClientRequestToken='string',
|
|
|
- # Tags=[{'Key': 'string','Value': 'string'},]
|
|
|
- )
|
|
|
- except Exception as e:
|
|
|
- return response.json(404, repr('模型正在训练或不存在，请等待模型训练完再创建端点'))
|
|
|
- else:
|
|
|
- print(response1)
|
|
|
- return response.json(0)
|
|
|
-
|
|
|
- def describe_document_classifier(self, request_dict, response):
|
|
|
- try:
|
|
|
- # classifier_name = request_dict.get('classifier_name', None)
|
|
|
- a = NeteaseMail().aws_arn()[0]
|
|
|
- # classifier_arn = a + str(classifier_name)
|
|
|
- classifier_arn = a + 'lhq'
|
|
|
- response1 = NeteaseMail().aws_login().describe_document_classifier(
|
|
|
- DocumentClassifierArn=classifier_arn
|
|
|
- )
|
|
|
- a1 = {"Status": response1['DocumentClassifierProperties']['Status']}
|
|
|
- except Exception as e:
|
|
|
- return response.json(404, repr('模型不存在'))
|
|
|
- else:
|
|
|
- return response.json(0, a1)
|
|
|
-
|
|
|
- def describe_endpoint(self, request_dict, response):
|
|
|
- try:
|
|
|
- # endpoint_name = request_dict.get('endpoint_name', None)
|
|
|
- a = NeteaseMail().aws_arn()[1]
|
|
|
- # endpoint_arn = a + str(endpoint_name)
|
|
|
- endpoint_arn = a + 'lhq'
|
|
|
- response1 = NeteaseMail().aws_login().describe_endpoint(
|
|
|
- EndpointArn=endpoint_arn
|
|
|
- )
|
|
|
- a1 = {"Status": response1['EndpointProperties']['Status']}
|
|
|
- except Exception as e:
|
|
|
- return response.json(404, repr('端点不存在'))
|
|
|
- else:
|
|
|
- return response.json(0, a1)
|
|
|
-
|
|
|
- def delete_endpoint(self, request_dict, response):
|
|
|
- try:
|
|
|
- # endpoint_name = request_dict.get('endpoint_name', None)
|
|
|
- a = NeteaseMail().aws_arn()[1]
|
|
|
- # endpoint_arn = a + str(endpoint_name)
|
|
|
- endpoint_arn = a + 'lhq'
|
|
|
- response1 = NeteaseMail().aws_login().delete_endpoint(
|
|
|
- EndpointArn=endpoint_arn)
|
|
|
- except Exception as e:
|
|
|
- return response.json(404, repr('端点不存在或正在删除中'))
|
|
|
- else:
|
|
|
- return response.json(0)
|
|
|
-
|
|
|
- def delete_document_classifier(self, request_dict, response):
|
|
|
- try:
|
|
|
- # classifier_name = request_dict.get('classifier_name', None)
|
|
|
- a = NeteaseMail().aws_arn()[0]
|
|
|
- # classifier_arn = a + str(classifier_name)
|
|
|
- classifier_arn = a + 'lhq'
|
|
|
- response1 = NeteaseMail().aws_login().delete_document_classifier(
|
|
|
- DocumentClassifierArn=classifier_arn)
|
|
|
- except Exception as e:
|
|
|
- return response.json(404, repr('模型不存在或正在删除中'))
|
|
|
- else:
|
|
|
- return response.json(0)
|
|
|
-
|
|
|
- def get_document_classifier(self, request_dict, response):
|
|
|
- ec_qs = EmailConfigModel.objects.filter(emailtag=1) # 获取总邮件
|
|
|
- emailsum = 0
|
|
|
- replyemailsum = 0
|
|
|
- for ec in ec_qs:
|
|
|
- email_server = NeteaseMail().loginEmail(ec.emailserver, ec.fromaddr, ec.password, ec.emailserverport)
|
|
|
- subject_list, from_list, bodydata_list, uid_list, results, email_body, fujian_list, image_list = NeteaseMail().getEmailContext(
|
|
|
- email_server)
|
|
|
- emailsum += len(results)
|
|
|
- print("标题：", len(subject_list), subject_list)
|
|
|
- print("发件人：", len(from_list), from_list)
|
|
|
- print("邮件内容：", len(bodydata_list), bodydata_list)
|
|
|
- print("邮件uid:", len(uid_list), uid_list)
|
|
|
- print("附件判断：", len(fujian_list), fujian_list)
|
|
|
- print('图片数量：', len(image_list), image_list)
|
|
|
- if not bodydata_list:
|
|
|
- print("邮箱内无未读邮件")
|
|
|
- else:
|
|
|
- print('成功拿到邮件数据')
|
|
|
- for i, v in enumerate(subject_list):
|
|
|
- print('-------------------------------------------------------------------------')
|
|
|
- print("邮件标题：", subject_list[i])
|
|
|
- if not bodydata_list[i] or not subject_list[i]:
|
|
|
- print("邮件无正文或无标题，不进行回复")
|
|
|
- continue
|
|
|
-
|
|
|
- if fujian_list[i] == 'have':
|
|
|
- reply_model = bodydata_list[i]
|
|
|
- image = image_list
|
|
|
- shoujianren = 'liehaoquan2021@163.com'
|
|
|
- fajianren = from_list[i].split()[1]
|
|
|
- NeteaseMail().sentemail(None, uid_list[i],reply_model, image, subject_list[i], fajianren, shoujianren,
|
|
|
- ec.fromaddr, ec.password)
|
|
|
- file_path = os.path.join(os.path.dirname(__file__) + '/../emailtrainfile/image/')
|
|
|
- shutil.rmtree(file_path)
|
|
|
- os.mkdir(file_path)
|
|
|
- print('邮件含有图片或附件，已转发到zendesk')
|
|
|
- email_server.set_flags(uid_list[i], b'\\Seen', silent=False)
|
|
|
- continue
|
|
|
-
|
|
|
- response1 = NeteaseMail().aws_login().classify_document(
|
|
|
- Text=bodydata_list[i].split('\n\n\n\n\n')[0],
|
|
|
- EndpointArn='arn:aws:comprehend:us-east-1:697864307463:document-classifier-endpoint/lhq'
|
|
|
- # EndpointArn='arn:aws:comprehend:us-east-1:697864307463:document-classifier-endpoint/test'
|
|
|
- )
|
|
|
- # print(response.index(max(response['Classes']['Score'])))
|
|
|
- nums = []
|
|
|
- print('emailsort:')
|
|
|
- for cls in response1['Classes']:
|
|
|
- print(cls['Name'])
|
|
|
- nums.append(cls['Score'])
|
|
|
- print("识别种类及命中率：", response1['Classes'][nums.index(max(nums))])
|
|
|
- if response1['Classes'][nums.index(max(nums))]['Score'] >= 0.95:
|
|
|
- reply_sort = EmailSortModel.objects.filter(
|
|
|
- sort=response1['Classes'][nums.index(max(nums))]['Name']).values('autoreplymodel')
|
|
|
- if reply_sort.exists():
|
|
|
- reply_model = reply_sort[0]['autoreplymodel'] + '\n' + '\n' + '\n' + '\n' + '\n' + '\n' + \
|
|
|
- 'At' + email_body[i]['Date'] + from_list[i].split()[0] + \
|
|
|
- from_list[i].split()[1] + \
|
|
|
- 'wrote:\n ' + bodydata_list[i]
|
|
|
- print(reply_model)
|
|
|
- shoujianren = from_list[i].split()[1].replace('<', '').replace('>', '')
|
|
|
- a = NeteaseMail().sentemail(None, uid_list[i], reply_model, None, subject_list[i], ec.fromaddr, shoujianren,
|
|
|
- ec.fromaddr, ec.password)
|
|
|
- email_server.set_flags(uid_list[i], b'\\Seen', silent=False)
|
|
|
- if a == 'fail':
|
|
|
- print("此邮件被判定为垃圾邮件，不进行回复")
|
|
|
- email_server.remove_flags(uid_list[i], b'\\Seen', silent=False)
|
|
|
- else:
|
|
|
- replyemailsum += a
|
|
|
- else:
|
|
|
- print("无此转发分类，不进行回复")
|
|
|
- else:
|
|
|
- reply_model = bodydata_list[i]
|
|
|
- shoujianren = 'liehaoquan2021@163.com'
|
|
|
- fajianren = from_list[i].split()[1]
|
|
|
- NeteaseMail().sentemail(reply_model, None, subject_list[i], fajianren, shoujianren,
|
|
|
- ec.fromaddr, ec.password)
|
|
|
- email_server.set_flags(uid_list[i], b'\\Seen', silent=False)
|
|
|
- print("命中率低于0.95，已转发到zendesk")
|
|
|
- # es_qs = EmailSortModel.objects.filter(sort=response1['Classes'][nums.index(max(nums))]['Name'])
|
|
|
- # if es_qs.exists():
|
|
|
- # uemail_qs = EmailConfigModel.objects.filter(userid=es_qs[0]['userid'], langconfig__langcode='en')
|
|
|
- # if uemail_qs.exists():
|
|
|
- # for uem in uemail_qs:
|
|
|
- # NeteaseMail().sentemail(bodydata_list[i], subject_list[i], from_list[i], uem.fromaddr, ec.fromaddr, ec.password)
|
|
|
- NeteaseMail().closeEmail(email_server)
|
|
|
- emaildict = {
|
|
|
- "邮箱内获取到未读邮件数": emailsum,
|
|
|
- "已自动回复的邮件数": replyemailsum
|
|
|
- }
|
|
|
- return response.json(0, emaildict)
|
|
|
-
|
|
|
- def email(self, request_dict, response):
|
|
|
- from imapclient import IMAPClient
|
|
|
- import email
|
|
|
- import time
|
|
|
- import email.parser
|
|
|
- from nntplib import decode_header
|
|
|
- from email.header import Header
|
|
|
- import chardet
|
|
|
-
|
|
|
- ec_qs = EmailConfigModel.objects.filter(emailtag=1) # 获取总邮件
|
|
|
- for ec in ec_qs:
|
|
|
- global a, email_server
|
|
|
-
|
|
|
- #邮件登录
|
|
|
- try:
|
|
|
- email_server = IMAPClient(ec.emailserver, ssl=True, port=ec.emailserverport)
|
|
|
- # email_server = imaplib.IMAP4_SSL(IMAP_SERVER, 993) # 网易企业邮箱服务器及SSL端口
|
|
|
- print("imap4 服务器连接成功")
|
|
|
- email_server.login(ec.fromaddr, ec.password)
|
|
|
- email_server.id_({"name": "IMAPClient", "version": "2.1.0"})
|
|
|
- # email_server.login(FROM_ADDR, PASSWORD)
|
|
|
- print("imap4 (%s)账号密码正确，登录成功" % ec.fromaddr)
|
|
|
- except:
|
|
|
- print("imap4 服务器连接失败")
|
|
|
-
|
|
|
- email_server.select_folder('INBOX')
|
|
|
- results = email_server.search('UNSEEN') # 读取未读邮件
|
|
|
- print("邮箱内获取到未读邮件：", len(results))
|
|
|
- subject_list = []
|
|
|
- from_list = []
|
|
|
- uid_list = []
|
|
|
- email_body = []
|
|
|
- fujian_list = []
|
|
|
- image_list = []
|
|
|
- plain_list = []
|
|
|
- html_list = []
|
|
|
- a = 0
|
|
|
-
|
|
|
- # 对每一封邮件进行内容解析
|
|
|
- for uid in results:
|
|
|
- msgdict = email_server.fetch(uid, ['Body[]', 'ENVELOPE'], '(RFC822)')
|
|
|
- mailbody = msgdict[uid][b'BODY[]']
|
|
|
- envelope = msgdict[uid][b'ENVELOPE']
|
|
|
- message = email.message_from_bytes(mailbody)
|
|
|
- text = message.as_string()
|
|
|
- body = email.parser.Parser().parsestr(text)
|
|
|
-
|
|
|
- nowtime = time.asctime(time.localtime(time.time()))
|
|
|
- nowmonth = nowtime.split()[1]
|
|
|
- nowday = nowtime.split()[2]
|
|
|
- emailmonth = body['Date'].split()[2]
|
|
|
- emailday = body['Date'].split()[1]
|
|
|
- print('email',emailmonth,emailday)
|
|
|
- print('now', nowmonth, nowday)
|
|
|
- # if emailmonth != nowmonth or emailday != nowday:
|
|
|
- # email_server.remove_flags(uid, b'\\Seen', silent=False)
|
|
|
- # continue
|
|
|
-
|
|
|
- email_body.append(body)
|
|
|
- subject_list.append(decode_header(body['Subject']))
|
|
|
- from_list.append(decode_header(body['from']))
|
|
|
- uid_list.append(uid)
|
|
|
- print("标题：", subject_list)
|
|
|
-
|
|
|
- attlist = {}
|
|
|
- try:
|
|
|
- for part in body.walk():
|
|
|
- if not part.is_multipart():
|
|
|
- file = part.get_filename() # 附件名
|
|
|
- if file:
|
|
|
- a = 1
|
|
|
- filename = email.header.decode_header(file)[0][0] # 附件名
|
|
|
- charset = email.header.decode_header(file)[0][1] # 编码
|
|
|
- if part.get_all("Content-ID"):
|
|
|
- content_id = part.get_all("Content-ID")[0][1:-1]
|
|
|
- else:
|
|
|
- content_id = "" # 附件ID,也就是邮件源码里面的cid
|
|
|
- ''' 多个附件时将附件名和ID对应保存到dict里面,后面将正文中的cid替换为本地保存路径 '''
|
|
|
- attlist[content_id] = filename
|
|
|
- ''' 附件文件名为中文或有编码的时候要进行转码 '''
|
|
|
- if str(charset) != "None":
|
|
|
- filename = filename.decode(charset)
|
|
|
- filedata = part.get_payload(decode=True) # 附件内容
|
|
|
- ''' 把附件写到文件里面,附件一定要用wb打开,二进制 '''
|
|
|
- file_path = os.path.join(os.path.dirname(__file__) + '/../emailtrainfile/image/')
|
|
|
- image_list.append(file_path + filename)
|
|
|
- with open(file_path + filename, "wb") as fw:
|
|
|
- fw.write(filedata)
|
|
|
- fw.close()
|
|
|
-
|
|
|
- elif part.get_content_type() == 'text/plain':
|
|
|
- con3 = part.get_payload(decode=True).strip()
|
|
|
- print('plain:', chardet.detect(con3))
|
|
|
- if chardet.detect(con3)['encoding'] == 'utf-8':
|
|
|
- plain_list.append(con3.decode('utf-8'))
|
|
|
- continue
|
|
|
- # if chardet.detect(con3)['encoding'] == 'ISO-8859-1':
|
|
|
- # plain_list.append(con3.decode('ISO-8859-1')) # .decode('gbk').encode('utf8')
|
|
|
- # continue
|
|
|
- else:
|
|
|
- plain_list.append(con3.decode('gbk'))
|
|
|
- continue
|
|
|
- elif part.get_content_type() == 'text/html':
|
|
|
- con3 = part.get_payload(decode=True).strip()
|
|
|
- print('html', chardet.detect(con3))
|
|
|
- if chardet.detect(con3)['encoding'] == 'utf-8':
|
|
|
- html_list.append(con3.decode('utf-8'))
|
|
|
- continue
|
|
|
- # if chardet.detect(con3)['encoding'] == 'ISO-8859-1':
|
|
|
- # html_list.append(con3.decode('ISO-8859-1'))
|
|
|
- # continue
|
|
|
- else:
|
|
|
- html_list.append(con3.decode('gbk'))
|
|
|
- continue
|
|
|
- except Exception as e:
|
|
|
- print(e)
|
|
|
- print('获取邮件内容失败')
|
|
|
- email_server.remove_flags(uid, b'\\Seen', silent=False)
|
|
|
- subject_list.clear()
|
|
|
- from_list.clear()
|
|
|
- uid_list.clear()
|
|
|
- email_body.clear()
|
|
|
- fujian_list.clear()
|
|
|
- image_list.clear()
|
|
|
- plain_list.clear()
|
|
|
- html_list.clear()
|
|
|
- print('-------------------------------------------------------------------------')
|
|
|
- continue
|
|
|
-
|
|
|
-
|
|
|
- if a == 1:
|
|
|
- fujian_list.append('have')
|
|
|
- a = 0
|
|
|
- else:
|
|
|
- fujian_list.append('none')
|
|
|
- email_server.remove_flags(uid, b'\\Seen', silent=False)
|
|
|
- print("发件人：", from_list)
|
|
|
- print("邮件内容：")
|
|
|
- print("plain形式:",plain_list)
|
|
|
- print("html形式:",html_list)
|
|
|
- print("邮件uid:", uid_list)
|
|
|
- print("邮件是否含有图片或附件：", fujian_list)
|
|
|
- print('图片或附件名字：', image_list)
|
|
|
- if not html_list and not plain_list:
|
|
|
- print("邮箱内无未读邮件")
|
|
|
- else:
|
|
|
- print('成功拿到邮件数据')
|
|
|
-
|
|
|
- # 对邮件类型进行判断处理
|
|
|
- for i, v in enumerate(uid_list):
|
|
|
- print("邮件标题：", subject_list[i])
|
|
|
- if html_list and not plain_list:
|
|
|
- print('此邮件仅含有html')
|
|
|
- reply_model = html_list[i]
|
|
|
- fajianren = from_list[i]
|
|
|
- shoujianren = 'liehaoquan2021@163.com' # 写zendesk邮箱
|
|
|
- NeteaseMail().sentemail(email_server, uid_list[i],reply_model, None, subject_list[i], fajianren, shoujianren,
|
|
|
- ec.fromaddr, ec.password)
|
|
|
- print('-------------------------------------------------------------------------')
|
|
|
- break
|
|
|
-
|
|
|
- if plain_list[i] == '':
|
|
|
- print('此邮件无正文')
|
|
|
- reply_model = ''
|
|
|
- fajianren = from_list[i]
|
|
|
- shoujianren = 'liehaoquan2021@163.com' # 写zendesk邮箱
|
|
|
- NeteaseMail().sentemail(email_server, uid_list[i],reply_model, None, subject_list[i], fajianren, shoujianren,
|
|
|
- ec.fromaddr, ec.password)
|
|
|
- print('-------------------------------------------------------------------------')
|
|
|
- break
|
|
|
-
|
|
|
- if not subject_list[i]:
|
|
|
- print('此邮件无主题')
|
|
|
- if html_list and not plain_list:
|
|
|
- print('此邮件无主题且仅含有html')
|
|
|
- reply_model = html_list[i]
|
|
|
- fajianren = from_list[i]
|
|
|
- shoujianren = 'liehaoquan2021@163.com' # 写zendesk邮箱
|
|
|
- biaoti = '(无主题)'
|
|
|
- NeteaseMail().sentemail(email_server, uid_list[i],reply_model, None, biaoti, fajianren, shoujianren,
|
|
|
- ec.fromaddr, ec.password)
|
|
|
- print('-------------------------------------------------------------------------')
|
|
|
- break
|
|
|
- elif plain_list:
|
|
|
- print('此邮件无主题且含有正文')
|
|
|
- reply_model = plain_list[i]
|
|
|
- fajianren = from_list[i]
|
|
|
- shoujianren = 'liehaoquan2021@163.com' # 写zendesk邮箱
|
|
|
- biaoti = '(无主题)'
|
|
|
- NeteaseMail().sentemail(email_server, uid_list[i], reply_model, None, biaoti, fajianren, shoujianren,
|
|
|
- ec.fromaddr, ec.password)
|
|
|
- print('-------------------------------------------------------------------------')
|
|
|
- break
|
|
|
-
|
|
|
- # 处理含有图片或附件的邮件
|
|
|
- if fujian_list[i] == 'have':
|
|
|
- print('此邮件含有图片或附件或视频或压缩包')
|
|
|
- reply_model = html_list[i]
|
|
|
- image = image_list
|
|
|
- fajianren = from_list[i]
|
|
|
- shoujianren = 'liehaoquan2021@163.com' # 写zendesk邮箱
|
|
|
- NeteaseMail().sentemail(email_server, uid_list[i], reply_model, image, subject_list[i], fajianren, shoujianren,
|
|
|
- ec.fromaddr, ec.password)
|
|
|
- file_path = os.path.join(os.path.dirname(__file__) + '/../emailtrainfile/image/')
|
|
|
- shutil.rmtree(file_path)
|
|
|
- os.mkdir(file_path)
|
|
|
- print('-------------------------------------------------------------------------')
|
|
|
- break
|
|
|
-
|
|
|
- if fujian_list[i] == 'none':
|
|
|
- # 处理无图片或附件的邮件
|
|
|
- # 进行种类判断
|
|
|
- print("识别内容：", plain_list[i].split('\n\n')[0]) # plain
|
|
|
- if len(plain_list[i].split('\n\n\n')[0]) < 1000:
|
|
|
- response1 = NeteaseMail().aws_login().classify_document(
|
|
|
- Text=plain_list[i].split('\n\n\n')[0],
|
|
|
- EndpointArn='arn:aws:comprehend:us-east-1:697864307463:document-classifier-endpoint/lhq'
|
|
|
- # EndpointArn='arn:aws:comprehend:us-east-1:697864307463:document-classifier-endpoint/test'
|
|
|
- )
|
|
|
- # print(response.index(max(response['Classes']['Score'])))
|
|
|
- nums = []
|
|
|
- print('emailsort:')
|
|
|
- for cls in response1['Classes']:
|
|
|
- print(cls['Name'])
|
|
|
- nums.append(cls['Score'])
|
|
|
- print("识别种类及命中率：", response1['Classes'][nums.index(max(nums))])
|
|
|
- # 命中率高于0.95时
|
|
|
- if response1['Classes'][nums.index(max(nums))]['Score'] >= 0.95:
|
|
|
- reply_sort = EmailSortModel.objects.filter(
|
|
|
- sort=response1['Classes'][nums.index(max(nums))]['Name']).values('autoreplymodel')
|
|
|
- if reply_sort.exists():
|
|
|
- reply_model = reply_sort[0]['autoreplymodel'] + '\n' + '\n' + '\n' + '\n' + '\n' + '\n' + \
|
|
|
- 'At' + email_body[i]['Date'] + str(from_list[i].split()[0:-1]) + \
|
|
|
- from_list[i].split()[-1] + \
|
|
|
- 'wrote:\n ' + plain_list[i]
|
|
|
- print(reply_model)
|
|
|
- shoujianren = from_list[i].split()[1].replace('<', '').replace('>', '')
|
|
|
- NeteaseMail().sentemail(email_server, uid_list[i], reply_model, None, subject_list[i], ec.fromaddr, shoujianren,
|
|
|
- ec.fromaddr, ec.password)
|
|
|
- print('-------------------------------------------------------------------------')
|
|
|
- break
|
|
|
- else:
|
|
|
- print("此邮件命中率低于0.95")
|
|
|
- reply_model = html_list[i] # html
|
|
|
- fajianren = from_list[i]
|
|
|
- print(fujian_list)
|
|
|
- shoujianren = 'liehaoquan2021@163.com' # 写zendesk邮箱
|
|
|
- NeteaseMail().sentemail(email_server, uid_list[i], reply_model, None, subject_list[i],
|
|
|
- fajianren, shoujianren,
|
|
|
- ec.fromaddr, ec.password)
|
|
|
- print('-------------------------------------------------------------------------')
|
|
|
- break
|
|
|
-
|
|
|
- else:
|
|
|
- print("识别内容过长")
|
|
|
- reply_model = html_list[i] # html
|
|
|
- fajianren = from_list[i]
|
|
|
- print(fujian_list)
|
|
|
- shoujianren = 'liehaoquan2021@163.com' # 写zendesk邮箱
|
|
|
- NeteaseMail().sentemail(email_server, uid_list[i], reply_model, None, subject_list[i], fajianren, shoujianren,
|
|
|
- ec.fromaddr, ec.password)
|
|
|
- print('-------------------------------------------------------------------------')
|
|
|
- break
|
|
|
- subject_list.clear()
|
|
|
- from_list.clear()
|
|
|
- uid_list.clear()
|
|
|
- email_body.clear()
|
|
|
- fujian_list.clear()
|
|
|
- image_list.clear()
|
|
|
- plain_list.clear()
|
|
|
- html_list.clear()
|
|
|
- NeteaseMail().closeEmail(email_server)
|
|
|
- return response.json(0)
|
|
|
-
|
|
|
-# if __name__ == '__main__':
|
|
|
-# ComprehendAction().get_document_classifier()
|
|
|
+# import imaplib
|
|
|
+# import shutil
|
|
|
+# import smtplib
|
|
|
+# from email.mime.multipart import MIMEMultipart
|
|
|
+# from email.mime.text import MIMEText
|
|
|
+#
|
|
|
+# import boto3
|
|
|
+# from boto3 import Session
|
|
|
+# from django.views import View
|
|
|
+#
|
|
|
+# from model.models import EmailSortModel, EmailConfigModel
|
|
|
+# from Utils.NeteaseMail import NeteaseMail
|
|
|
+# from django.views.generic import TemplateView
|
|
|
+#
|
|
|
+# from object.ResponseObject import ResponseObject
|
|
|
+# import os
|
|
|
+# import csv
|
|
|
+#
|
|
|
+#
|
|
|
+# class ComprehendView(TemplateView):
|
|
|
+#
|
|
|
+# def get(self, request, *args, **kwargs):
|
|
|
+# request.encoding = 'utf-8'
|
|
|
+# operation = kwargs.get('operation')
|
|
|
+# return self.validation(request.GET, request, operation)
|
|
|
+#
|
|
|
+# def post(self, request, *args, **kwargs):
|
|
|
+# request.encoding = 'utf-8'
|
|
|
+# operation = kwargs.get('operation')
|
|
|
+# return self.validation(request.POST, request, operation)
|
|
|
+#
|
|
|
+# def validation(self, request_dict, request, operation):
|
|
|
+# response = ResponseObject()
|
|
|
+# if operation is None:
|
|
|
+# return response.json(444, 'error path')
|
|
|
+# else:
|
|
|
+# if operation == 'createSort':
|
|
|
+# return self.createSort(request_dict, response)
|
|
|
+# elif operation == 'doStartSortWord':
|
|
|
+# return self.doStartSortWord(request_dict, response)
|
|
|
+# elif operation == 'write_csv':
|
|
|
+# return self.write_csv(request_dict, response)
|
|
|
+# elif operation == 'upload_csv':
|
|
|
+# return self.upload_csv(request_dict, response)
|
|
|
+# elif operation == 'create_document_classifier':
|
|
|
+# return self.create_document_classifier(request_dict, response)
|
|
|
+# elif operation == 'create_endpoint':
|
|
|
+# return self.create_endpoint(request_dict, response)
|
|
|
+# elif operation == 'describe_document_classifier':
|
|
|
+# return self.describe_document_classifier(request_dict, response)
|
|
|
+# elif operation == 'describe_endpoint':
|
|
|
+# return self.describe_endpoint(request_dict, response)
|
|
|
+# elif operation == 'delete_endpoint':
|
|
|
+# return self.delete_endpoint(request_dict, response)
|
|
|
+# elif operation == 'delete_document_classifier':
|
|
|
+# return self.delete_document_classifier(request_dict, response)
|
|
|
+# elif operation == 'getDocumentClassifier':
|
|
|
+# return self.get_document_classifier(request_dict, response)
|
|
|
+# elif operation == 'email':
|
|
|
+# return self.email(request_dict, response)
|
|
|
+#
|
|
|
+# def createSort(self, request_dict, response):
|
|
|
+# client = boto3.client('comprehend', region_name='region')
|
|
|
+#
|
|
|
+# # Create a document classifier
|
|
|
+# create_response = client.create_document_classifier(
|
|
|
+# InputDataConfig={
|
|
|
+# 'S3Uri': 's3://S3Bucket/docclass/file name'
|
|
|
+# },
|
|
|
+# DataAccessRoleArn='arn:aws:iam::account number:role/resource name',
|
|
|
+# DocumentClassifierName='SampleCodeClassifier1',
|
|
|
+# LanguageCode='en'
|
|
|
+# )
|
|
|
+# print("Create response: %s\n", create_response)
|
|
|
+#
|
|
|
+# # Check the status of the classifier
|
|
|
+# describe_response = client.describe_document_classifier(
|
|
|
+# DocumentClassifierArn=create_response['DocumentClassifierArn'])
|
|
|
+# print("Describe response: %s\n", describe_response)
|
|
|
+#
|
|
|
+# # List all classifiers in account
|
|
|
+# list_response = client.list_document_classifiers()
|
|
|
+# print("List response: %s\n", list_response)
|
|
|
+#
|
|
|
+# def doStartSortWord(self, request_dict, response):
|
|
|
+# client = boto3.client('comprehend', region_name='region')
|
|
|
+#
|
|
|
+# start_response = client.start_document_classification_job(
|
|
|
+# InputDataConfig={
|
|
|
+# 'S3Uri': 's3://srikad-us-west-2-input/docclass/file name',
|
|
|
+# 'InputFormat': 'ONE_DOC_PER_LINE'
|
|
|
+# },
|
|
|
+# OutputDataConfig={
|
|
|
+# 'S3Uri': 's3://S3Bucket/output'
|
|
|
+# },
|
|
|
+# DataAccessRoleArn='arn:aws:iam::account number:role/resource name',
|
|
|
+# DocumentClassifierArn=
|
|
|
+# 'arn:aws:comprehend:region:account number:document-classifier/SampleCodeClassifier1'
|
|
|
+# )
|
|
|
+#
|
|
|
+# print("Start response: %s\n", start_response)
|
|
|
+#
|
|
|
+# # Check the status of the job
|
|
|
+# describe_response = client.describe_document_classification_job(JobId=start_response['JobId'])
|
|
|
+# print("Describe response: %s\n", describe_response)
|
|
|
+#
|
|
|
+# # List all classification jobs in account
|
|
|
+# list_response = client.list_document_classification_jobs()
|
|
|
+# print("List response: %s\n", list_response)
|
|
|
+#
|
|
|
+# def write_csv(self, request_dict, response):
|
|
|
+# file_path = os.path.join(os.path.dirname(__file__) + '/../emailtrainfile/emailtrain.csv')
|
|
|
+# with open(file_path, "w", newline='') as f:
|
|
|
+# sort = EmailSortModel.objects.values('sort', 'clientquestion')
|
|
|
+# for a in sort:
|
|
|
+# text = [a['sort'], a['clientquestion']]
|
|
|
+# csv_writer = csv.writer(f)
|
|
|
+# for i in range(50):
|
|
|
+# csv_writer.writerow(text)
|
|
|
+# return response.json(0)
|
|
|
+#
|
|
|
+# def upload_csv(self, request_dict, response):
|
|
|
+# file_path = os.path.join(os.path.dirname(__file__) + '/../emailtrainfile/emailtrain.csv')
|
|
|
+# bucket_name = "asj-amazon-comprehend"
|
|
|
+# upload_key = "location/emailtrain.csv"
|
|
|
+# with open(file_path, "rb") as f:
|
|
|
+# NeteaseMail().s3_login().upload_fileobj(f, bucket_name, Key=upload_key)
|
|
|
+# return response.json(0)
|
|
|
+#
|
|
|
+# def create_document_classifier(self, request_dict, response):
|
|
|
+# try:
|
|
|
+# response1 = NeteaseMail().aws_login().create_document_classifier(
|
|
|
+# DocumentClassifierName='lhq',
|
|
|
+# DataAccessRoleArn='arn:aws:iam::697864307463:role/service-role/AmazonComprehendServiceRoleS3FullAccess-admin',
|
|
|
+# # Tags=[{'Key': 'string','Value': 'string'},],
|
|
|
+# InputDataConfig={
|
|
|
+# 'DataFormat': 'COMPREHEND_CSV',
|
|
|
+# # | 'AUGMENTED_MANIFEST',
|
|
|
+# 'S3Uri': 's3://asj-amazon-comprehend/location/emailtrain.csv',
|
|
|
+# # 'LabelDelimiter': 'string',
|
|
|
+# # 'AugmentedManifests': [
|
|
|
+# # {
|
|
|
+# # 'S3Uri': 'string',
|
|
|
+# # 'AttributeNames': ['string', ]
|
|
|
+# # },
|
|
|
+# # ]
|
|
|
+# },
|
|
|
+# OutputDataConfig={
|
|
|
+# 'S3Uri': 's3://asj-amazon-comprehend/output/lhq/'},
|
|
|
+# # 'KmsKeyId': 'string'},
|
|
|
+# # ClientRequestToken='string',
|
|
|
+# LanguageCode='en',
|
|
|
+# # | 'es' | 'fr' | 'de' | 'it' | 'pt' | 'ar'
|
|
|
+# # | 'hi' | 'ja' | 'ko' | 'zh' | 'zh-TW',
|
|
|
+# # VolumeKmsKeyId='string',
|
|
|
+# # VpcConfig={
|
|
|
+# # 'SecurityGroupIds': ['string', ],
|
|
|
+# # 'Subnets': ['string', ]
|
|
|
+# # },
|
|
|
+# Mode='MULTI_CLASS' # 'MULTI_LABEL'
|
|
|
+# )
|
|
|
+# except Exception as e:
|
|
|
+# return response.json(404, repr('模型正在训练或已存在'))
|
|
|
+# else:
|
|
|
+# print(response1)
|
|
|
+# return response.json(0)
|
|
|
+#
|
|
|
+# def create_endpoint(self, request_dict, response):
|
|
|
+# try:
|
|
|
+# response1 = NeteaseMail().aws_login().create_endpoint(
|
|
|
+# EndpointName='lhq',
|
|
|
+# ModelArn='arn:aws:comprehend:us-east-1:697864307463:document-classifier/lhq',
|
|
|
+# # Document classifier arn
|
|
|
+# DesiredInferenceUnits=1,
|
|
|
+# # ClientRequestToken='string',
|
|
|
+# # Tags=[{'Key': 'string','Value': 'string'},]
|
|
|
+# )
|
|
|
+# except Exception as e:
|
|
|
+# return response.json(404, repr('模型正在训练或不存在，请等待模型训练完再创建端点'))
|
|
|
+# else:
|
|
|
+# print(response1)
|
|
|
+# return response.json(0)
|
|
|
+#
|
|
|
+# def describe_document_classifier(self, request_dict, response):
|
|
|
+# try:
|
|
|
+# # classifier_name = request_dict.get('classifier_name', None)
|
|
|
+# a = NeteaseMail().aws_arn()[0]
|
|
|
+# # classifier_arn = a + str(classifier_name)
|
|
|
+# classifier_arn = a + 'lhq'
|
|
|
+# response1 = NeteaseMail().aws_login().describe_document_classifier(
|
|
|
+# DocumentClassifierArn=classifier_arn
|
|
|
+# )
|
|
|
+# a1 = {"Status": response1['DocumentClassifierProperties']['Status']}
|
|
|
+# except Exception as e:
|
|
|
+# return response.json(404, repr('模型不存在'))
|
|
|
+# else:
|
|
|
+# return response.json(0, a1)
|
|
|
+#
|
|
|
+# def describe_endpoint(self, request_dict, response):
|
|
|
+# try:
|
|
|
+# # endpoint_name = request_dict.get('endpoint_name', None)
|
|
|
+# a = NeteaseMail().aws_arn()[1]
|
|
|
+# # endpoint_arn = a + str(endpoint_name)
|
|
|
+# endpoint_arn = a + 'lhq'
|
|
|
+# response1 = NeteaseMail().aws_login().describe_endpoint(
|
|
|
+# EndpointArn=endpoint_arn
|
|
|
+# )
|
|
|
+# a1 = {"Status": response1['EndpointProperties']['Status']}
|
|
|
+# except Exception as e:
|
|
|
+# return response.json(404, repr('端点不存在'))
|
|
|
+# else:
|
|
|
+# return response.json(0, a1)
|
|
|
+#
|
|
|
+# def delete_endpoint(self, request_dict, response):
|
|
|
+# try:
|
|
|
+# # endpoint_name = request_dict.get('endpoint_name', None)
|
|
|
+# a = NeteaseMail().aws_arn()[1]
|
|
|
+# # endpoint_arn = a + str(endpoint_name)
|
|
|
+# endpoint_arn = a + 'lhq'
|
|
|
+# response1 = NeteaseMail().aws_login().delete_endpoint(
|
|
|
+# EndpointArn=endpoint_arn)
|
|
|
+# except Exception as e:
|
|
|
+# return response.json(404, repr('端点不存在或正在删除中'))
|
|
|
+# else:
|
|
|
+# return response.json(0)
|
|
|
+#
|
|
|
+# def delete_document_classifier(self, request_dict, response):
|
|
|
+# try:
|
|
|
+# # classifier_name = request_dict.get('classifier_name', None)
|
|
|
+# a = NeteaseMail().aws_arn()[0]
|
|
|
+# # classifier_arn = a + str(classifier_name)
|
|
|
+# classifier_arn = a + 'lhq'
|
|
|
+# response1 = NeteaseMail().aws_login().delete_document_classifier(
|
|
|
+# DocumentClassifierArn=classifier_arn)
|
|
|
+# except Exception as e:
|
|
|
+# return response.json(404, repr('模型不存在或正在删除中'))
|
|
|
+# else:
|
|
|
+# return response.json(0)
|
|
|
+#
|
|
|
+# def get_document_classifier(self, request_dict, response):
|
|
|
+# ec_qs = EmailConfigModel.objects.filter(emailtag=1) # 获取总邮件
|
|
|
+# emailsum = 0
|
|
|
+# replyemailsum = 0
|
|
|
+# for ec in ec_qs:
|
|
|
+# email_server = NeteaseMail().loginEmail(ec.emailserver, ec.fromaddr, ec.password, ec.emailserverport)
|
|
|
+# subject_list, from_list, bodydata_list, uid_list, results, email_body, fujian_list, image_list = NeteaseMail().getEmailContext(
|
|
|
+# email_server)
|
|
|
+# emailsum += len(results)
|
|
|
+# print("标题：", len(subject_list), subject_list)
|
|
|
+# print("发件人：", len(from_list), from_list)
|
|
|
+# print("邮件内容：", len(bodydata_list), bodydata_list)
|
|
|
+# print("邮件uid:", len(uid_list), uid_list)
|
|
|
+# print("附件判断：", len(fujian_list), fujian_list)
|
|
|
+# print('图片数量：', len(image_list), image_list)
|
|
|
+# if not bodydata_list:
|
|
|
+# print("邮箱内无未读邮件")
|
|
|
+# else:
|
|
|
+# print('成功拿到邮件数据')
|
|
|
+# for i, v in enumerate(subject_list):
|
|
|
+# print('-------------------------------------------------------------------------')
|
|
|
+# print("邮件标题：", subject_list[i])
|
|
|
+# if not bodydata_list[i] or not subject_list[i]:
|
|
|
+# print("邮件无正文或无标题，不进行回复")
|
|
|
+# continue
|
|
|
+#
|
|
|
+# if fujian_list[i] == 'have':
|
|
|
+# reply_model = bodydata_list[i]
|
|
|
+# image = image_list
|
|
|
+# shoujianren = 'liehaoquan2021@163.com'
|
|
|
+# fajianren = from_list[i].split()[1]
|
|
|
+# NeteaseMail().sentemail(None, uid_list[i],reply_model, image, subject_list[i], fajianren, shoujianren,
|
|
|
+# ec.fromaddr, ec.password)
|
|
|
+# file_path = os.path.join(os.path.dirname(__file__) + '/../emailtrainfile/image/')
|
|
|
+# shutil.rmtree(file_path)
|
|
|
+# os.mkdir(file_path)
|
|
|
+# print('邮件含有图片或附件，已转发到zendesk')
|
|
|
+# email_server.set_flags(uid_list[i], b'\\Seen', silent=False)
|
|
|
+# continue
|
|
|
+#
|
|
|
+# response1 = NeteaseMail().aws_login().classify_document(
|
|
|
+# Text=bodydata_list[i].split('\n\n\n\n\n')[0],
|
|
|
+# EndpointArn='arn:aws:comprehend:us-east-1:697864307463:document-classifier-endpoint/lhq'
|
|
|
+# # EndpointArn='arn:aws:comprehend:us-east-1:697864307463:document-classifier-endpoint/test'
|
|
|
+# )
|
|
|
+# # print(response.index(max(response['Classes']['Score'])))
|
|
|
+# nums = []
|
|
|
+# print('emailsort:')
|
|
|
+# for cls in response1['Classes']:
|
|
|
+# print(cls['Name'])
|
|
|
+# nums.append(cls['Score'])
|
|
|
+# print("识别种类及命中率：", response1['Classes'][nums.index(max(nums))])
|
|
|
+# if response1['Classes'][nums.index(max(nums))]['Score'] >= 0.95:
|
|
|
+# reply_sort = EmailSortModel.objects.filter(
|
|
|
+# sort=response1['Classes'][nums.index(max(nums))]['Name']).values('autoreplymodel')
|
|
|
+# if reply_sort.exists():
|
|
|
+# reply_model = reply_sort[0]['autoreplymodel'] + '\n' + '\n' + '\n' + '\n' + '\n' + '\n' + \
|
|
|
+# 'At' + email_body[i]['Date'] + from_list[i].split()[0] + \
|
|
|
+# from_list[i].split()[1] + \
|
|
|
+# 'wrote:\n ' + bodydata_list[i]
|
|
|
+# print(reply_model)
|
|
|
+# shoujianren = from_list[i].split()[1].replace('<', '').replace('>', '')
|
|
|
+# a = NeteaseMail().sentemail(None, uid_list[i], reply_model, None, subject_list[i], ec.fromaddr, shoujianren,
|
|
|
+# ec.fromaddr, ec.password)
|
|
|
+# email_server.set_flags(uid_list[i], b'\\Seen', silent=False)
|
|
|
+# if a == 'fail':
|
|
|
+# print("此邮件被判定为垃圾邮件，不进行回复")
|
|
|
+# email_server.remove_flags(uid_list[i], b'\\Seen', silent=False)
|
|
|
+# else:
|
|
|
+# replyemailsum += a
|
|
|
+# else:
|
|
|
+# print("无此转发分类，不进行回复")
|
|
|
+# else:
|
|
|
+# reply_model = bodydata_list[i]
|
|
|
+# shoujianren = 'liehaoquan2021@163.com'
|
|
|
+# fajianren = from_list[i].split()[1]
|
|
|
+# NeteaseMail().sentemail(reply_model, None, subject_list[i], fajianren, shoujianren,
|
|
|
+# ec.fromaddr, ec.password)
|
|
|
+# email_server.set_flags(uid_list[i], b'\\Seen', silent=False)
|
|
|
+# print("命中率低于0.95，已转发到zendesk")
|
|
|
+# # es_qs = EmailSortModel.objects.filter(sort=response1['Classes'][nums.index(max(nums))]['Name'])
|
|
|
+# # if es_qs.exists():
|
|
|
+# # uemail_qs = EmailConfigModel.objects.filter(userid=es_qs[0]['userid'], langconfig__langcode='en')
|
|
|
+# # if uemail_qs.exists():
|
|
|
+# # for uem in uemail_qs:
|
|
|
+# # NeteaseMail().sentemail(bodydata_list[i], subject_list[i], from_list[i], uem.fromaddr, ec.fromaddr, ec.password)
|
|
|
+# NeteaseMail().closeEmail(email_server)
|
|
|
+# emaildict = {
|
|
|
+# "邮箱内获取到未读邮件数": emailsum,
|
|
|
+# "已自动回复的邮件数": replyemailsum
|
|
|
+# }
|
|
|
+# return response.json(0, emaildict)
|
|
|
+#
|
|
|
+# def email(self, request_dict, response):
|
|
|
+# from imapclient import IMAPClient
|
|
|
+# import email
|
|
|
+# import time
|
|
|
+# import email.parser
|
|
|
+# from nntplib import decode_header
|
|
|
+# from email.header import Header
|
|
|
+# import chardet
|
|
|
+#
|
|
|
+# ec_qs = EmailConfigModel.objects.filter(emailtag=1) # 获取总邮件
|
|
|
+# for ec in ec_qs:
|
|
|
+# global a, email_server
|
|
|
+#
|
|
|
+# #邮件登录
|
|
|
+# try:
|
|
|
+# email_server = IMAPClient(ec.emailserver, ssl=True, port=ec.emailserverport)
|
|
|
+# # email_server = imaplib.IMAP4_SSL(IMAP_SERVER, 993) # 网易企业邮箱服务器及SSL端口
|
|
|
+# print("imap4 服务器连接成功")
|
|
|
+# email_server.login(ec.fromaddr, ec.password)
|
|
|
+# email_server.id_({"name": "IMAPClient", "version": "2.1.0"})
|
|
|
+# # email_server.login(FROM_ADDR, PASSWORD)
|
|
|
+# print("imap4 (%s)账号密码正确，登录成功" % ec.fromaddr)
|
|
|
+# except:
|
|
|
+# print("imap4 服务器连接失败")
|
|
|
+#
|
|
|
+# email_server.select_folder('INBOX')
|
|
|
+# results = email_server.search('UNSEEN') # 读取未读邮件
|
|
|
+# print("邮箱内获取到未读邮件：", len(results))
|
|
|
+# subject_list = []
|
|
|
+# from_list = []
|
|
|
+# uid_list = []
|
|
|
+# email_body = []
|
|
|
+# fujian_list = []
|
|
|
+# image_list = []
|
|
|
+# plain_list = []
|
|
|
+# html_list = []
|
|
|
+# a = 0
|
|
|
+#
|
|
|
+# # 对每一封邮件进行内容解析
|
|
|
+# for uid in results:
|
|
|
+# msgdict = email_server.fetch(uid, ['Body[]', 'ENVELOPE'], '(RFC822)')
|
|
|
+# mailbody = msgdict[uid][b'BODY[]']
|
|
|
+# envelope = msgdict[uid][b'ENVELOPE']
|
|
|
+# message = email.message_from_bytes(mailbody)
|
|
|
+# text = message.as_string()
|
|
|
+# body = email.parser.Parser().parsestr(text)
|
|
|
+#
|
|
|
+# nowtime = time.asctime(time.localtime(time.time()))
|
|
|
+# nowmonth = nowtime.split()[1]
|
|
|
+# nowday = nowtime.split()[2]
|
|
|
+# emailmonth = body['Date'].split()[2]
|
|
|
+# emailday = body['Date'].split()[1]
|
|
|
+# print('email',emailmonth,emailday)
|
|
|
+# print('now', nowmonth, nowday)
|
|
|
+# # if emailmonth != nowmonth or emailday != nowday:
|
|
|
+# # email_server.remove_flags(uid, b'\\Seen', silent=False)
|
|
|
+# # continue
|
|
|
+#
|
|
|
+# email_body.append(body)
|
|
|
+# subject_list.append(decode_header(body['Subject']))
|
|
|
+# from_list.append(decode_header(body['from']))
|
|
|
+# uid_list.append(uid)
|
|
|
+# print("标题：", subject_list)
|
|
|
+#
|
|
|
+# attlist = {}
|
|
|
+# try:
|
|
|
+# for part in body.walk():
|
|
|
+# if not part.is_multipart():
|
|
|
+# file = part.get_filename() # 附件名
|
|
|
+# if file:
|
|
|
+# a = 1
|
|
|
+# filename = email.header.decode_header(file)[0][0] # 附件名
|
|
|
+# charset = email.header.decode_header(file)[0][1] # 编码
|
|
|
+# if part.get_all("Content-ID"):
|
|
|
+# content_id = part.get_all("Content-ID")[0][1:-1]
|
|
|
+# else:
|
|
|
+# content_id = "" # 附件ID,也就是邮件源码里面的cid
|
|
|
+# ''' 多个附件时将附件名和ID对应保存到dict里面,后面将正文中的cid替换为本地保存路径 '''
|
|
|
+# attlist[content_id] = filename
|
|
|
+# ''' 附件文件名为中文或有编码的时候要进行转码 '''
|
|
|
+# if str(charset) != "None":
|
|
|
+# filename = filename.decode(charset)
|
|
|
+# filedata = part.get_payload(decode=True) # 附件内容
|
|
|
+# ''' 把附件写到文件里面,附件一定要用wb打开,二进制 '''
|
|
|
+# file_path = os.path.join(os.path.dirname(__file__) + '/../emailtrainfile/image/')
|
|
|
+# image_list.append(file_path + filename)
|
|
|
+# with open(file_path + filename, "wb") as fw:
|
|
|
+# fw.write(filedata)
|
|
|
+# fw.close()
|
|
|
+#
|
|
|
+# elif part.get_content_type() == 'text/plain':
|
|
|
+# con3 = part.get_payload(decode=True).strip()
|
|
|
+# print('plain:', chardet.detect(con3))
|
|
|
+# if chardet.detect(con3)['encoding'] == 'utf-8':
|
|
|
+# plain_list.append(con3.decode('utf-8'))
|
|
|
+# continue
|
|
|
+# # if chardet.detect(con3)['encoding'] == 'ISO-8859-1':
|
|
|
+# # plain_list.append(con3.decode('ISO-8859-1')) # .decode('gbk').encode('utf8')
|
|
|
+# # continue
|
|
|
+# else:
|
|
|
+# plain_list.append(con3.decode('gbk'))
|
|
|
+# continue
|
|
|
+# elif part.get_content_type() == 'text/html':
|
|
|
+# con3 = part.get_payload(decode=True).strip()
|
|
|
+# print('html', chardet.detect(con3))
|
|
|
+# if chardet.detect(con3)['encoding'] == 'utf-8':
|
|
|
+# html_list.append(con3.decode('utf-8'))
|
|
|
+# continue
|
|
|
+# # if chardet.detect(con3)['encoding'] == 'ISO-8859-1':
|
|
|
+# # html_list.append(con3.decode('ISO-8859-1'))
|
|
|
+# # continue
|
|
|
+# else:
|
|
|
+# html_list.append(con3.decode('gbk'))
|
|
|
+# continue
|
|
|
+# except Exception as e:
|
|
|
+# print(e)
|
|
|
+# print('获取邮件内容失败')
|
|
|
+# email_server.remove_flags(uid, b'\\Seen', silent=False)
|
|
|
+# subject_list.clear()
|
|
|
+# from_list.clear()
|
|
|
+# uid_list.clear()
|
|
|
+# email_body.clear()
|
|
|
+# fujian_list.clear()
|
|
|
+# image_list.clear()
|
|
|
+# plain_list.clear()
|
|
|
+# html_list.clear()
|
|
|
+# print('-------------------------------------------------------------------------')
|
|
|
+# continue
|
|
|
+#
|
|
|
+#
|
|
|
+# if a == 1:
|
|
|
+# fujian_list.append('have')
|
|
|
+# a = 0
|
|
|
+# else:
|
|
|
+# fujian_list.append('none')
|
|
|
+# email_server.remove_flags(uid, b'\\Seen', silent=False)
|
|
|
+# print("发件人：", from_list)
|
|
|
+# print("邮件内容：")
|
|
|
+# print("plain形式:",plain_list)
|
|
|
+# print("html形式:",html_list)
|
|
|
+# print("邮件uid:", uid_list)
|
|
|
+# print("邮件是否含有图片或附件：", fujian_list)
|
|
|
+# print('图片或附件名字：', image_list)
|
|
|
+# if not html_list and not plain_list:
|
|
|
+# print("邮箱内无未读邮件")
|
|
|
+# else:
|
|
|
+# print('成功拿到邮件数据')
|
|
|
+#
|
|
|
+# # 对邮件类型进行判断处理
|
|
|
+# for i, v in enumerate(uid_list):
|
|
|
+# print("邮件标题：", subject_list[i])
|
|
|
+# if html_list and not plain_list:
|
|
|
+# print('此邮件仅含有html')
|
|
|
+# reply_model = html_list[i]
|
|
|
+# fajianren = from_list[i]
|
|
|
+# shoujianren = 'liehaoquan2021@163.com' # 写zendesk邮箱
|
|
|
+# NeteaseMail().sentemail(email_server, uid_list[i],reply_model, None, subject_list[i], fajianren, shoujianren,
|
|
|
+# ec.fromaddr, ec.password)
|
|
|
+# print('-------------------------------------------------------------------------')
|
|
|
+# break
|
|
|
+#
|
|
|
+# if plain_list[i] == '':
|
|
|
+# print('此邮件无正文')
|
|
|
+# reply_model = ''
|
|
|
+# fajianren = from_list[i]
|
|
|
+# shoujianren = 'liehaoquan2021@163.com' # 写zendesk邮箱
|
|
|
+# NeteaseMail().sentemail(email_server, uid_list[i],reply_model, None, subject_list[i], fajianren, shoujianren,
|
|
|
+# ec.fromaddr, ec.password)
|
|
|
+# print('-------------------------------------------------------------------------')
|
|
|
+# break
|
|
|
+#
|
|
|
+# if not subject_list[i]:
|
|
|
+# print('此邮件无主题')
|
|
|
+# if html_list and not plain_list:
|
|
|
+# print('此邮件无主题且仅含有html')
|
|
|
+# reply_model = html_list[i]
|
|
|
+# fajianren = from_list[i]
|
|
|
+# shoujianren = 'liehaoquan2021@163.com' # 写zendesk邮箱
|
|
|
+# biaoti = '(无主题)'
|
|
|
+# NeteaseMail().sentemail(email_server, uid_list[i],reply_model, None, biaoti, fajianren, shoujianren,
|
|
|
+# ec.fromaddr, ec.password)
|
|
|
+# print('-------------------------------------------------------------------------')
|
|
|
+# break
|
|
|
+# elif plain_list:
|
|
|
+# print('此邮件无主题且含有正文')
|
|
|
+# reply_model = plain_list[i]
|
|
|
+# fajianren = from_list[i]
|
|
|
+# shoujianren = 'liehaoquan2021@163.com' # 写zendesk邮箱
|
|
|
+# biaoti = '(无主题)'
|
|
|
+# NeteaseMail().sentemail(email_server, uid_list[i], reply_model, None, biaoti, fajianren, shoujianren,
|
|
|
+# ec.fromaddr, ec.password)
|
|
|
+# print('-------------------------------------------------------------------------')
|
|
|
+# break
|
|
|
+#
|
|
|
+# # 处理含有图片或附件的邮件
|
|
|
+# if fujian_list[i] == 'have':
|
|
|
+# print('此邮件含有图片或附件或视频或压缩包')
|
|
|
+# reply_model = html_list[i]
|
|
|
+# image = image_list
|
|
|
+# fajianren = from_list[i]
|
|
|
+# shoujianren = 'liehaoquan2021@163.com' # 写zendesk邮箱
|
|
|
+# NeteaseMail().sentemail(email_server, uid_list[i], reply_model, image, subject_list[i], fajianren, shoujianren,
|
|
|
+# ec.fromaddr, ec.password)
|
|
|
+# file_path = os.path.join(os.path.dirname(__file__) + '/../emailtrainfile/image/')
|
|
|
+# shutil.rmtree(file_path)
|
|
|
+# os.mkdir(file_path)
|
|
|
+# print('-------------------------------------------------------------------------')
|
|
|
+# break
|
|
|
+#
|
|
|
+# if fujian_list[i] == 'none':
|
|
|
+# # 处理无图片或附件的邮件
|
|
|
+# # 进行种类判断
|
|
|
+# print("识别内容：", plain_list[i].split('\n\n')[0]) # plain
|
|
|
+# if len(plain_list[i].split('\n\n\n')[0]) < 1000:
|
|
|
+# response1 = NeteaseMail().aws_login().classify_document(
|
|
|
+# Text=plain_list[i].split('\n\n\n')[0],
|
|
|
+# EndpointArn='arn:aws:comprehend:us-east-1:697864307463:document-classifier-endpoint/lhq'
|
|
|
+# # EndpointArn='arn:aws:comprehend:us-east-1:697864307463:document-classifier-endpoint/test'
|
|
|
+# )
|
|
|
+# # print(response.index(max(response['Classes']['Score'])))
|
|
|
+# nums = []
|
|
|
+# print('emailsort:')
|
|
|
+# for cls in response1['Classes']:
|
|
|
+# print(cls['Name'])
|
|
|
+# nums.append(cls['Score'])
|
|
|
+# print("识别种类及命中率：", response1['Classes'][nums.index(max(nums))])
|
|
|
+# # 命中率高于0.95时
|
|
|
+# if response1['Classes'][nums.index(max(nums))]['Score'] >= 0.95:
|
|
|
+# reply_sort = EmailSortModel.objects.filter(
|
|
|
+# sort=response1['Classes'][nums.index(max(nums))]['Name']).values('autoreplymodel')
|
|
|
+# if reply_sort.exists():
|
|
|
+# reply_model = reply_sort[0]['autoreplymodel'] + '\n' + '\n' + '\n' + '\n' + '\n' + '\n' + \
|
|
|
+# 'At' + email_body[i]['Date'] + str(from_list[i].split()[0:-1]) + \
|
|
|
+# from_list[i].split()[-1] + \
|
|
|
+# 'wrote:\n ' + plain_list[i]
|
|
|
+# print(reply_model)
|
|
|
+# shoujianren = from_list[i].split()[1].replace('<', '').replace('>', '')
|
|
|
+# NeteaseMail().sentemail(email_server, uid_list[i], reply_model, None, subject_list[i], ec.fromaddr, shoujianren,
|
|
|
+# ec.fromaddr, ec.password)
|
|
|
+# print('-------------------------------------------------------------------------')
|
|
|
+# break
|
|
|
+# else:
|
|
|
+# print("此邮件命中率低于0.95")
|
|
|
+# reply_model = html_list[i] # html
|
|
|
+# fajianren = from_list[i]
|
|
|
+# print(fujian_list)
|
|
|
+# shoujianren = 'liehaoquan2021@163.com' # 写zendesk邮箱
|
|
|
+# NeteaseMail().sentemail(email_server, uid_list[i], reply_model, None, subject_list[i],
|
|
|
+# fajianren, shoujianren,
|
|
|
+# ec.fromaddr, ec.password)
|
|
|
+# print('-------------------------------------------------------------------------')
|
|
|
+# break
|
|
|
+#
|
|
|
+# else:
|
|
|
+# print("识别内容过长")
|
|
|
+# reply_model = html_list[i] # html
|
|
|
+# fajianren = from_list[i]
|
|
|
+# print(fujian_list)
|
|
|
+# shoujianren = 'liehaoquan2021@163.com' # 写zendesk邮箱
|
|
|
+# NeteaseMail().sentemail(email_server, uid_list[i], reply_model, None, subject_list[i], fajianren, shoujianren,
|
|
|
+# ec.fromaddr, ec.password)
|
|
|
+# print('-------------------------------------------------------------------------')
|
|
|
+# break
|
|
|
+# subject_list.clear()
|
|
|
+# from_list.clear()
|
|
|
+# uid_list.clear()
|
|
|
+# email_body.clear()
|
|
|
+# fujian_list.clear()
|
|
|
+# image_list.clear()
|
|
|
+# plain_list.clear()
|
|
|
+# html_list.clear()
|
|
|
+# NeteaseMail().closeEmail(email_server)
|
|
|
+# return response.json(0)
|
|
|
+#
|
|
|
+# # if __name__ == '__main__':
|
|
|
+# # ComprehendAction().get_document_classifier()
|
