edms.py
6.39 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
import os
import requests
from zeep import Client, xsd
from settings import conf
from apps.doc import consts
from common.redis_cache import redis_handler as rh
class EDMS:
def __init__(self):
self.sm_client = Client(wsdl=conf.SM_WSDL)
self.dm_client = Client(wsdl=conf.DM_WSDL)
self.df_client = Client(wsdl=conf.DF_WSDL)
self.rc_client = Client(wsdl=conf.RC_WSDL)
self.download_url = conf.EDMS_DOWNLOAD_URL
self.upload_url = conf.EDMS_UPLOAD_URL
self.dealer_code = conf.DEALER_CODE
self.user_name = conf.EDMS_USER
self.pwd = conf.EDMS_PWD
self.session_id = None
self.prefix = 'OCR'
def set_session_id(self):
self.session_id = self.sm_client.service.StartSession(login=self.user_name,
password=self.pwd,
clientType=consts.CUSTOM_CLIENT)
rh.set_session_id(self.session_id)
return self.session_id
def get_session_id(self):
if self.session_id is None:
# redis获取session_id
self.session_id = rh.get_session_id()
if self.session_id is None:
return self.set_session_id()
# 验证session_id
is_session_valid = self.sm_client.service.IsSessionValid(sessionId=self.session_id, keepAlive=False)
if is_session_valid is True:
return self.session_id
return self.set_session_id()
def get_headers(self):
session_id = self.get_session_id()
headers = {'Cookie': '{0}={1}'.format(consts.SESSION_PREFIX, session_id)}
return headers
def get_download_token(self, headers, metadata_version_id):
with self.dm_client.settings(extra_http_headers=headers):
res = self.dm_client.service.PrepareSingleDocumentToDownload(metadataVersionId=metadata_version_id,
token=consts.FIXED_TOKEN,
fileSize=consts.FIXED_FILE_SIZE,
actionType=consts.DOWNLOAD_ACTION_TYPE)
return res.token
def download_handler(self, params, headers, save_path):
r = requests.get(self.download_url, params=params, headers=headers, stream=True)
with open(save_path, "wb") as f:
# chunk是指定每次写入的大小，每次只写了512byte
for chunk in r.iter_content(chunk_size=1024):
if chunk:
f.write(chunk)
f.flush()
def download(self, save_path, metadata_version_id):
headers = self.get_headers()
token = self.get_download_token(headers, metadata_version_id)
params = {'token': token}
self.download_handler(params, headers, save_path)
def create_upload_token(self, headers):
with self.rc_client.settings(extra_http_headers=headers):
token = self.rc_client.service.CreateUploadToken(fileSize=consts.FIXED_FILE_SIZE)
return token
def upload_handler(self, file_path, params, headers):
with open(file_path, 'rb') as f:
data = f.read()
for retry in range(4):
res = requests.post(self.upload_url, params=params, headers=headers, data=data)
if res.status_code == requests.codes.ok:
break
else:
raise Exception
def get_doc_file_name(self, doc_name):
if not isinstance(doc_name, str):
return self.prefix
if doc_name.endswith('.pdf') or doc_name.endswith('.PDF') or \
doc_name.endswith('.pdF') or doc_name.endswith('.pDF') or doc_name.endswith('.pDf') or \
doc_name.endswith('.Pdf') or doc_name.endswith('.PdF') or doc_name.endswith('.PDf'):
name, _ = os.path.splitext(doc_name)
return '{0}{1}'.format(self.prefix, name)
return '{0}{1}'.format(self.prefix, doc_name)
def get_doc_info(self, token, doc, business_type, file_path):
business_type = consts.BUSINESS_TYPE_DICT.get(business_type)
doc_schema_id, auto_filing = consts.DOC_SCHEMA_ID_FILL.get(doc.document_scheme)
application_id = doc.application_id
doc_file_name = self.get_doc_file_name(doc.document_name)
origin_file_name = os.path.basename(file_path)
fields_with_value = [
{'FieldId': consts.APPLICATION_ID_META_FIELD_id,
'FieldValue': xsd.AnyObject(xsd.String(), application_id)},
{'FieldId': consts.DEALER_CODE_META_FIELD_id,
'FieldValue': xsd.AnyObject(xsd.String(), self.dealer_code)},
{'FieldId': consts.BUSINESS_TYPE_META_FIELD_id,
'FieldValue': xsd.AnyObject(xsd.String(), business_type)},
]
fields_with_values = {'FieldWithValue': fields_with_value}
info = {
'DocumentSchemaId': doc_schema_id,
'DocumentName': doc_file_name,
'FieldsWithValues': fields_with_values,
'UploadToken': token,
'OriginalFileName': origin_file_name,
'SendEmailToMembers': False,
'AutoFilingScriptToUse': auto_filing,
'DocumentSchemaType': consts.DOC_SCHEMA_TYPE,
}
return info
def add_doc_info(self, headers, token, doc, business_type, file_path):
info = self.get_doc_info(token, doc, business_type, file_path)
with self.dm_client.settings(extra_http_headers=headers):
metadata_version_id = self.dm_client.service.AddDocumentInfo(info=info)
return metadata_version_id
def upload(self, file_path, doc, business_type):
# file_path = '/Users/clay/Postman/files/OCRuploadTest4.txt'
# file_size = 16
# doc_info = {
# 'document_scheme': 'Acceptance',
# 'application_id': 'CH-B100014248',
# 'doc_file_name': 'OCRuploadTest4.txt',
# 'business_type': 'CO00001',
# }
headers = self.get_headers()
token = self.create_upload_token(headers)
headers.update({'Content-Type': 'application/octet-stream'})
params = {'token': token}
self.upload_handler(file_path, params, headers)
headers.pop('Content-Type')
metadata_version_id = self.add_doc_info(headers, token, doc, business_type, file_path)
return metadata_version_id