add eDMS

@@ -8,4 +8,8 @@ HIL_SET = {'HIL', 'HIl', 'HiL', 'Hil', 'hIL', 'hIl', 'hiL', 'hil', 'CO00002'}
 HIL_PREFIX = 'HIL'
 HIL_PREFIX = 'HIL'
 AFC_PREFIX = 'AFC'
 AFC_PREFIX = 'AFC'
 
 
+SESSION_PREFIX = 'FHLSID'
 CUSTOM_CLIENT = 'CustomClient'
 CUSTOM_CLIENT = 'CustomClient'
+FIXED_TOKEN = '00000000-0000-0000-0000-000000000000'
+FIXED_FILE_SIZE = 0
+DOWNLOAD_ACTION_TYPE = 'Downloaded'

+import requests
+from zeep import Client
+from settings import conf
+from . import consts
+
+
+class EDMS:
+
+    def __init__(self, user_name, pwd):
+        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.download_url = conf.EDMS_DOWNLOAD_URL
+        self.user_name = user_name
+        self.pwd = pwd
+        self.session_id = None
+
+    def get_session_id(self):
+        self.session_id = self.sm_client.service.StartSession(login=self.user_name,
+                                                              password=self.pwd,
+                                                              clientType=consts.CUSTOM_CLIENT)
+        return self.session_id
+
+    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(self, save_path, metadata_version_id):
+        session_id = self.get_session_id()
+        headers = {'Cookie': '{0}={1}'.format(consts.SESSION_PREFIX, session_id)}
+        token = self.get_download_token(headers, metadata_version_id)
+        params = {'token': token}
+
+        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=512):
+                if chunk:
+                    f.write(chunk)
+                    f.flush()
+

@@ -17,6 +17,7 @@ from common.tools.file_tools import write_zip_file
 from apps.doc.models import DocStatus, HILDoc, AFCDoc
 from apps.doc.models import DocStatus, HILDoc, AFCDoc
 from apps.doc import consts
 from apps.doc import consts
 from settings import conf
 from settings import conf
+from apps.doc.edms import EDMS
 
 
 
 
 class Command(BaseCommand, LoggerMixin):
 class Command(BaseCommand, LoggerMixin):
@@ -39,7 +40,7 @@ class Command(BaseCommand, LoggerMixin):
             'Content-Type': 'application/json'
             'Content-Type': 'application/json'
         }
         }
         # EDMS web_service_api
         # EDMS web_service_api
-        self.sm_client = Client(wsdl=conf.SM_WSDL)
+        self.edms = EDMS(conf.EDMS_USER, conf.EDMS_PWD)
         # 优雅退出信号：15
         # 优雅退出信号：15
         signal.signal(signal.SIGTERM, self.signal_handler)
         signal.signal(signal.SIGTERM, self.signal_handler)
 
 
@@ -70,9 +71,6 @@ class Command(BaseCommand, LoggerMixin):
         if doc_info is None:
         if doc_info is None:
             return None, None, None
             return None, None, None
         # TODO EDMS下载pdf
         # TODO EDMS下载pdf
-        # session_id = self.sm_client.service.StartSession(login=conf.EDMS_USER,
-        #                                                  password=conf.EDMS_PWD,
-        #                                                  clientType=consts.CUSTOM_CLIENT)
 
 
         doc_data_path = os.path.join(self.data_dir, business_type, str(doc_id))
         doc_data_path = os.path.join(self.data_dir, business_type, str(doc_id))
         pdf_path = os.path.join(doc_data_path, '{0}.pdf'.format(doc_id))
         pdf_path = os.path.join(doc_data_path, '{0}.pdf'.format(doc_id))
@@ -200,16 +198,20 @@ class Command(BaseCommand, LoggerMixin):
     def handle(self, *args, **kwargs):
     def handle(self, *args, **kwargs):
         sleep_second = int(conf.SLEEP_SECOND)
         sleep_second = int(conf.SLEEP_SECOND)
         max_sleep_second = int(conf.MAX_SLEEP_SECOND)
         max_sleep_second = int(conf.MAX_SLEEP_SECOND)
+
         while self.switch:
         while self.switch:
             # 1. 从队列获取文件信息
             # 1. 从队列获取文件信息
             doc_info, doc_class, doc_id, business_type = self.get_doc_info()
             doc_info, doc_class, doc_id, business_type = self.get_doc_info()
+
             # 2. 从EDMS获取PDF文件
             # 2. 从EDMS获取PDF文件
             doc_data_path, excel_path, pdf_path = self.pdf_download(doc_id, doc_info, business_type)
             doc_data_path, excel_path, pdf_path = self.pdf_download(doc_id, doc_info, business_type)
+
             # 队列为空时的处理
             # 队列为空时的处理
             if pdf_path is None:
             if pdf_path is None:
                 time.sleep(sleep_second)
                 time.sleep(sleep_second)
                 sleep_second = min(max_sleep_second, sleep_second+5)
                 sleep_second = min(max_sleep_second, sleep_second+5)
                 continue
                 continue
+
             sleep_second = int(conf.SLEEP_SECOND)
             sleep_second = int(conf.SLEEP_SECOND)
             try:
             try:
                 # 3.PDF文件提取图片
                 # 3.PDF文件提取图片
@@ -280,6 +282,7 @@ class Command(BaseCommand, LoggerMixin):
                     self.cronjob_log.info('{0} [pdf to img success] [doc_id={1}]'.format(self.log_base, doc_id))
                     self.cronjob_log.info('{0} [pdf to img success] [doc_id={1}]'.format(self.log_base, doc_id))
 
 
                 write_zip_file(img_save_path, os.path.join(doc_data_path, '{0}_img.zip'.format(doc_id)))
                 write_zip_file(img_save_path, os.path.join(doc_data_path, '{0}_img.zip'.format(doc_id)))
+
                 # 4.图片调用算法判断是否为银行流水, 图片调用算法OCR为excel文件
                 # 4.图片调用算法判断是否为银行流水, 图片调用算法OCR为excel文件
                 wb = xlwt.Workbook()
                 wb = xlwt.Workbook()
                 loop = asyncio.get_event_loop()
                 loop = asyncio.get_event_loop()
@@ -288,7 +291,9 @@ class Command(BaseCommand, LoggerMixin):
                 # loop.close()
                 # loop.close()
                 wb.save(excel_path)  # TODO no sheet (res always [])
                 wb.save(excel_path)  # TODO no sheet (res always [])
                 # 整合excel文件
                 # 整合excel文件
+
                 # 5.上传至EDMS
                 # 5.上传至EDMS
+
             except Exception as e:
             except Exception as e:
                 doc_class.objects.filter(id=doc_id).update(status=DocStatus.PROCESS_FAILED.value)
                 doc_class.objects.filter(id=doc_id).update(status=DocStatus.PROCESS_FAILED.value)
                 self.cronjob_log.error('{0} [process failed] [doc_id={1}] [err={2}]'.format(self.log_base, doc_id, e))
                 self.cronjob_log.error('{0} [process failed] [doc_id={1}] [err={2}]'.format(self.log_base, doc_id, e))

@@ -9,6 +9,8 @@ WSDL_DIR = os.path.join(os.path.dirname(BASE_DIR), 'wsdl')
 SECRET_CONF_FILE = os.path.join(SECRET_CONF_DIR, 'secret.ini')
 SECRET_CONF_FILE = os.path.join(SECRET_CONF_DIR, 'secret.ini')
 LOGGING_CONFIG_FILE = os.path.join(COMMON_CONF_DIR, 'logging.conf')
 LOGGING_CONFIG_FILE = os.path.join(COMMON_CONF_DIR, 'logging.conf')
 SM_WSDL = os.path.join(WSDL_DIR, 'SessionManager.wsdl')
 SM_WSDL = os.path.join(WSDL_DIR, 'SessionManager.wsdl')
+DM_WSDL = os.path.join(WSDL_DIR, 'DocumentManager.wsdl')
+DF_WSDL = os.path.join(WSDL_DIR, 'DocumentFinder.wsdl')
 
 
 # 文件存放根目录
 # 文件存放根目录
 LOG_DIR = os.path.join(os.path.dirname(BASE_DIR), 'logs')
 LOG_DIR = os.path.join(os.path.dirname(BASE_DIR), 'logs')

 [settings]
 [settings]
 DEBUG = False
 DEBUG = False
 SLEEP_SECOND = 5
 SLEEP_SECOND = 5
-MAX_SLEEP_SECOND = 60
\ No newline at end of file
+MAX_SLEEP_SECOND = 60
+
+EDMS_DOWNLOAD_URL = https://edms-test.bmw.com/FH/FileHold/DocumentRepository/DownloadHandler.ashx
\ No newline at end of file

@@ -2,3 +2,5 @@
 DEBUG = True
 DEBUG = True
 SLEEP_SECOND = 5
 SLEEP_SECOND = 5
 MAX_SLEEP_SECOND = 60
 MAX_SLEEP_SECOND = 60
+
+EDMS_DOWNLOAD_URL = https://edms-test.bmw.com/FH/FileHold/DocumentRepository/DownloadHandler.ashx
\ No newline at end of file

@@ -2,3 +2,5 @@
 DEBUG = False
 DEBUG = False
 SLEEP_SECOND = 5
 SLEEP_SECOND = 5
 MAX_SLEEP_SECOND = 60
 MAX_SLEEP_SECOND = 60
+
+EDMS_DOWNLOAD_URL = https://edms-test.bmw.com/FH/FileHold/DocumentRepository/DownloadHandler.ashx